On-board monitoring video splicing method and apparatus, and electronic device and storage medium

Abstract

Disclosed in the present application are an on-board monitoring video splicing method, an on-board monitoring video splicing apparatus, an electronic device, a storage medium, and a vehicle. The method comprises: for a preset target, a plurality of cameras recording monitoring videos from respective angles of view; selecting video frames having the preset target; exiting a photographing area of a first camera according to the preset target, and labeling a monitoring video frame of the first camera with a first-type timestamp; entering a photographing area of a second camera according to the preset target, and labeling a monitoring video frame of the second camera with a second-type timestamp; according to the first-type timestamp and the second-type timestamp, cropping monitoring videos in which the preset target is recorded; and according to a timestamp sequence, splicing the cropped monitoring videos in which the preset target is recorded. By means of the solution, videos of a plurality of cameras are spliced according to a timestamp sequence, such that a spliced video presents a movement trajectory of a preset target at different positions around a vehicle.

Description

Vehicle-mounted surveillance video splicing method, device, electronic device and storage medium Technical Field

[0001] The present application relates to the field of vehicle-mounted video, and in particular to a vehicle-mounted surveillance video splicing method, a vehicle-mounted surveillance video splicing device, an electronic device, a storage medium, and a vehicle. Background Art

[0002] With the popularization of car use, people are paying more and more attention to vehicle anti-theft security. However, in many scenarios, due to the lack of some road monitoring equipment, vehicle damage and claims lack effective compensation evidence, making it difficult to effectively identify vehicle losses.

[0003] Although the vehicle itself is equipped with many cameras, each camera has its own functional purpose. Although it has the ability to record surveillance videos, simple and direct recording cannot improve efficiency in forming evidence.

[0004] With the reduction and convenience of implementing video cloud technology, as well as the popularization and standardization of overall systems such as vehicle smart cockpits and intelligent networking, solving the above problems has become possible.

[0005] Therefore, through the identity authentication of the vehicle hardware camera and the coordinated use of various cameras, the movement trajectory of the monitored person can be tracked, and the embedded system software of the vehicle computer can complete the recording and splicing of video content, realize video retention and alarm prompt functions, effectively improving the convenience and security of evidence retention.

[0006] Summary of the Invention

[0007] The object of the present invention is to provide a vehicle fuel reminder method, a vehicle fuel reminder system, a vehicle fuel reminder device, an electronic device, a storage medium and a vehicle, so as to solve at least one of the above-mentioned technical problems.

[0008] The present invention provides the following solutions:

[0009] According to one aspect of the present invention, a method for splicing vehicle-mounted surveillance videos is provided, the method comprising:

[0010] For preset targets, multiple cameras record surveillance videos from their respective perspectives;

[0011] Select the video frame with the preset target;

[0012] Exit the shooting area of ​​the first camera according to the preset target, and mark the first type of timestamp on the monitoring video frame of the first camera;

[0013] Entering the shooting area of ​​the second camera according to the preset target, marking the second type of timestamp on the monitoring video frame of the second camera;

[0014] According to the first type of timestamp and the second type of timestamp, intercept and record the surveillance video of the preset target;

[0015] According to the timestamp sequence, the intercepted surveillance videos of the preset targets are spliced ​​together.

[0016] Furthermore, the multiple cameras recording surveillance videos from respective perspectives include:

[0017] Obtain intrusion trigger information of preset targets;

[0018] According to the preset target intruding into the vehicle monitoring range, the camera records the monitoring video corresponding to the preset target.

[0019] Furthermore, the camera records the surveillance video corresponding to the preset target including:

[0020] According to multiple preset targets invading the vehicle monitoring range, multiple cameras record monitoring videos corresponding to the same preset target.

[0021] Furthermore, intercepting and recording the surveillance video of the preset target according to the first type of timestamp and the second type of timestamp includes:

[0022] Exiting the shooting area of ​​the first camera respectively according to the plurality of preset targets, and marking a first type of timestamp for the same preset target in the surveillance video frame of the first camera;

[0023] According to a plurality of preset targets, each target enters a shooting area of ​​the second camera, and a second type of timestamp is marked on the surveillance video frame of the second camera for the same preset target;

[0024] According to the first type of timestamp and the second type of timestamp, intercept the surveillance video recording the same preset target;

[0025] According to the order of timestamps, the intercepted surveillance videos of the same preset target are spliced ​​together.

[0026] Furthermore, the camera recording the surveillance video corresponding to the preset target according to the preset target intruding into the vehicle monitoring range includes:

[0027] Obtaining the first type of identification feature information of the preset target;

[0028] Filtering preset targets and non-preset targets in the surveillance video according to the first type of identification features;

[0029] Obtaining the second type of identification feature information of the preset target;

[0030] Filtering multiple preset targets in the surveillance video according to the second type of identification features;

[0031] Since there are multiple preset targets in the surveillance video, the same preset target is distinguished and marked with an identity ID.

[0032] Furthermore, the splicing of intercepted surveillance videos recorded for the same preset target according to the timestamp order includes:

[0033] Generate the preset target movement trajectory information based on the same preset target exiting and entering the vehicle monitoring range of multiple cameras;

[0034] The preset target movement trajectory corresponds to the timestamp sequence and fills the blind spots between the vehicle monitoring ranges of the cameras.

[0035] According to two aspects of the present invention, there is provided a vehicle-mounted surveillance video splicing device, the vehicle-mounted surveillance video splicing device comprising:

[0036] Video recording module, used for recording surveillance videos from multiple cameras from their respective perspectives for preset targets;

[0037] A video frame selection module is used to select video frames with preset targets;

[0038] A first-type timestamp module, configured to exit the shooting area of ​​the first camera according to a preset target and mark the first-type timestamp on the monitoring video frame of the first camera;

[0039] A second timestamp module is used to mark a second timestamp on a surveillance video frame of the second camera according to a preset target entering the shooting area of ​​the second camera;

[0040] A video capture module, configured to capture and record surveillance videos of preset targets based on the first and second timestamps;

[0041] The video splicing module is used to splice the intercepted surveillance videos of the preset targets according to the order of timestamps.

[0042] According to three aspects of the present invention, there is provided an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0043] A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the vehicle-mounted surveillance video splicing method.

[0044] According to four aspects of the present invention, a computer-readable storage medium is provided, comprising: a computer program executable by an electronic device is stored therein, and when the computer program runs on the electronic device, the electronic device executes the steps of the vehicle-mounted surveillance video splicing method.

[0045] According to five aspects of the present invention, there is provided a vehicle comprising:

[0046] An electronic device for implementing the steps of the vehicle-mounted surveillance video splicing method;

[0047] A processor, wherein the processor runs a program, and when the program runs, the steps of the vehicle monitoring video splicing method are executed based on the data output by the electronic device;

[0048] The storage medium is used to store a program, and when the program is running, it executes the steps of the vehicle-mounted monitoring video splicing method for data output from the electronic device.

[0049] Through the above solution, the following beneficial technical effects are achieved:

[0050] This application starts recording surveillance video through a trigger signal. Compared with loop recording, the recorded surveillance video is targeted, which is beneficial to saving hardware resources and improving the effectiveness of video data.

[0051] This application stitches the videos of multiple cameras in the order of timestamps so that the stitched videos show the movement trajectory of the preset target at different positions around the vehicle.

[0052] This application not only identifies the preset targets through different recognition features, but also distinguishes different preset targets, labels the preset targets with IDs, and records monitoring videos for each preset target as each preset target appears within the vehicle monitoring range. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] FIG1 is a flowchart of a method for splicing vehicle-mounted surveillance videos provided by one or more embodiments of the present invention.

[0054] FIG2 is a structural diagram of a vehicle-mounted surveillance video splicing device provided by one or more embodiments of the present invention.

[0055] FIG3 is a flow chart of detecting an intrusion and waking up a vehicle monitoring state according to a specific embodiment of the present invention.

[0056] FIG4 is a schematic diagram of the workflow of an image recognition module according to a specific embodiment of the present invention.

[0057] FIG5 is a schematic diagram of a video editing and assembling process according to a specific embodiment of the present invention.

[0058] FIG6 is a schematic diagram of a vehicle-mounted alarm video system according to a specific embodiment of the present invention.

[0059] FIG7 is a block diagram of an electronic device structure of a vehicle-mounted surveillance video splicing method provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0060] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] FIG1 is a flowchart of a method for splicing vehicle-mounted surveillance videos provided by one or more embodiments of the present invention.

[0062] As shown in Figure 1, the vehicle surveillance video splicing method includes:

[0063] Step S1: for a preset target, multiple cameras record surveillance videos from their respective perspectives;

[0064] Step S2, selecting a video frame with a preset target;

[0065] Step S3, exiting the shooting area of ​​the first camera according to the preset target, and marking the first type of timestamp on the monitoring video frame of the first camera;

[0066] Step S4, entering the shooting area of ​​the second camera according to the preset target, and marking the second type of timestamp on the monitoring video frame of the second camera;

[0067] Step S5, intercepting and recording the surveillance video of the preset target according to the first type of timestamp and the second type of timestamp;

[0068] Step S6: splicing the intercepted surveillance videos of the preset target according to the order of timestamps.

[0069] Through the above solution, the following beneficial technical effects are achieved:

[0070] This application starts recording surveillance video through a trigger signal. Compared with loop recording, the recorded surveillance video is targeted, which is beneficial to saving hardware resources and improving the effectiveness of video data.

[0071] This application stitches the videos of multiple cameras in the order of timestamps so that the stitched videos show the movement trajectory of the preset target at different positions around the vehicle.

[0072] This application not only identifies the preset targets through different recognition features, but also distinguishes different preset targets, labels the preset targets with IDs, and records monitoring videos for each preset target as each preset target appears within the vehicle monitoring range.

[0073] Specifically, the vehicle itself can be equipped with many camera devices, such as AVM surround view camera, DVR vehicle reversing camera, OMS in-vehicle camera, etc., but each camera device has its own functional purpose.

[0074] For example, the AVM surround view camera seamlessly stitches images, and the image display should reflect a sense of integrity, showing the ground scenery intact without obvious deformation, and truly reflecting the actual objects during movement. Dynamic guide lines are set, and when following the trajectory of the vehicle body, the width is always consistent and does not deviate, assisting the driver in parking and reversing. The AVM view display should support multiple perspectives, including the front, left front, left, left rear, rear, right rear, right right, right front and even more. The front and rear generally support wide-angle perspectives. The camera supports adaptive adjustment of image brightness. When the camera fails, the corresponding side image should support blackening processing; when the door is open, the corresponding side image should be grayed out in the stitched view. It is mainly an assisted driving function.

[0075] For example, the OMS in-cabin camera, also known as the Occupancy Monitoring System (OMS), is an extension of the DMS. It can further enhance vehicle safety by monitoring passenger sensory data within the cabin. Seatbelt warnings are among the most traditional OMS features. OMS can also help determine whether passengers are safely seated, whether children or pets have been left unattended, and whether passengers are wearing seatbelts. Its primary function is to monitor the completeness of passenger safety measures.

[0076] For example, a DVR (on-board backup camera) is derived from a traditional embedded hard disk video recorder (DVR). It utilizes an embedded processor and operating system, integrating H.264 audio and video compression, GPS, and WiFi / 4G wireless transmission technologies. It is widely used on large vehicles like trucks, buses, and sanitation trucks, as well as on ships, airplanes, trains, and subways. It provides real-time vehicle monitoring, including audio and video recording and real-time transmission, GPS positioning, and the ability to connect to various on-board devices such as sensors, display screens, and passenger counts. Its primary function is monitoring and recording.

[0077] A moving target invading a vehicle typically moves from outside to inside. However, each camera has different coverage areas, and there's no coordinated relay tracking of the same pre-set target. Therefore, when the pre-set target enters the AVM surround-view camera's monitoring range, the other cameras are ready. For example, if the pre-set target leaves the AVM surround-view camera's monitoring range and enters the vehicle's interior, the OMS interior camera takes over. A timestamp is set at the intersection of the two cameras. This sequence of timestamps clearly depicts the pre-set target's movements inside and outside the vehicle, ensuring that monitoring remains focused on the pre-set target.

[0078] By splicing and recording videos for the same preset target, the consumption of storage space can be reduced, so that the video records are meaningful.

[0079] The first type of timestamp is added to the video captured by the camera upon exiting the camera's field of view. The second type of timestamp is added to the video captured by the camera upon entering the field of view. Although AVM surround-view cameras are nearly seamless, recording is not required for all cameras. Recording can be enabled upon entering the corresponding camera field of view according to a preset target, thus requiring the above timestamps. A blind spot between the two cameras' field of view is possible, so both the first and second timestamps must be set, not just one.

[0080] In this embodiment, multiple cameras recording surveillance videos from respective perspectives include:

[0081] Obtain intrusion trigger information of preset targets;

[0082] According to the preset target intruding into the vehicle monitoring range, the camera records the monitoring video corresponding to the preset target.

[0083] Specifically, each camera typically operates according to its original function, and begins recording when a preset target enters the monitoring range. For example, when a user leaves the vehicle and locks the door, the monitoring function is triggered. Once a preset target enters the monitoring range of the AVM surround-view camera, the other cameras are also ready.

[0084] It's possible that the OMS in-car camera could trigger the monitoring and recording function. For example, if a child is left in the car and wakes up, the OMS in-car camera would trigger the monitoring and recording function. If the child leaves the vehicle and enters the monitoring range of the AVM surround-view camera, a timestamp is added, and the AVM surround-view camera takes over the recording.

[0085] In this embodiment, the camera records the surveillance video corresponding to the preset target including:

[0086] According to multiple preset targets invading the vehicle monitoring range, multiple cameras record monitoring videos corresponding to the same preset target.

[0087] Specifically, we can't rule out the possibility that multiple preset targets appear within the same camera's monitoring range, but each is marked individually when timestamping. This allows for easier splicing of videos based on the different preset targets. For example, several people may vandalize the same vehicle, each carrying out different acts. Some may cause damage independently, while others may result in damage in combination. By recording videos based on different preset targets while still capturing the same target, organized video evidence can be generated.

[0088] Of course, when the two preset targets A and B appear in the monitoring range of the first camera, the camera will work, recording both A and B. When A leaves the monitoring range of the first camera and enters the monitoring range of the second camera, the first camera continues to work. Although it no longer records A, it still records B. At this time, the second camera starts to work and takes over the first camera, but the relay is to continue monitoring A.

[0089] In this embodiment, intercepting and recording the surveillance video of the preset target according to the first type of timestamp and the second type of timestamp includes:

[0090] Exiting the shooting area of ​​the first camera respectively according to the plurality of preset targets, and marking a first type of timestamp for the same preset target in the surveillance video frame of the first camera;

[0091] According to a plurality of preset targets, each target enters a shooting area of ​​the second camera, and a second type of timestamp is marked on the surveillance video frame of the second camera for the same preset target;

[0092] According to the first type of timestamp and the second type of timestamp, intercept the surveillance video recording the same preset target;

[0093] According to the order of timestamps, the intercepted surveillance videos of the same preset target are spliced ​​together.

[0094] Specifically, to distinguish the entry and exit of multiple preset targets within the surveillance range of different cameras, a set of timestamps is added to the same preset target. This ensures that when stitching together videos, the trajectory information generated is also for the same preset target, preventing confusion in the stitched video.

[0095] That is to say, a video may contain both A and B, but the same video is included in the splicing results of A and B's respective videos, which means that A and B have an intersection under a certain camera.

[0096] In this embodiment, when a preset target intrudes into the vehicle monitoring range, the camera records the monitoring video corresponding to the preset target, including:

[0097] Obtaining the first type of identification feature information of the preset target;

[0098] Filtering preset targets and non-preset targets in the surveillance video based on the first type of identification features;

[0099] Obtaining the second type of identification feature information of the preset target;

[0100] Filter multiple preset targets in the surveillance video according to the second type of recognition features;

[0101] Since there are multiple preset targets in the surveillance video, the same preset target is distinguished and marked with an identity ID.

[0102] Specifically, for the purpose of theft prevention, multiple pre-set targets can be set based on behavioral characteristics of theft, but they are not the same person. Other biometric characteristics are also needed to distinguish different "thieves." Each pre-set target is labeled with an identity ID, and the corresponding spliced ​​video associated with that ID has its timestamps tracked only by the pre-set target's movements.

[0103] In this embodiment, the intercepted surveillance videos recorded for the same preset target are spliced ​​together according to the timestamp order, including:

[0104] Generate the preset target movement trajectory information based on the same preset target exiting and entering the vehicle monitoring range of multiple cameras;

[0105] The target movement trajectory is preset, corresponding to the timestamp sequence, to fill the blind spots between the on-board monitoring ranges of the cameras.

[0106] Specifically, the movement trajectory of the preset target mainly refers to the entry and exit of the preset target in the shooting range of each camera. The movement trajectory of the preset target is described in chronological order based on the shooting angle and shooting range of the camera. For example, if the preset target enters the monitoring range of the OMS in-vehicle camera from the monitoring range of the AVM surround-view camera, the trajectory is from outside the vehicle to inside the vehicle. Of course, there is more than one AVM surround-view camera, and the trajectory of the preset target moving around the vehicle outside the vehicle can be described in chronological order based on the entry and exit of the preset target between the cameras.

[0107] FIG2 is a structural diagram of a vehicle-mounted surveillance video splicing device provided by one or more embodiments of the present invention.

[0108] As shown in Figure 2, the vehicle-mounted surveillance video splicing device includes: a video recording module, a video frame selection module, a first-type timestamp module, a second-type timestamp module, a video interception module, and a video splicing module;

[0109] Video recording module, used for recording surveillance videos from multiple cameras from their respective perspectives for preset targets;

[0110] A video frame selection module is used to select video frames with preset targets;

[0111] A first-type timestamp module, configured to exit the shooting area of ​​the first camera according to a preset target and mark the first-type timestamp on the monitoring video frame of the first camera;

[0112] A second timestamp module is used to mark a second timestamp on a surveillance video frame of the second camera according to a preset target entering the shooting area of ​​the second camera;

[0113] A video capture module, configured to capture and record surveillance videos of preset targets based on the first and second timestamps;

[0114] The video splicing module is used to splice the intercepted surveillance videos of the preset targets according to the order of timestamps.

[0115] It is worth noting that although the present system only discloses a video recording module, a video frame selection module, a first-class timestamp module, a second-class timestamp module, a video capture module, and a video stitching module, it does not mean that the present device is limited to the above-mentioned basic functional modules. Rather, what the present invention wants to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the existing technology to form an infinite number of embodiments or technical solutions. In other words, the present system is open rather than closed. Just because the present embodiment only discloses individual basic functional modules, it cannot be considered that the scope of protection of the claims of the present invention is limited to the above-mentioned basic functional modules.

[0116] FIG3 is a flow chart of detecting an intrusion and waking up a vehicle monitoring state according to a specific embodiment of the present invention.

[0117] As shown in Figure 3, this embodiment is primarily applicable to in-vehicle surveillance systems equipped with camera hardware, including AVM surround-view cameras, DVR vehicle reversing cameras, and OMS in-vehicle cameras. It can leverage facial recognition or morphological recognition to track and record the movements of intruders. Furthermore, it can record and extract corresponding camera footage for multiple intruders.

[0118] In this embodiment, the main steps for recording and saving video include: first, in the vehicle monitoring state, the vehicle's sensors use the camera to detect intruders and activate the CSC monitoring service. Second, the intruder is identified and tracked, and information such as timestamps is continuously uploaded. Finally, the cloud-based video stream is edited and assembled based on the recognition results.

[0119] In this embodiment, the Ethernet system of the vehicle-mounted CSC and VDC and the Android Framework support the standard interface of the Camera, and the control of the CSC and cloud ICC mainly relies on the SOA interface implementation of the standard control layer.

[0120] In this embodiment, when a vehicle is under surveillance, a sensor detects an intrusion and wakes it up. For example, if a door sensor senses an external intrusion, such as a collision or door being pulled, it notifies the VDC, which then activates the corresponding AVM / DVR camera. Based on the direction information transmitted by the sensor, it determines the camera's intended viewing angle. At this point, the video surveillance service on the CSC activates the AVM / DVR through a control command and notifies the cloud to begin recording.

[0121] The overall process of this embodiment is as follows: 1. Alarm event; 2. Switch to the corresponding angle; 3. Start the video monitoring service; 4. Start uploading the video stream.

[0122] FIG4 is a schematic diagram of the workflow of an image recognition module according to a specific embodiment of the present invention.

[0123] As shown in Figure 4, the image recognition module identifies the intruder and continuously uploads information such as timestamps.

[0124] For example, in the program, define the identification information structure Struct.

[0125] The above is the continuous reporting of the recognition results of each camera by the corresponding image recognition module. The image recognition module uses a third-party system for offline recognition. The CSC image recognition module continuously encapsulates the recognition results and object confirmation and uploads them to the cloud.

[0126] VDC samples different camera streams and performs frame-by-frame recognition. For the recognition results, the same feature object must be uniformly identified using the same ID according to the recognition result structure requirements. After identification, a globally unique event stamp must be recorded. The system's sampling rate must balance performance and sampling accuracy. The sequence of recognized sample frames must be synchronously provided to the video cloud server. The video cloud server only records the sampling process.

[0127] FIG5 is a schematic diagram of a video editing and assembling process according to a specific embodiment of the present invention.

[0128] As shown in Figure 5, the cloud-based video stream is clipped and assembled based on the recognition results. After the cloud receives the video stream via the RTMP protocol and continuously obtains the timestamps of the recognition results through the signaling channel, the following steps need to be implemented.

[0129] First, based on the segmented storage of the video stream, the corresponding time of the recognition result and the matching storage time are found. Furthermore, video segments with the same ObjID are identified, that is, video frames that identify the same object. Furthermore, for the same object process, the cropping or supplementary video segmentation operations are repeated, such as the generation of a, b, and c, and A, B, and C in the figure below. Furthermore, for the same sequence, the assembled video sequence with the same ObjID is completed and the video is reassembled according to the timestamp order.

[0130] FIG6 is a schematic diagram of a vehicle-mounted alarm video system according to a specific embodiment of the present invention.

[0131] As shown in Figure 6, DVR (Dash Recorder) refers to the driving video camera. AVM (Around View Camera) refers to the surround view camera. OMS (Occupant Monitoring System) refers to the in-car passenger camera. HAD (Advanced Autonomous Driving Module) refers to the Advanced Automated Driving Module. VDC (Vehicle Dynamic Control) refers to the Vehicle Dynamic Control System. CSC (Infotainment Controller) refers to the infotainment controller.

[0132] Let's take a specific example of this system process. When DVR / AVM data collection is enabled, the video software module on the HAD / VDC encodes and streams the video data, which is then pushed to the CSC via the in-vehicle Ethernet network for reception. Data is also collected from the vehicle's OMS (deployed directly on the CSC). Data from different camera sources is uniformly managed by the CSC's video processing module. The video stream management module first desensitizes the video, removing sensitive user information such as faces and ID numbers. The video is then uploaded to the real-time cloud for push notification. A mobile phone can then access the vehicle control room in the same vehicle and view the video stream pushed by the vehicle. The vehicle also uses the application cloud for data verification and the signaling cloud for interactive control with the mobile phone.

[0133] FIG7 is a block diagram of an electronic device structure of a vehicle-mounted surveillance video splicing method provided by one or more embodiments of the present invention.

[0134] As shown in FIG7 , the present application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0135] A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of a vehicle-mounted monitoring video splicing method.

[0136] The present application also provides a computer-readable storage medium, which stores a computer program that can be executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of a vehicle-mounted surveillance video splicing method.

[0137] The present application also provides a vehicle, comprising:

[0138] Electronic equipment for implementing the steps of the vehicle surveillance video splicing method;

[0139] A processor, wherein the processor runs a program, and when the program runs, the steps of the vehicle monitoring video splicing method are executed based on the data output by the electronic device;

[0140] The storage medium is used to store a program, and when the program is running, it executes the steps of the vehicle monitoring video splicing method for the data output from the electronic device.

[0141] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0142] The electronic device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control electronic devices through processes, such as the Linux operating system, the Unix operating system, the Android operating system, the iOS operating system, or the Windows operating system. In the embodiments of the present invention, the electronic device can be a handheld device such as a smartphone or a tablet computer, or an electronic device such as a desktop computer or a portable computer, which is not particularly limited in the embodiments of the present invention.

[0143] The execution subject of the electronic device control in the embodiment of the present invention can be an electronic device, or a functional module in the electronic device that can call a program and execute the program. The electronic device can obtain the firmware corresponding to the storage medium. The firmware corresponding to the storage medium is provided by the supplier. The firmware corresponding to different storage media can be the same or different, and is not limited here. After the electronic device obtains the firmware corresponding to the storage medium, it can write the firmware corresponding to the storage medium into the storage medium, specifically, burn the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology and will not be described in detail in the embodiment of the present invention.

[0144] The electronic device can also obtain a reset command corresponding to the storage medium. The reset command corresponding to the storage medium is provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and are not limited here.

[0145] In this case, the storage medium of the electronic device is a storage medium in which the corresponding firmware is written. The electronic device can respond to the reset command corresponding to the storage medium in which the corresponding firmware is written, thereby resetting the storage medium in which the corresponding firmware is written according to the reset command corresponding to the storage medium. The process of resetting the storage medium according to the reset command can be implemented in the existing technology and will not be described in detail in the embodiments of the present invention.

[0146] For the convenience of description, the above devices are described as various units and modules according to their functions. Of course, when implementing this application, the functions of each unit and module can be implemented in the same or multiple software and / or hardware.

[0147] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art in the art to which the present invention pertains. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with those in the context of the prior art and, unless specifically defined, will not be interpreted in an idealized or overly formal sense.

[0148] For simplicity of description, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because certain steps can be performed in other orders or simultaneously according to the embodiments of the present invention. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0149] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present application or certain parts of the embodiments.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle-mounted surveillance video splicing method, characterized in that: The vehicle-mounted monitoring video splicing method comprises: For preset targets, multiple cameras record surveillance videos from their respective perspectives; Select the video frame with the preset target; Exit the shooting area of ​​the first camera according to the preset target, and mark the first type of timestamp on the monitoring video frame of the first camera; Entering the shooting area of ​​the second camera according to the preset target, marking the second type of timestamp on the monitoring video frame of the second camera; According to the first type of timestamp and the second type of timestamp, intercept and record the surveillance video of the preset target; According to the order of timestamps, the surveillance videos of the preset targets are spliced ​​together.

2. The vehicle-mounted surveillance video splicing method according to claim 1, characterized in that: The multiple cameras recording surveillance videos from respective perspectives include: Obtain intrusion trigger information of preset targets; According to the preset target intruding into the vehicle monitoring range, the camera records the monitoring video corresponding to the preset target.

3. The vehicle-mounted surveillance video splicing method according to claim 2, characterized in that: The surveillance video recorded by the camera corresponding to the preset target includes: According to multiple preset targets invading the vehicle monitoring range, multiple cameras record monitoring videos corresponding to the same preset target.

4. The vehicle-mounted monitoring video splicing method according to claim 3 is characterized in that: The intercepting and recording of the surveillance video of the preset target according to the first type of timestamp and the second type of timestamp comprises: Exiting the shooting area of ​​the first camera respectively according to the plurality of preset targets, and marking a first type of timestamp for the same preset target in the surveillance video frame of the first camera; Entering the shooting area of ​​the second camera respectively according to a plurality of preset targets, marking a second type of timestamp for the same preset target in the surveillance video frame of the second camera; According to the first type of timestamp and the second type of timestamp, intercept the surveillance video recording the same preset target; According to the order of timestamps, the intercepted surveillance videos of the same preset target are spliced ​​together.

5. The vehicle-mounted monitoring video splicing method according to claim 4 is characterized in that: The camera records the monitoring video corresponding to the preset target according to the preset target intruding into the vehicle monitoring range, including: Obtaining the first type of identification feature information of the preset target; According to the first type of identification features, filter the preset targets and non-preset targets in the surveillance video; Obtaining the second type of identification feature information of the preset target; Filtering a plurality of preset targets in the surveillance video according to the second type of identification features; Since there are multiple preset targets in the surveillance video, the same preset target is distinguished and marked with an identity ID.

6. The vehicle-mounted monitoring video splicing method according to claim 5, characterized in that: The splicing of intercepted and recorded surveillance videos for the same preset target according to the order of timestamps includes: Generate movement trajectory information of the preset target based on the same preset target exiting and entering the vehicle-mounted monitoring range of multiple cameras; The preset target movement trajectory corresponds to the timestamp sequence and fills the blind spots between the vehicle monitoring ranges of the cameras.

7. A vehicle-mounted surveillance video splicing device, characterized in that: The vehicle-mounted monitoring video splicing device comprises: The video recording module is used to record surveillance videos from different perspectives of multiple cameras for preset targets; A video frame selection module, used to select video frames with preset targets; A first-type timestamp module, used to exit the shooting area of ​​the first camera according to a preset target, and mark the first-type timestamp on the monitoring video frame of the first camera; A second timestamp module is used to enter the shooting area of ​​the second camera according to a preset target and mark the second timestamp on the monitoring video frame of the second camera; A video capture module, used to capture and record the surveillance video of a preset target according to the first type of timestamp and the second type of timestamp; The video stitching module is used to stitch the intercepted surveillance videos of preset targets according to the order of timestamps.

8. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the vehicle-mounted surveillance video splicing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: include: It stores a computer program that can be executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the vehicle-mounted monitoring video splicing method described in any one of claims 1 to 6.

10. A vehicle, characterized in that: include: An electronic device for implementing the steps of the vehicle surveillance video splicing method according to any one of claims 1 to 6; A processor, wherein the processor runs a program, and when the program runs, data output from the electronic device executes the steps of the vehicle surveillance video splicing method according to any one of claims 1 to 6; A storage medium for storing a program, wherein when the program is running, the program executes the steps of the vehicle-mounted monitoring video splicing method according to any one of claims 1 to 6 for data output from an electronic device.

Images