Target video generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a target video generation method and device, electronic equipment and a storage medium. The method comprises the following steps: determining reference image feature information associated with at least one reference shooting device in a target area and shooting time corresponding to the reference image feature information, wherein a reference image is a global image obtained when the reference shooting device shoots a snapshot target; determining the corresponding shooting time when the same snapshot target is shot by different reference shooting devices according to the reference image feature information associated with the at least one reference shooting device and the shooting time corresponding to the reference image feature information; and determining target video information corresponding to the same snapshot target according to the corresponding shooting time when the same snapshot target is shot by different reference shooting devices. According to the technical scheme, the integration and utilization efficiency of the video information of the same snapshot target shot by different shooting devices can be improved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, electronic device, and storage medium for generating target videos. Background Technology

[0002] With the rise and development of short video technology, people frequently use short videos to record important and memorable moments during their travels. Taking scenic spots as an example, more and more scenic spots are using security cameras to capture the moments of visitors, editing and processing short videos from different locations to create exciting short videos of the visit in chronological order. However, capturing gestures, expressions, or postures through cameras to create short videos and saving them to the server system consumes storage space. For example, during peak travel seasons, there are many people capturing videos, resulting in a large volume of short videos to save, leading to high storage space requirements, high bandwidth costs, and slow retrieval speeds. This results in long video retrieval times for captured targets and heavy pressure on the server. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for generating target videos, in order to solve the problems of repeated real-time editing required for each video acquisition, long video acquisition time, high server pressure, and large storage consumption of videos.

[0004] In a first aspect, embodiments of the present invention provide a method for generating a target video, the method comprising:

[0005] Determine the reference image feature information associated with at least one reference shooting device in the target area and the shooting time corresponding to the reference image feature information, wherein the reference image is a global image acquired by the reference shooting device when shooting the target;

[0006] Based on the reference image feature information associated with each of at least one reference shooting device and the shooting time corresponding to the reference image feature information, the shooting time corresponding to the same target being captured by different reference shooting devices is determined.

[0007] Based on the shooting time when the same target is captured by different reference shooting devices, the target video information corresponding to the same target is determined.

[0008] Secondly, embodiments of the present invention also provide a target video generation apparatus, the apparatus comprising:

[0009] The first determining module is used to determine the reference image feature information associated with at least one reference shooting device in the target area and the shooting time corresponding to the reference image feature information, wherein the reference image is a global image acquired by the reference shooting device when shooting the target;

[0010] The second determining module is used to determine the shooting time when the same target is captured by different reference shooting devices based on the reference image feature information associated with each of the at least one reference shooting devices and the shooting time corresponding to the reference image feature information.

[0011] The third determination module is used to determine the target video information corresponding to the same capture target based on the shooting time when the same capture target is captured by different reference shooting devices.

[0012] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0013] One or more processors;

[0014] Storage device for storing one or more programs.

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the target video generation method as provided in any embodiment of the present invention.

[0016] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the target video generation method as provided in any embodiment of the present invention.

[0017] The technical solution of this invention determines the reference image feature information associated with at least one reference shooting device in the target area and the corresponding shooting time. Each reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target. This enables comprehensive analysis of the image content and provides a basis for accurate identification of the target. Furthermore, based on the reference image feature information associated with at least one reference shooting device and the corresponding shooting time, the shooting time corresponding to the same target being captured by different reference shooting devices is determined. This achieves accurate positioning of the shooting time corresponding to the same target being captured by different shooting devices, which helps to construct a complete activity trajectory and timeline of the same target. It can integrate images of the same target captured by different shooting devices into target video information, restoring the complete video of the target. This solves the problems of repeated real-time editing required for each video acquisition, long video acquisition time, high server pressure, and large video storage requirements. It improves the efficiency of integrating and utilizing video information captured by different shooting devices on the same target.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] The above and other features, advantages, and aspects of the various embodiments of the present invention will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 This is a flowchart illustrating a target video generation method provided in an embodiment of the present invention;

[0021] Figure 2 This is a flowchart illustrating another target video generation method provided in an embodiment of the present invention;

[0022] Figure 3 This is a flowchart illustrating another target video generation method provided in an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the structure of a target video generation device provided in an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing a target video generation method provided in an embodiment of the present invention. Detailed Implementation

[0025] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0026] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0027] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0028] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0029] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0030] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0031] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0032] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application program, server, or storage medium executing the operation of this invention, based on the prompt message.

[0033] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0034] It is understood that the above notification and user authorization process is merely illustrative and does not constitute a limitation on the implementation of the present invention. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present invention.

[0035] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0036] To better understand the technical solution of this application, we will first briefly introduce the background of the solution. Taking the sequential travel and play in scenic areas involving tracks, slides and other target areas as an example, more and more scenic projects are starting to use cameras to capture exciting short video moments of the target's travel. The short videos captured by cameras at different locations are then edited and processed to finally provide a short video generated according to the order of the captured target's tour. The captured target can obtain their own exciting short video of the tour.

[0037] Cameras typically capture images of a target's gestures, expressions, or postures, storing these short videos on a server. However, during peak tourist seasons, scenic areas have numerous targets, and the same target may be captured repeatedly, resulting in a large volume of short videos requiring significant storage space and high bandwidth costs. This slows down the retrieval speed for user-requested videos, requiring longer access times and placing considerable pressure on the server. The following detailed implementation examples illustrate this:

[0038] Figure 1 This is a flowchart illustrating a target video generation method provided in an embodiment of the present invention. The technical solution of this embodiment is applicable to the integration of video information of the same target captured by multiple shooting devices. The method can be executed by a target video generation device, which can be implemented in the form of software and / or hardware, and is generally integrated on any electronic device with network communication function, such as a mobile terminal, PC, or server.

[0039] like Figure 1 As shown, the target video generation method of this invention may include the following processes:

[0040] S110. Determine the reference image feature information associated with at least one reference shooting device in the target area and the shooting time corresponding to the reference image feature information. The reference image is a global image acquired by the reference shooting device when shooting the target.

[0041] Among them, the reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target.

[0042] A target area can refer to a specific geographical or spatial range pre-determined using multiple pre-deployed reference shooting devices to achieve a specific shooting purpose. Multiple reference shooting devices are deployed within the target area. The target area can be defined based on the shooting points traversed when using each reference shooting device; for example, if shooting a scenic area's track system, reference shooting devices are deployed at pre-defined locations associated with the track. The target area can be delineated based on the shooting points traversed when using each reference shooting device.

[0043] When a target enters the shooting field of view of the reference shooting device, the reference shooting device can perform image feature analysis on the captured image within its shooting field of view to obtain one or more reference image feature information associated with the reference shooting device. In this way, the global image features of the captured image formed when the reference shooting device captures an image of the target can be described using the reference image feature information. Simultaneously, when capturing an image of the target, the shooting time corresponding to each of the one or more reference image feature information obtained from the image feature analysis of the reference shooting device is recorded.

[0044] Optionally, the global image features of the captured image can refer to the key elements or attribute features that can describe and distinguish the corresponding image content of the captured image. For example, the global image features of the captured image can be represented by at least one of the following: color features, shape features, texture features, spatial relationship features, and background features.

[0045] Optionally, color features describe the distribution and variation of colors in an image, and can be represented using the mean, variance, histogram, etc. For example, an image with blue as the dominant color will have significantly different color features than an image with red as the dominant color. Texture features reflect the spatial distribution patterns of pixel gray levels in an image, such as roughness and directionality; wood grain and fabric textures, for instance, have unique texture features. Shape features describe the shape of objects in an image, such as circles, squares, and irregular shapes, as well as parameters like perimeter and area, such as identifying the outline of a car. Spatial relationship features refer to the position, distance, and orientation relationships between different objects in an image; for example, the relationship between a person's position in a scene and the surrounding scenery. Background features can be the characteristics of the image content that serves as a backdrop to the target.

[0046] S120. Based on the reference image feature information associated with each of the at least one reference shooting device and the shooting time corresponding to the reference image feature information, determine the shooting time corresponding to when the same target is shot by different reference shooting devices.

[0047] In scenarios involving motion capture on track vehicles or water slides, the relatively fixed pose of the target makes it ineffective to filter and deduplicate images solely based on this information. However, by identifying the associated reference image feature information and capture time for each reference shooting device, and using this reference image feature information to describe the global image features of the captured scene, the limitations of relying solely on target pose information are overcome. This way, even with a fixed target pose, other elements in the captured scene, such as the position and speed of the track vehicle, the surrounding environment, and changes in lighting, can be represented using the reference image feature information.

[0048] When using various reference shooting devices to capture images for image acquisition, the description of the global image features of the captured images provides a more comprehensive and richer basis for filtering and deduplicating captured videos. Even if the captured targets have similar postures on the track vehicle or water ski, the subtle differences in the surrounding environment of the reference shooting devices and the different shooting angles can be reflected in detail in the global image features of the captured images, thereby effectively distinguishing and identifying captured images for different captured targets.

[0049] For example, when multiple reference shooting devices capture images of a target on a water slide, even though the target's posture may be similar, the reference image features—such as the varying number of trees in the background due to the device's position at a given moment, changes in the angle of light resulting in different lighting effects on the target, or differences in the shooting angle causing variations in the target's proportion and presentation in the image—can help accurately distinguish between capture images of different targets, avoid redundant filtering, quickly obtain the required effective capture images, and thus improve the efficiency of the entire capture and filtering process.

[0050] Furthermore, without the need for complex pose analysis of the captured target, it can quickly and accurately determine which reference image feature information corresponds to similar or identical captured targets in the captured images based directly on the similarity between the reference image feature information. It can initially merge and deduplicate reference image feature information with similarity, and quickly generate the captured images corresponding to the same captured target when captured by different reference shooting devices. In this way, it can find the reference image feature information corresponding to the same captured target when captured by different reference shooting devices, and thus determine the corresponding shooting time when the same captured target is captured by different reference shooting devices, saving a lot of processing time and computing resources.

[0051] S130. Determine the target video information corresponding to the same target based on the shooting time when the same target is captured by different reference shooting devices.

[0052] When capturing the same target, multiple different reference shooting devices will participate, and each reference shooting device has its corresponding shooting time record. Therefore, the order of the capture images related to the target can be determined according to the shooting time recorded by different reference shooting devices for the same target, thus forming target video information about the same target.

[0053] By conducting in-depth analysis and systematic organization of the time data recorded by various reference shooting devices, it is possible to filter out all videos involving this target within a specific time range from numerous video clips, and effectively integrate and aggregate these video clips to ultimately construct a complete and clearly targeted target video information.

[0054] For example, in a 100-meter sprint race, multiple cameras capture images of a particular athlete from different angles. By examining the specific times each camera captured the athlete, we can determine all the video information about that athlete within a certain timeframe, such as a crucial stage of the race. This provides accurate and useful data for subsequent race analysis and highlight replays. In this way, we can provide accurate and highly valuable data support for important tasks such as in-depth race analysis and replaying of exciting moments.

[0055] By using the above method, and by analyzing and organizing the time recorded by each reference shooting device, a series of video clips about the same captured target within a specific time range can be selected and integrated to form a complete and targeted target video information.

[0056] As an optional but non-limiting implementation, the reference image feature information is also used to describe the local image features of the captured image formed when the reference shooting device captures an image of the target. The local image features are used to describe the appearance features of the target in the captured image. The appearance features are used to indicate the salient features and attributes of the target that can be directly perceived in appearance.

[0057] In certain situations, two targets may interfere with or overlap in a scene captured by the same camera. This "collision" or "ship collision" does not refer to a physical collision, but rather to the simultaneous appearance and mutual influence of two targets within the same camera's view. This situation increases the complexity of image feature information, often making it impossible to accurately identify the same target from multiple cameras using only image feature information.

[0058] Based on the above, the solution proposed in this application can extract some local image features from the captured image of the target. These local image features can describe the appearance of the target in the captured image. These appearance features typically refer to the salient features and attributes of the target that can be directly perceived. For example, the local image features can be characterized by the target's clothing style, clothing color, hat, glasses, etc.

[0059] Taking the peak season of scenic spots as an example, due to the large number of targets to be captured, multiple water slides often appear at the same time in actual track scenes, which is the so-called "collision" (boat collision) phenomenon. This situation where a large number of boats appear at the same time makes the global image features of the captured image extremely complex. It is often difficult to achieve accurate results by simply relying on background features to filter out the same target from multiple cameras.

[0060] In this context, the reference image feature information can not only describe the global image features of the captured image, but also depict the local image features of the captured image formed during the capture of the target. These local image features are mainly used to describe the appearance features of the captured target in the captured image, while appearance features indicate the salient features and attributes of the captured target that can be directly perceived in appearance.

[0061] This solution references both overall and local image features in its image feature information. It combines these features to handle situations where two targets exist within the captured image. It's important to understand that people in the background environment typically exhibit variations in clothing style, color, and whether they wear glasses or hats. Therefore, further comparison and filtering can be performed on these local features, such as clothing style, color, whether glasses are worn, and hat style. This allows for accurate identification of the same target from multiple reference image feature information linked to various shooting devices, even in complex situations like "collisions."

[0062] For example, taking an L1 camera, the global image feature of the captured image indicated in the reference image feature information is L1C1, and the local image feature is defined as L1J1. The clothing style feature is defined as L1Y1, the clothing color feature as L1Y2, the feature of whether glasses are worn corresponds to L1Y3, and the hat style feature is L1Y4. Then, L1J1 = L1Y1 + L1Y2 + L1Y3. The L1 camera reference image feature information can be updated as follows: L1 camera reference image feature information = a * L1C1 + b * L1J1, where a and b are the ratio coefficients of the global image feature and the local image feature of the captured image, respectively, and a + b = 1.

[0063] The above approach effectively addresses the challenging problem of filtering reference image feature information for the same captured target in complex background environments. When multiple targets appear simultaneously, drastically increasing background complexity, focusing on the local appearance features of the targets significantly improves the accuracy and reliability of the filtering process. Even in extremely cluttered backgrounds, the unique local features of the captured targets allow for accurate identification and tracking of the same target. Furthermore, it greatly enhances the adaptability and stability of the entire system. Whether in crowded and busy conditions like peak tourist seasons or other complex environments, it remains unaffected by interference from global image features, maintaining stable and reliable performance. Finally, it significantly saves time and computational resources for filtering and identification, avoiding extensive unnecessary analysis due to the complexity of global image features in the captured image, thus improving overall processing efficiency.

[0064] The technical solution of this invention determines the reference image feature information associated with at least one reference shooting device in the target area and the corresponding shooting time. Each reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target. This enables comprehensive analysis of the image content and provides a basis for accurate identification of the target. Furthermore, based on the reference image feature information associated with at least one reference shooting device and the corresponding shooting time, the shooting time corresponding to the same target being captured by different reference shooting devices is determined. This achieves accurate positioning of the shooting time corresponding to the same target being captured by different shooting devices, which helps to construct a complete activity trajectory and timeline of the same target. It can integrate images of the same target captured by different shooting devices into target video information, restoring the complete video of the target. This solves the problems of repeated real-time editing required for each video acquisition, long video acquisition time, high server pressure, and large video storage requirements. It improves the efficiency of integrating and utilizing video information captured by different shooting devices on the same target.

[0065] Figure 2 This is a flowchart illustrating another target video generation method provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the process of determining the reference image feature information associated with at least one reference shooting device in the target area in the foregoing embodiments based on the technical solutions of the above embodiments. This embodiment can be combined with various optional solutions in one or more of the above embodiments.

[0066] like Figure 2 As shown, the target video generation method of this invention may include the following processes:

[0067] S210. For at least one reference shooting device in the target area, determine the candidate image feature information associated with the reference shooting device. The candidate image is a global image of the captured scene formed when the reference shooting device captures an image.

[0068] Among them, candidate image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image.

[0069] For each reference shooting device, the reference shooting device will capture images within its own shooting angle range to obtain the corresponding shooting scene. The target may or may not have entered the shooting angle range of the reference shooting device. At this time, one or more candidate image feature information can be obtained to describe in detail the global image features of the shooting scene formed when the reference shooting device captures and acquires images.

[0070] The candidate image features provided by the above method can achieve a comprehensive and detailed depiction of the features of the captured image. Whether the captured image contains a target or not, there is corresponding specific feature information for precise description, which makes the understanding and cognition of the captured image formed by the reference shooting device when capturing and acquiring the image more complete and in-depth, without any omissions or oversights.

[0071] S220. Determine the static image feature information associated with the reference shooting device. The static image feature information includes a description of the global image features of the captured image formed when the reference shooting device captures an image, provided that there are no dynamic target elements within the shooting angle range of the reference shooting device.

[0072] The classification process focuses on the scene conditions captured by a single reference imaging device. Static image feature information primarily describes situations where no dynamic target elements exist within the shooting field of view of the reference imaging device. In other words, static image feature information focuses on specific cases where no dynamic target elements are present within the shooting field of view of the reference imaging device. That is, when the image captured by the reference imaging device does not contain a target, the global image features of the image acquired by the reference imaging device are described using static image feature information.

[0073] If the shooting scene of the reference shooting device does not contain any targets such as scooters or water slides, then the shooting scene of the reference shooting device is defined as a static background, and the global image features of the captured image formed when the reference shooting device captures the image will be recorded as static image features associated with the reference shooting device. However, if it is unclear whether scooters, water slides, or targets appear in the shooting scene of the reference shooting device, then these are defined as global image features of the captured image formed when the reference shooting device captures the image, and the extracted features will be recorded as candidate image feature information associated with the reference shooting device.

[0074] S230. Based on the candidate image feature information and static image feature information associated with the reference shooting device, determine the reference image feature information associated with the reference shooting device from the candidate image feature information. The reference image is the global image acquired by the reference shooting device when shooting the target.

[0075] Among them, the reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target.

[0076] For each individual reference imaging device, a static feature library is constructed. This library records the global image features of the captured image when the reference imaging device captures and acquires images in a static scene (i.e., without dynamic target elements, such as moving objects or people). Then, image feature similarity is compared between the candidate image feature information (which may include image features from various scenes) associated with the reference imaging device and the static image feature information (image features only in static scenes). The reference image feature information associated with the reference imaging device is then selected and determined from the candidate image feature information. The reference image feature information primarily describes in detail the global image features of the captured image formed when the reference imaging device captures and acquires images of the target.

[0077] By adopting the above approach and establishing a static feature library, a benchmark and comparative basis can be provided for subsequent image analysis and processing, which helps to more accurately identify and extract effective image features. Clearly distinguishing between static and dynamic scenes helps to more accurately grasp the nature and characteristics of the scene, providing a clear premise for subsequent image processing and analysis. In actual snapshot capture, comparison with the static background feature library can more effectively identify reference image feature information, including the target image, improving the accuracy of detection and tracking.

[0078] As an optional but non-limiting implementation, determining the still image feature information associated with the reference capturing device includes the following steps A1-A2:

[0079] Step A1: Determine the reference shooting environment attribute conditions when capturing images of the target using the reference shooting device to obtain reference image feature information. The reference shooting device has dynamically adjusted and updated static image feature information matched for each type of shooting environment attribute condition.

[0080] Step A2: Match the static image feature information corresponding to the reference shooting environment attribute conditions to determine the static image feature information associated with the reference shooting device.

[0081] Because the static scene of the reference shooting device is not always constant, when the static scene of the reference shooting device changes—for example, during the alternation of day and night, the changing of the four seasons, or different shooting environment attributes such as sunny and rainy days—the corresponding shooting scene of the reference shooting device will actually vary significantly. Therefore, it is necessary to reasonably classify and update the static scene of the reference shooting device in a timely manner.

[0082] When using a reference shooting device to capture images of a target to obtain reference image feature information, the corresponding reference shooting environment attributes are specified. These attributes may include, but are not limited to, factors such as light intensity, light color, weather conditions (e.g., sunny, cloudy, rainy), shooting location (indoor, outdoor), and shooting time (daytime, nighttime). Furthermore, for each type of shooting environment attribute, the reference shooting device dynamically adjusts and updates the corresponding static image feature information. By using the determined reference shooting environment attribute conditions to match the pre-stored static image feature information, the static image feature information associated with the current reference shooting device is determined.

[0083] By adopting the above method and considering the shooting environment attributes, we can more accurately obtain static image feature information that matches the actual shooting situation, making the shooting results more in line with expectations. It can adapt to various shooting environments, whether it is complex and ever-changing lighting conditions or different weather and locations, and can obtain appropriate feature information. This allows for adjustments and optimizations based on the matched static image feature information, regardless of how the shooting environment changes, thereby ensuring the relative stability of image quality.

[0084] As an optional but not limited implementation method, the shooting environment attribute conditions are determined by describing the image characteristics of the specified sub-screen area. The specified sub-screen area is the sub-screen area that the target has not entered after the image is segmented into the shooting screen formed when the shooting device captures the image.

[0085] In the shooting scenario of the reference shooting equipment, the position of the track vehicle or water slide boat in the shooting frame is usually relatively fixed. To eliminate the influence of dynamic areas on the global image feature judgment of the shooting image, specific regions can be pre-drawn and segmented in the shooting scene, dividing the entire shooting image into moving and static regions. For the static region, features can be extracted at fixed time intervals, and the features extracted at fixed intervals can be initially classified according to the time of day, such as roughly distinguishing the time of day into four categories: morning, daytime, evening, and night.

[0086] Then, each day, similarity is calculated between the static area features at the same time the previous day, based on these four dimensions. Once the similarity falls below a pre-set threshold, it indicates a significant change in the scene, triggering the system to automatically record the global image features and scene of the captured image at that time. Subsequently, humans can intervene, reviewing the before and after scenes based on the system's records and labeling them accordingly, such as rainy, sunny, cloudy, snowy, or seasonal information (spring, summer, autumn, winter). Through this iterative process, the static image feature information associated with the shooting device is continuously updated, and the robustness and adaptability of the static image feature information associated with the shooting device are continuously improved.

[0087] By employing the above approach, precisely segmenting the scene into dynamic and static regions and classifying and comparing features according to time, changes in static scenes can be captured more accurately, thereby improving the accuracy of background feature judgment. Furthermore, the continuously updated static background feature library allows for better adaptation to various environmental and seasonal changes, enhancing its ability to function in complex scenarios. In addition, timely detection and recording of significant scene changes reduces system errors and instability caused by scene variations, enhancing system reliability and stability. Targeted updates to the feature library avoid unnecessary data processing and storage, improving the efficiency of system resource utilization.

[0088] As an optional but non-limiting implementation, the reference image feature information associated with the reference shooting device is determined from the candidate image feature information based on the candidate image feature information and the still image feature information associated with the reference shooting device, including the following steps B1-B2:

[0089] Step B1: Detect the image feature information comparison results between the candidate image feature information associated with the reference shooting device and the static image feature information. The image feature information comparison results are described by the similarity and / or difference between the image feature information.

[0090] Step B2: Based on the comparison results of image feature information, determine the reference image feature information associated with the reference shooting device from the candidate image feature information. The similarity between the reference image feature information and the static image feature information is less than a preset similarity threshold or the difference is greater than a preset difference threshold.

[0091] The comparison results of candidate image feature information and static image feature information associated with a reference shooting device are obtained by detecting the relationship between them. The comparison results are expressed through similarity and / or difference between the image feature information. Specifically, similarity measures the degree of similarity between two image feature information, with higher values ​​indicating greater similarity; difference reflects the degree of difference between the reference image feature information and the static image feature information, with higher values ​​indicating greater difference. Using this method, the relationship between candidate image feature information and static image feature information can be accurately measured through similarity and difference descriptions. Considering both similarity and difference allows for a comprehensive evaluation of the image feature comparison from multiple perspectives.

[0092] Based on the comparison results of the obtained image feature information, the reference image feature information associated with the reference capturing device is identified from the candidate image feature information. There is a certain relationship between the reference image feature information and the static image feature information; that is, the similarity between the reference image feature information and the static image feature information is less than a pre-set similarity threshold, or the difference between the reference image feature information and the static image feature information is greater than a pre-set difference threshold. Using the above method, by setting thresholds, reference image feature information with significant differences can be effectively filtered from numerous candidate image feature information, ensuring that the selected reference image feature information can be clearly distinguished from the static image feature information, thereby providing more valuable information for subsequent processing and analysis.

[0093] For example, for each independent reference shooting device, a static feature library associated with each reference shooting device needs to be established. Assume the static image feature information stored in the static feature library of the L1 shooting device is L1K1, L1K2, L1K3…L1Km, and similarly, the static image feature information stored in the static feature library of the Ln shooting device is LnK1, LnK2, LnK3…LnKm. Taking the L1 camera as an example, the cosine distance similarity L1S1 between the candidate image feature information L1C1 associated with the L1 shooting device and the static image feature information L1K1 stored in the static feature library is calculated. When L1S1 is less than 0.1 (the similarity threshold, which can be adjusted as needed), it indicates that the image captured by the L1 shooting device has changed significantly. Therefore, the candidate image feature information L1C1 is recorded in the dynamic feature library of the L1 camera as the reference image feature information associated with the reference shooting device. Simultaneously, the shooting time corresponding to the candidate image feature information L1C1 also needs to be recorded.

[0094] As an optional but non-limiting implementation, at least one reference shooting device in the target area sequentially captures the same target in a preset shooting order. Each of the at least one reference shooting device is installed in a different position and corresponds to a different shooting scene. Each reference shooting device is configured to ensure that the sharpness of a preset part of the target meets a preset sharpness when capturing the target.

[0095] This solution is applicable in scenarios where multiple reference shooting devices within a target area are configured to sequentially capture the same target in a preset shooting order. Examples include track-based attractions within a scenic area, where the target rides fixed facilities in a fixed sequence, such as roller coasters, water slides, scooters, or semi-open chairlifts. Its characteristics include: a strict sequential relationship between the reference shooting devices installed along the attraction; the scene corresponding to each reference shooting device is generally unique; and the target's body or face is partially visible in the shooting scene, allowing for clear differentiation. Feature clarity can be described by whether the target's preset features, such as facial contours, hairstyle, and unique clothing markings, are clearly identifiable.

[0096] Optionally, the shooting order is configured to allow multiple reference shooting devices within the target area to shoot the same target sequentially according to a preset shooting order. Here, it is necessary to calculate and update the time interval between two adjacent reference shooting devices according to the shooting order.

[0097] In an optional example, taking a scenic area as the target region, n reference shooting devices are deployed along the scenic area's track scene. These reference shooting devices are labeled L1, L2, L3…Ln according to the order of visit, and the time intervals between two reference shooting devices are assumed to be t12, t23,…tnn-1. Typically, the time difference between reference shooting devices can be pre-calibrated manually using a watch. However, this manual calculation becomes very cumbersome when there are many projects. Furthermore, if a point in a project moves, the time marking needs to be re-established. A better approach is to use initial manual time calibration followed by automatic iterative calculation of time intervals. The initial time intervals between the points of each reference shooting device can be obtained through human observation, i.e., recording the time points when the same target passes different reference shooting devices.

[0098] In one optional example, the time points corresponding to the same captured target passing through different reference shooting devices can be obtained. By calculating the time difference between the time points corresponding to the passing through different reference shooting devices, the actual time interval between different reference shooting devices can be automatically obtained. To improve the accuracy of the time interval, a Gaussian averaging method is used, with one day as the unit, to count the time difference of the same camera position passing through all cameras in one day. For example, the time difference of captured target M1 from reference shooting devices L1 to Ln is M1L12, M1L23, ..., M1Lnn-1, then the time difference of captured target Mx from L1 to Ln is MxL12, MxL23, ..., MxLnn-1. The time interval between reference shooting devices L1 and L2 can be calculated using the average value of M1L12...MxL12. To eliminate the influence of outliers, the maximum and minimum values ​​of M1L12...MxL12 can be removed before averaging.

[0099] S240. Based on the reference image feature information associated with each of the at least one reference shooting devices and the shooting time corresponding to the reference image feature information, determine the shooting time corresponding to when the same target is shot by different reference shooting devices.

[0100] S250. Based on the shooting time corresponding to the same target being captured by different reference shooting devices, determine the target video information corresponding to the same target.

[0101] The technical solution of this invention determines the reference image feature information associated with at least one reference shooting device in the target area and the corresponding shooting time. Each reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target. This enables comprehensive analysis of the image content and provides a basis for accurate identification of the target. Furthermore, based on the reference image feature information associated with at least one reference shooting device and the corresponding shooting time, the shooting time corresponding to the same target being captured by different reference shooting devices is determined. This achieves accurate positioning of the shooting time corresponding to the same target being captured by different shooting devices, which helps to construct a complete activity trajectory and timeline of the same target. It can integrate images of the same target captured by different shooting devices into target video information, restoring the complete video of the target. This solves the problems of repeated real-time editing required for each video acquisition, long video acquisition time, high server pressure, and large video storage requirements. It improves the efficiency of integrating and utilizing video information captured by different shooting devices on the same target. Most importantly, this solution does not rely on facial features. It only uses the image features of the captured image and the location information of the captured target to solve the problem of target selection and deduplication when the face is obscured or the capture is poor. This allows us to obtain a short video of the same captured target recorded by each reference shooting device, which can then be merged into a wonderful short travel video.

[0102] Figure 3 This is a flowchart illustrating another target video generation method provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the process in the foregoing embodiment of determining the shooting time corresponding to the same target being shot by different reference shooting devices based on the reference image feature information associated with at least one reference shooting device and the shooting time corresponding to the reference image feature information. This embodiment can be combined with various optional solutions in one or more of the above embodiments.

[0103] like Figure 3 As shown, the target video generation method of this invention may include the following processes:

[0104] S310. Determine the reference image feature information associated with at least one reference shooting device in the target area and the shooting time corresponding to the reference image feature information. The reference image is a global image acquired by the reference shooting device when shooting the target.

[0105] Among them, the reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target.

[0106] S320. For at least one reference shooting device, determine the target image feature information associated with the reference shooting device based on the reference image feature information associated with the reference shooting device. The similarity between the target image feature information associated with the reference shooting device is greater than the similarity between the remaining reference image feature information (excluding the target image feature information associated with the reference shooting device) in the reference image feature information associated with the same reference shooting device. Furthermore, the similarity between the target image feature information associated with adjacent reference shooting devices in terms of shooting order is greater than the similarity between the remaining reference image feature information (excluding the target image feature information associated with the reference shooting device) in the reference image feature information associated with the same reference shooting device.

[0107] Since at least one reference shooting device in the target area sequentially captures the same target in a preset shooting order, and considering the continuity of the same target when it is captured, the reference image feature information corresponding to the same target captured by the same reference shooting device should be relatively similar. Therefore, by combining the similarity between the reference image feature information associated with each reference shooting device, the reference image feature information associated with the same reference shooting device with a high degree of similarity can be filtered out. This satisfies the requirement that the similarity between the target image feature information associated with adjacent reference shooting devices in the shooting order is greater than the similarity between the remaining reference image feature information associated with the same reference shooting device, excluding the target image feature information.

[0108] At the same time, the reference image feature information corresponding to two adjacent reference shooting devices when capturing the same target should also be relatively similar. Therefore, based on the similarity between the reference image feature information associated with adjacent reference shooting devices, the reference image feature information obtained when the same target is captured by different reference shooting devices can be further filtered out on the basis of the reference image feature information with high similarity associated with the same reference shooting device, and used as the target image feature information associated with each reference shooting device.

[0109] By employing the above method, and analyzing the similarity of feature information in reference images, we can more accurately determine the relevant image features of the same captured target, reduce misjudgments, and only filter out feature information with high similarity. This avoids processing and storing a large amount of irrelevant or low-similarity image data, saving system resources. Furthermore, based on the continuity of the captured target and the shooting order of the shooting equipment, the selected target image feature information is more coherent and logical.

[0110] S330. Based on the shooting time corresponding to the target image feature information associated with each of the at least one reference shooting devices, determine the shooting time corresponding to the same target being captured by different reference shooting devices.

[0111] Based on at least one reference shooting device, each reference shooting device is associated with a target image feature information with a corresponding shooting time. By analyzing and processing these shooting times, the specific shooting times corresponding to the same target when it is captured by different reference shooting devices can be determined. Then, the images corresponding to the images captured by each reference shooting device in chronological order can be combined to form the target video information.

[0112] By adopting the above method, we can ensure that the shooting time of the target is fully and accurately recorded, without missing any important moments, reducing confusion and errors in time information processing, improving the efficiency and accuracy of the entire image processing process, and thus more effectively filtering and selecting the most suitable images based on the shooting time, such as images within a specific time period.

[0113] As an optional but non-limiting implementation, determining the target image feature information associated with the reference imaging device based on the reference image feature information associated with the reference imaging device includes the following steps C1-C3:

[0114] Step C1: When the reference shooting device is the first shooting device, cluster the feature information of each reference image associated with the first shooting device to obtain at least two reference image feature cluster groups; wherein, the first shooting device is the first reference shooting device to be processed among at least one reference shooting device.

[0115] Step C2: For each reference image feature cluster, determine the similarity between the reference image feature information in the reference image feature cluster.

[0116] Step C3: Determine the target image feature information associated with the first imaging device based on the similarity between the reference image feature information in each reference image feature cluster group.

[0117] For example, taking the first shooting device as an L1 reference shooting device, a time window Wt (the maximum time that the target can appear in the scene) can be set in the same L1 reference shooting device. In this time window, all the reference image feature information associated with the L1 reference shooting device is clustered to obtain the set of reference image feature information with the highest similarity and the shooting time corresponding to the reference image feature information. In this way, the target image feature information associated with the L1 reference shooting device can be obtained.

[0118] As an optional but non-limiting implementation, the target image feature information associated with the reference shooting device is determined based on the reference image feature information associated with the reference shooting device, including the following steps D1-D2:

[0119] Step D1: When the reference shooting device is the second shooting device, determine the target image feature information associated with the third shooting device. The similarity between the target image feature information associated with the third shooting device is greater than the similarity between the remaining reference image feature information in the reference image feature information associated with the third shooting device, excluding the target image feature information associated with the third shooting device. Wherein, the second shooting device is not the first reference shooting device to be processed among at least one reference shooting device, and the third shooting device is the reference shooting device that was processed before the second shooting device and is adjacent to the second shooting device in the shooting order among at least one reference shooting devices.

[0120] Step D2: Based on the target image feature information associated with the third shooting device and the reference image feature information associated with the second shooting device among at least one reference shooting device, determine the target image feature information associated with the second shooting device. The similarity between the target image feature information associated with the third shooting device and the target image feature information associated with the second shooting device is greater than the similarity between the target image feature information associated with the third shooting device and the remaining reference image feature information associated with the second shooting device, excluding the target image feature information associated with the second shooting device.

[0121] When the reference imaging device is the second imaging device, the target image feature information associated with the third imaging device is determined. Here, the third imaging device is at least one of the reference imaging devices that is processed before the second imaging device and is adjacent to the second imaging device in the imaging order. Moreover, the similarity between the target image feature information associated with the third imaging device is greater than the similarity between the remaining reference image feature information excluding the target image feature information in the reference image feature information associated with the third imaging device.

[0122] Based on the above, the feature similarity between the target image feature information associated with the third shooting device and each of the reference image feature information associated with the second shooting device can be calculated according to the target image feature information associated with the third shooting device and the reference image feature information associated with the second shooting device. The reference image feature information associated with the second shooting device with the highest similarity to the target image feature information associated with the third shooting device is determined as the target image feature information associated with the second shooting device. This ensures that the similarity between the target image feature information associated with the third shooting device and the target image feature information associated with the second shooting device is greater than the similarity between the target image feature information associated with the third shooting device and the remaining reference image feature information associated with the second shooting device, excluding the target image feature information associated with the second shooting device.

[0123] By employing the above method, and through comparing and filtering the similarity of image feature information from adjacent shooting devices, the target image feature information of each shooting device can be determined more accurately, reducing errors and uncertainties. Considering the relationship between the feature information of adjacent devices in the shooting order ensures that the determined target image feature information has better temporal and spatial coherence, aligning with the actual shooting situation. Similarity-based comparison and filtering avoids processing a large amount of irrelevant or low-similarity image feature information, improving image processing efficiency. The accurate and coherent method for determining target image feature information contributes to improving the stability and reliability of the entire system, providing a more reliable data foundation for subsequent applications.

[0124] As an optional but non-limiting implementation, the target image feature information associated with the second shooting device is determined based on the target image feature information associated with the third shooting device and the reference image feature information associated with the second shooting device among at least one reference shooting device, including the following steps E1-E3:

[0125] Step E1: Determine the image feature information to be used associated with the third shooting device from the target image feature information associated with the third shooting device. The image feature information to be used associated with the third shooting device is obtained by sorting the target image feature information associated with the third shooting device according to the shooting time corresponding to the target image feature information associated with the third shooting device and then filtering it.

[0126] Step E2: Determine the similarity between the image feature information to be used associated with the third shooting device and the reference image feature information associated with the second shooting device.

[0127] Step E3: Based on the similarity between the reference image feature information associated with the second shooting device and the reference image feature information associated with the second shooting device, determine the target image feature information associated with the second shooting device from the reference image feature information associated with the second shooting device.

[0128] The target image feature information associated with the third imaging device may include multiple image feature information. Therefore, the target image feature information associated with the third imaging device is sorted according to the shooting time corresponding to it. The middle target image feature information and its corresponding shooting time are taken as the shooting time L1T1 and the image feature information to be used associated with the third imaging device L1B1. Then, the similarity between the image feature information to be used associated with the third imaging device and each reference image feature information associated with the second imaging device is calculated. Based on the similarity between the reference image feature information associated with the third imaging device and each reference image feature information associated with the second imaging device, the reference image feature information associated with the second imaging device with the highest similarity to the image feature information to be used associated with the third imaging device is determined as the target image feature information associated with the second imaging device.

[0129] The capture time corresponding to the target image feature information of the L1 reference shooting device is the time interval t12 shifted backward from L1T1. In the L2 reference shooting device, within the time window Wx before and after L1T1+t12, the best image feature information in the L1 reference shooting device is compared with the associated reference image features of the L2 reference shooting device to calculate similarity. This yields a set of image feature information that meets all the conditions in the L2 reference shooting device. Similarly, this set of features can be sorted by time point, and the middle image feature information and its capture time are taken as the capture time L2T2 corresponding to the target image feature information in the L2 reference shooting device. This process is repeated to obtain the target image feature information and the corresponding capture time for the same target in all reference shooting devices.

[0130] As an optional but non-limiting implementation, when determining the reference image feature information associated with at least one reference capturing device in the target area, the following steps F1-F3 are also included:

[0131] Step F1: Determine the reference shooting position when capturing the target image using the reference shooting device to obtain reference image feature information.

[0132] Step F2: Based on the reference shooting position and the position of the reference shooting device corresponding to the acquisition of reference image feature information, determine the relative distance between the position of the reference shooting device and the reference shooting position.

[0133] Step F3: If the relative distance between the location of the reference shooting device and the reference shooting location is less than a preset relative distance, the reference shooting location is bound to the reference image feature information, which is used to filter the target image feature information corresponding to the same capture target from the reference image feature information associated with at least one reference shooting device.

[0134] Since mobile phones and other terminals are now very common, people usually carry mobile phones and other terminal devices when they go out to capture images. Mobile phones and other terminals can communicate and transmit information with the outside world. By using the communication function of mobile phones and other terminals, they can be wirelessly connected to reference shooting devices. Based on the target image feature information associated with the reference shooting device, and superimposed with the positioning information of mobile phones and other terminals, a comprehensive judgment can be made, which can further improve the efficiency and accuracy of screening the same capture target.

[0135] In one optional example, the location information of the target's personal terminal device is introduced to assist in the screening and judgment: a special QR code is placed at the starting point for network connection between the terminal device and the reference shooting device. The target can scan the QR code to register on-site and enter an app, obtaining a unique target code identifier. The app sends this target code identifier to all reference shooting devices along the track, and each reference shooting device records the target's code identifier. The app can obtain the target's GPS location information at any time and send the GPS location information to the reference shooting devices. Each reference shooting device receives its own location information sent by the target's terminal device at regular intervals (e.g., every 1 second) and compares it with the location coordinate information of the reference shooting device recorded in its own storage, continuously updating and retaining the location coordinate value of the target closest to the reference shooting device. When the reference shooting device determines that the target's location and the nearest location coordinate value of the reference shooting device are within a specified threshold range, it associates and binds the terminal location information with the reference image feature information at that time.

[0136] For example, scenic area rail or water slide projects are fixed amusement facilities that are played in a certain order, with a starting point and an ending point. First, at the starting point, a special QR code sign needs to be placed. Staff at the starting point guide the target to scan the code and download the app. Once registered, the target will receive a unique identification code.

[0137] (1) Reference camera location information marking: For reference cameras with built-in GPS positioning chips, the reference camera can automatically obtain its own GPS location coordinates; for reference cameras without GPS positioning chips, the location of the reference camera needs to be manually calibrated, and the obtained reference camera location coordinate information is stored inside the reference camera. Assume that the reference cameras along the track are set as follows: the coordinate position latitude and longitude information of reference camera L1 is L1(lon, lat), the coordinate position latitude and longitude information of reference camera L2 is L2(lon, lat)... the coordinate position latitude and longitude information of reference camera Ln is Ln(lon, lat), after the mobile phone used by the target M registers and enters, the target code identifier obtained is Mi, and the real-time coordinate position information of the target code identifier Mi can be represented by Mi(lon, lat).

[0138] (2) During the target's activity, the app on the target's terminal device periodically (assuming a time interval of 1 second) sends its own position coordinates Mi(lon, lat) to the reference shooting devices L1 to Ln. The reference shooting device Ln calculates in real time the distance between its own coordinates Ln(lon, lat) and the target's terminal device's position coordinates Mi(lon, lat), denoted as Ln(Gcdf). Ln(Gcdf) can then be expressed as:

[0139] Ln(Gcdf)=2×R×atan2(√a,√1-a)

[0140] Where R is a constant, i.e., the average radius of the Earth (approximately 6371 kilometers). The formula for calculating a is as follows:

[0141]

[0142] (3) When the distance between the reference shooting device Ln and the terminal device identifier Mi of the target to be captured is less than the set threshold (set as the variable distance), the reference shooting device records the reference image feature information at this time, and at the same time records the coordinate information of the terminal device. At this time, when storing the reference image feature information, the coded identifier and coordinate latitude and longitude position information corresponding to the reference image feature information are uniquely bound.

[0143] (4) Taking the reference shooting device L1 as an example, in addition to obtaining the reference image feature information L1C1=a*L1C1+b*L1J1 (a and b are the ratio coefficients of the global image feature information and the local image feature information of the shooting screen, respectively, a+b=1); at the same time, there is also the coded identifier Mi corresponding to the reference image feature information. Then, for all reference image feature information with the same coded identifier Mi, they can be clustered into one category for processing, thereby further narrowing the screening range and further improving the target screening accuracy.

[0144] S340. Based on the shooting time when the same target is captured by different reference shooting devices, determine the target video information corresponding to the same target.

[0145] The technical solution of this invention determines the reference image feature information associated with at least one reference shooting device in the target area and the corresponding shooting time. Each reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target. This enables comprehensive analysis of the image content and provides a basis for accurate identification of the target. Furthermore, based on the reference image feature information associated with at least one reference shooting device and the corresponding shooting time, the shooting time corresponding to the same target being captured by different reference shooting devices is determined. This achieves accurate positioning of the shooting time corresponding to the same target being captured by different shooting devices, which helps to construct a complete activity trajectory and timeline of the same target. It can integrate images of the same target captured by different shooting devices into target video information, restoring the complete video of the target. This solves the problems of repeated real-time editing required for each video acquisition, long video acquisition time, high server pressure, and large video storage requirements. It improves the efficiency of integrating and utilizing video information captured by different shooting devices on the same target.

[0146] Figure 4 This is a schematic diagram of a target video generation device provided in an embodiment of the present invention. The technical solution of the present invention is applicable to the situation of integrating video information of the same target captured by multiple shooting devices. The target video generation device can be implemented in the form of software and / or hardware, and is generally integrated on any electronic device with network communication function, such as a mobile terminal, PC or server.

[0147] like Figure 4 As shown, the target video generation apparatus of this embodiment may include the following:

[0148] The first determining module 410 is used to determine the shooting time corresponding to the reference image feature information associated with at least one reference shooting device in the target area and the shooting time of the reference image feature information. The reference image is a global image obtained by the reference shooting device when shooting the target.

[0149] The second determining module 420 is used to determine the shooting time when the same target is captured by different reference shooting devices based on the reference image feature information associated with each of the at least one reference shooting devices and the shooting time corresponding to the reference image feature information.

[0150] The third determining module 430 is used to determine the target video information corresponding to the same capture target based on the shooting time when the same capture target is captured by different reference shooting devices.

[0151] Based on the above embodiments, optionally, determining the reference image feature information associated with at least one reference capturing device in the target area includes:

[0152] For at least one reference imaging device, determine candidate image feature information associated with the reference imaging device, wherein the candidate image is a global image of the captured scene formed when the reference imaging device captures an image;

[0153] Determine the static image feature information associated with the reference shooting device. The static image feature information includes a description of the global image features of the shooting scene formed when the reference shooting device captures an image, provided that there are no dynamic target elements within the shooting angle range of the reference shooting device.

[0154] Based on the candidate image feature information and still image feature information associated with the reference shooting device, the reference image feature information associated with the reference shooting device is determined from the candidate image feature information.

[0155] Based on the above embodiments, optionally, determining the still image feature information associated with the reference capturing device includes:

[0156] When capturing images of a target using a reference shooting device, the corresponding reference shooting environment attribute conditions are determined. The reference shooting device is matched with dynamically adjusted and updated static image feature information under each type of shooting environment attribute condition.

[0157] Based on the reference shooting environment attribute conditions, the static image feature information corresponding to the reference shooting device is matched to determine the static image feature information associated with the reference shooting device.

[0158] Based on the above embodiments, optionally, the shooting environment attribute conditions are determined by describing the image characteristics of a specified sub-screen area. The specified sub-screen area is a sub-screen area that the target has not entered after the image is segmented into screen regions when the shooting device captures an image.

[0159] Based on the above embodiments, optionally, the reference image feature information associated with the reference shooting device is determined from the candidate image feature information according to the candidate image feature information and the still image feature information associated with the reference shooting device, including:

[0160] The image feature information comparison result between the candidate image feature information and the static image feature information associated with the reference shooting device is detected, and the image feature information comparison result is described by the similarity and / or difference between the image feature information;

[0161] Based on the comparison results of the image feature information, reference image feature information associated with the reference shooting device is determined from the candidate image feature information. The similarity between the reference image feature information and the static image feature information is less than a preset similarity threshold or the difference is greater than a preset difference threshold.

[0162] Based on the above embodiments, optionally, at least one reference shooting device in the target area is configured to sequentially shoot the same target according to a preset shooting order. Each of the at least one reference shooting device is installed in a different position and corresponds to a different shooting scene. Each reference shooting device is configured to ensure that the sharpness of a preset part of the target meets a preset sharpness when shooting the target.

[0163] Based on the above embodiments, optionally, the shooting time corresponding to when the same target is captured by different reference shooting devices is determined according to the reference image feature information associated with each of the at least one reference shooting device and the shooting time corresponding to the reference image feature information, including:

[0164] For at least one reference shooting device, target image feature information associated with the reference shooting device is determined based on the reference image feature information associated with the reference shooting device. The similarity between the target image feature information associated with the reference shooting device is greater than the similarity between the remaining reference image feature information in the same reference image feature information (excluding the target image feature information associated with the reference shooting device). Furthermore, the similarity between the target image feature information associated with adjacent reference shooting devices in terms of shooting order is greater than the similarity between the remaining reference image feature information in the same reference image feature information (excluding the target image feature information associated with the reference shooting device).

[0165] Based on the shooting time corresponding to the target image feature information associated with each of the at least one reference shooting device, the shooting time corresponding to the same target being captured by different reference shooting devices is determined.

[0166] Based on the above embodiments, optionally, determining the target image feature information associated with the reference shooting device according to the reference image feature information associated with the reference shooting device includes:

[0167] When the reference shooting device is the first shooting device, the feature information of each reference image associated with the first shooting device is clustered to obtain at least two reference image feature clustering groups; wherein, the first shooting device is the first reference shooting device to be processed among the at least one reference shooting device;

[0168] For each reference image feature cluster, the similarity between the reference image feature information in the reference image feature cluster is determined;

[0169] Based on the similarity between the reference image feature information in each of the reference image feature clusters, the target image feature information associated with the first shooting device is determined.

[0170] Based on the above embodiments, optionally, determining the target image feature information associated with the reference shooting device according to the reference image feature information associated with the reference shooting device includes:

[0171] When the reference shooting device is the second shooting device, target image feature information associated with the third shooting device is determined. The similarity between the target image feature information associated with the third shooting device is greater than the similarity between the remaining reference image feature information in the reference image feature information associated with the third shooting device, excluding the target image feature information associated with the third shooting device. Wherein, the second shooting device is not the first reference shooting device to be processed among the at least one reference shooting devices, and the third shooting device is the reference shooting device that is processed before the second shooting device and is adjacent to the second shooting device in the shooting order among the at least one reference shooting devices.

[0172] Based on the target image feature information associated with the third shooting device and the reference image feature information associated with the second shooting device among at least one reference shooting device, the target image feature information associated with the second shooting device is determined. The similarity between the target image feature information associated with the third shooting device and the target image feature information associated with the second shooting device is greater than the similarity between the target image feature information associated with the third shooting device and the remaining reference image feature information associated with the second shooting device, excluding the target image feature information associated with the second shooting device.

[0173] Based on the above embodiments, optionally, the target image feature information associated with the second shooting device is determined according to the target image feature information associated with the third shooting device and the reference image feature information associated with the second shooting device among at least one reference shooting device, including:

[0174] The image feature information to be used associated with the third shooting device is determined from the target image feature information associated with the third shooting device. The image feature information to be used associated with the third shooting device is obtained by sorting the target image feature information associated with the third shooting device according to the shooting time corresponding to the target image feature information associated with the third shooting device and then filtering it.

[0175] Determine the similarity between the image feature information to be used associated with the third shooting device and the reference image feature information associated with the second shooting device;

[0176] Based on the similarity between the reference image feature information associated with the second shooting device and the reference image feature information associated with the second shooting device, the target image feature information associated with the second shooting device is determined from the reference image feature information associated with the second shooting device.

[0177] Optionally, based on the above embodiments, when determining the reference image feature information associated with at least one reference capturing device in the target area, the method further includes:

[0178] Determine the reference shooting position when capturing images of the target using a reference shooting device to obtain reference image feature information;

[0179] Based on the reference shooting position corresponding to the acquisition of reference image feature information and the position of the reference shooting device, the relative distance between the position of the reference shooting device and the reference shooting position is determined.

[0180] If the relative distance between the location of the reference shooting device and the reference shooting location is less than a preset relative distance, the reference shooting location is bound to the reference image feature information, which is used to filter the target image feature information corresponding to the same capture target from the reference image feature information associated with at least one reference shooting device.

[0181] Optionally, based on the above embodiments, the reference image feature information is also used to describe the local image features of the captured image formed when the reference shooting device captures an image of the target. The local image features are used to describe the appearance features of the target in the captured image. The appearance features are used to indicate the salient features and attributes of the target that can be directly perceived in appearance.

[0182] The technical solution of this invention determines the reference image feature information associated with at least one reference shooting device in the target area and the corresponding shooting time. Each reference image feature information is used to describe the global image features of the captured image formed when the reference shooting device captures an image of the target. This enables comprehensive analysis of the image content and provides a basis for accurate identification of the target. Furthermore, based on the reference image feature information associated with at least one reference shooting device and the corresponding shooting time, the shooting time corresponding to the same target being captured by different reference shooting devices is determined. This achieves accurate positioning of the shooting time corresponding to the same target being captured by different shooting devices, which helps to construct a complete activity trajectory and timeline of the same target. It can integrate images of the same target captured by different shooting devices into target video information, restoring the complete video of the target. This solves the problems of repeated real-time editing required for each video acquisition, long video acquisition time, high server pressure, and large video storage requirements. It improves the efficiency of integrating and utilizing video information captured by different shooting devices on the same target.

[0183] The target video generation apparatus provided in this embodiment of the invention can execute the target video generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0184] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0185] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Refer to the following... Figure 5 It illustrates an electronic device suitable for implementing embodiments of the present invention (e.g., Figure 5 The diagram below shows the structure of the terminal device or server 500. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0186] like Figure 5As shown, electronic device 500 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An edit / output (I / O) interface 505 is also connected to bus 504.

[0187] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0188] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of the embodiments of the present invention.

[0189] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0190] The electronic device provided in this embodiment of the invention and the voice wake-up method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0191] This invention provides a computer storage medium storing a computer program that, when executed by a processor, implements the voice wake-up method provided in the above embodiments.

[0192] It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0193] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0194] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0195] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: determine the shooting time corresponding to the reference image feature information associated with each of at least one reference shooting device in the target area, wherein the reference image is a global image acquired by the reference shooting device when shooting at the target; determine the shooting time corresponding to the same target being shot by different reference shooting devices based on the shooting time corresponding to the reference image feature information associated with each of the at least one reference shooting device; and determine the target video information corresponding to the same target based on the shooting time corresponding to the same target being shot by different reference shooting devices.

[0196] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0197] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0198] The units described in the embodiments of the present invention can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0199] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0200] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0201] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0202] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the invention. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0203] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A target video generation method, characterized by, The method includes: Determine the reference image feature information associated with at least one reference shooting device in the target area and the shooting time corresponding to the reference image feature information, wherein the reference image is a global image acquired by the reference shooting device when shooting the target; Based on the reference image feature information associated with each of at least one reference shooting device and the shooting time corresponding to the reference image feature information, the shooting time corresponding to the same target being captured by different reference shooting devices is determined. Based on the shooting time when the same target is captured by different reference shooting devices, the target video information corresponding to the same target is determined.

2. The method of claim 1, wherein, Determine the reference image feature information associated with at least one reference capturing device in the target area, including: For at least one reference imaging device, determine candidate image feature information associated with the reference imaging device, wherein the candidate image is a global image of the captured scene formed when the reference imaging device captures an image; Determine the static image feature information associated with the reference shooting device. The static image feature information includes a description of the global image features of the shooting scene formed when the reference shooting device captures an image, provided that there are no dynamic target elements within the shooting angle range of the reference shooting device. Based on the candidate image feature information and still image feature information associated with the reference shooting device, the reference image feature information associated with the reference shooting device is determined from the candidate image feature information.

3. The method of claim 2, wherein, Determining the still image feature information associated with the reference capturing device includes: When capturing images of a target using a reference shooting device, the corresponding reference shooting environment attribute conditions are determined. The reference shooting device is matched with dynamically adjusted and updated static image feature information under each type of shooting environment attribute condition. Based on the reference shooting environment attribute conditions, the static image feature information corresponding to the reference shooting device is matched to determine the static image feature information associated with the reference shooting device.

4. The method of claim 3, wherein, The shooting environment attribute conditions are determined based on the image characteristics of the specified sub-screen area. The specified sub-screen area is the sub-screen area that the target has not entered after the image is segmented into screen regions when the shooting device captures the image.

5. The method of claim 1, wherein, At least one reference shooting device in the target area is configured to sequentially shoot the same target in a preset shooting order. Each of the at least one reference shooting device is installed in a different position and corresponds to a different shooting scene. Each reference shooting device is configured to ensure that the sharpness of a preset part of the target meets a preset sharpness when shooting the target.

6. The method of claim 5, wherein, Based on the reference image feature information associated with each of at least one reference capturing device and the capturing time corresponding to the reference image feature information, the capturing time corresponding to the capturing target being captured by different reference capturing devices is determined, including: determining target image feature information associated with each of the at least one reference photographing device according to reference image feature information associated with the reference photographing device, the similarity between the target image feature information associated with the reference photographing device being greater than the similarity between the remaining reference image feature information associated with the reference photographing device other than the target image feature information associated with the reference photographing device, and the similarity between target image feature information associated with reference photographing devices adjacent in photographing order being greater than the similarity between the remaining reference image feature information associated with the reference photographing device other than the target image feature information associated with the reference photographing device; determining photographing time corresponding to the target image feature information associated with each of the at least one reference photographing device, and determining photographing time corresponding to the target image feature information associated with each of the at least one reference photographing device.

7. The method of claim 6, wherein, determining target image feature information associated with each of the at least one reference photographing device according to reference image feature information associated with the reference photographing device, including: when the reference photographing device is a first photographing device, clustering each reference image feature information associated with the first photographing device to obtain at least two reference image feature clustering groups, the first photographing device being the first reference photographing device to be processed in the at least one reference photographing device; for each reference image feature clustering group, determining the similarity between reference image feature information in the reference image feature clustering group; determining target image feature information associated with the first photographing device according to the similarity between reference image feature information in each reference image feature clustering group.

8. The method of claim 6, wherein, determining target image feature information associated with each of the at least one reference photographing device according to reference image feature information associated with the reference photographing device, including: when the reference photographing device is a second photographing device, determining target image feature information associated with a third photographing device, the similarity between the target image feature information associated with the third photographing device being greater than the similarity between the remaining reference image feature information associated with the third photographing device other than the target image feature information associated with the third photographing device, the second photographing device being a reference photographing device other than the first photographing device in the at least one reference photographing device, and the third photographing device being a reference photographing device processed before the second photographing device and adjacent to the second photographing device in photographing order in the at least one reference photographing device; determining photographing time corresponding to the target image feature information associated with each of the at least one reference photographing device, and determining photographing time corresponding to the target image feature information associated with each of the at least one reference photographing device. Based on the target image feature information associated with the third shooting device and the reference image feature information associated with the second shooting device among at least one reference shooting device, the target image feature information associated with the second shooting device is determined. The similarity between the target image feature information associated with the third shooting device and the target image feature information associated with the second shooting device is greater than the similarity between the target image feature information associated with the third shooting device and the remaining reference image feature information associated with the second shooting device, excluding the target image feature information associated with the second shooting device.

9. The method of claim 8, wherein, Based on the target image feature information associated with the third imaging device and the reference image feature information associated with the second imaging device among at least one reference imaging device, the target image feature information associated with the second imaging device is determined, including: The image feature information to be used associated with the third shooting device is determined from the target image feature information associated with the third shooting device. The image feature information to be used associated with the third shooting device is obtained by sorting the target image feature information associated with the third shooting device according to the shooting time corresponding to the target image feature information associated with the third shooting device and then filtering it. Determine the similarity between the image feature information to be used associated with the third shooting device and the reference image feature information associated with the second shooting device; Based on the similarity between the reference image feature information associated with the second shooting device and the reference image feature information associated with the second shooting device, the target image feature information associated with the second shooting device is determined from the reference image feature information associated with the second shooting device.

10. The method of claim 6, wherein, When determining the reference image feature information associated with at least one reference capturing device in the target area, the method further includes: Determine the reference shooting position when capturing images of the target using a reference shooting device to obtain reference image feature information; Based on the reference shooting position corresponding to the acquisition of reference image feature information and the position of the reference shooting device, the relative distance between the position of the reference shooting device and the reference shooting position is determined. If the relative distance between the position of the reference shooting device and the reference shooting position is less than a preset relative distance, the reference shooting position is bound to the reference image feature information, which is used to filter the target image feature information corresponding to the same capture target from the reference image feature information associated with at least one reference shooting device.

11. The method of any one of claims 1-10, wherein, The reference image feature information is also used to describe the local image features of the captured image formed when the reference shooting device captures an image of the target. The local image features are used to describe the appearance features of the target in the captured image. The appearance features are used to indicate the salient features and attributes of the target that can be directly perceived in appearance.

12. A target video generation apparatus, comprising: The device includes: The first determining module is used to determine the reference image feature information associated with at least one reference shooting device in the target area and the shooting time corresponding to the reference image feature information, wherein the reference image is a global image acquired by the reference shooting device when shooting the target; The second determining module is configured to determine the photographing time corresponding to the same snapshot target when the same snapshot target is photographed by different reference photographing devices according to the reference image feature information of each reference photographing device and the photographing time corresponding to the reference image feature information. The third determining module is configured to determine the target video information corresponding to the same snapshot target according to the photographing time corresponding to the same snapshot target when the same snapshot target is photographed by different reference photographing devices.

13. An electronic device, comprising: The electronic device includes: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the target video generation method in any one of claims 1-11.

14. A storage medium containing computer-executable instructions, wherein: The computer executable instructions, when executed by a computer processor, are configured to perform the target video generation method in any one of claims 1-11.

Images