A method, apparatus, electronic device and storage medium for displaying test results

Abstract

This application provides a method, apparatus, electronic device, and storage medium for displaying detection results, applied to following vehicles in a vehicle platoon. The method includes: determining a display detection type from preset detection types; obtaining a detection result file for the display detection type; obtaining the detection result file by detecting a display video using a target detection model, the detection result file including the detection results of the display detection type for all frames of the display video, the detection results being used to identify the detection objects of the display detection type in the display video; and displaying the detection results of the current frame's display detection type on top of the display video based on the detection result file. This method for displaying detection results avoids obscuring some detection results in the display screen and flexibly displays target detection results according to actual needs.

Description

Technical Field

[0001] This invention relates to the field of testing, and more particularly to a method, apparatus, electronic device, and storage medium for displaying test results. Background Technology

[0002] With the continuous development of information technology, model-based object detection methods are being widely applied in an increasing number of fields. For example, in the field of autonomous driving, deep learning models can detect the surrounding environment, enabling real-time identification of pedestrians, vehicles, obstacles, and other objects during vehicle operation. They can also track and predict the trajectories of moving objects to assist autonomous driving in making appropriate driving maneuvers. In the presentation of object detection model results, the efficiency of displaying the results directly affects developers' evaluation of the results, thus impacting their work efficiency.

[0003] Current detection result display methods can only show the detection results of all detected objects at once, and cannot selectively hide the detection results. On the one hand, when there are too many detected objects, too many detection results need to be displayed, which may cause some detection results to be obscured; on the other hand, the displayed detection results cannot be adjusted according to actual needs, resulting in inflexible adjustment of the displayed content. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this disclosure provides a method, apparatus, electronic device, and storage medium for displaying detection results, which can flexibly display target detection results according to actual needs.

[0005] This application provides a method for displaying detection results. The method includes: determining a display detection type from a preset detection type; obtaining a detection result file of the display detection type; obtaining the detection result file by detecting the display video using a target detection model, the detection result file including the detection results of the display detection type for all frames of the display video, the detection results being used to identify the detection objects of the display detection type in the display video; and displaying the detection results of the current frame of the display detection type on top of the display video based on the detection result file.

[0006] Optionally, each display detection type corresponds to each detection result file; before determining the display detection type from the preset detection types, the method further includes: detecting the display video through the target detection model to obtain the detection result of each preset detection type; and generating a detection result file based on the detection result of each preset detection type.

[0007] Optionally, each detection result file corresponds to an index number; obtaining the detection result file for the display detection type includes: determining the index number of the display detection type; and reading the detection result file based on the index number.

[0008] Optionally, the display video is detected by the target detection model to obtain the detection results of each preset detection type in the preset detection types, including: determining the target detection model corresponding to each preset detection type in the preset detection types; and detecting the display video by the target detection model to obtain the detection results of each preset detection type.

[0009] Optionally, the display detection type can be determined from the preset detection types, including: in response to a confirmation command from the interactive interface, determining the display detection type from the preset detection types; the interactive interface is used to play the display video.

[0010] Optionally, based on the detection result file, the detection results of the current frame's display detection type are displayed on top of the display video, including: if the number of detected objects of the current frame's display detection type is greater than a threshold, the display detection type is determined from the display detection types according to the priority of the preset detection types; based on the detection result file, the detection results of the current frame's display detection type are displayed on top of the display video.

[0011] Optionally, the preset detection types include a first detection type and a second detection type. Based on the detection result file, the detection results of the current frame of the display detection type are displayed on top of the display video, including: if the current frame contains a detection object of the first detection type, the detection results of the current frame of the second detection type are displayed on top of the display video based on the detection result file of the second detection type.

[0012] Accordingly, embodiments of this application provide a detection result display device, including: The type module is used to determine the display detection type from preset detection types; The acquisition module is used to acquire the detection result file of the display detection type. The detection result file is obtained by detecting the display video through the target detection model. The detection result file includes the detection results of the display detection type for all frames of the display video. The detection results are used to identify the detection objects of the display detection type in the display video. The display module is used to display the detection results of the current frame on top of the display video, based on the detection result file.

[0013] Optionally, each display detection type corresponds to each detection result file; the device may also include a detection module, used to detect the display video through a target detection model before determining the display detection type from the preset detection types, to obtain the detection result of each preset detection type in the preset detection types; and to generate a detection result file based on the detection result of each preset detection type.

[0014] Optionally, each detection result file corresponds to an index number; the acquisition module is used to: determine the index number of the detection type to be displayed; and read the detection result file based on the index number.

[0015] Optionally, the display module is used to: determine the target detection model corresponding to each preset detection type in the preset detection types; detect the display video through the target detection model to obtain the detection results of each preset detection type.

[0016] Optionally, the type module is used to: determine the display detection type from the preset detection types in response to the confirmation command of the interactive interface; the interactive interface is used to play the display video.

[0017] Optionally, the display module is used to: determine the display detection type from the display detection types according to the priority of the preset detection types when the number of detected objects of the display detection type in the current frame is greater than the threshold; and display the detection results of the display detection type of the current frame on the upper layer of the display video based on the detection result file.

[0018] Optionally, the preset detection types include a first detection type and a second detection type. The display module is used to: if a detection object of the first detection type exists in the current frame, display the detection result of the second detection type of the current frame on top of the display video based on the detection result file of the second detection type.

[0019] Accordingly, this application provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The processor loads and executes the at least one instruction, at least one program, code set, or instruction set to implement the above-mentioned detection result display method.

[0020] Accordingly, embodiments of this application provide a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the above-described detection result display method.

[0021] The embodiments of this application have the following beneficial effects: (1) The target detection model is used to detect the video in advance and output the detection result file. This makes it convenient to obtain the corresponding detection result file with low latency according to the actual selected display detection type during the display, and to display the algorithm result to be displayed in real time. This ensures that the display effect can efficiently select the result while filtering the detection object type in real time, so as to facilitate the user to analyze the algorithm recognition result. (2) For the same display video that is playing, whether the video is paused or during the video playback, the display detection type can be selected from the preset detection type to display the detection results of the detection objects of the display detection type in real time. Furthermore, the displayed detection results can be changed according to the real-time adjustment of the display detection type to control the display and hiding of the target algorithm output results in real time, thereby improving the flexibility of the display. (3) Different display types may exist in different display scenarios. With the detection result display method provided in this application embodiment, no matter how many display scenarios it is applied to, it is only necessary to perform a single detection on the display video to obtain all the detection result files required for all displays. Subsequently, it is only necessary to obtain the corresponding detection result files for the specific display detection type required, generate display data, and display the detection results on the video layer, thereby making the display of detection results more convenient and faster, and saving manpower and time costs. (4) When there are too many detection results that may cause occlusion, the detection type can be automatically filtered according to the preset priority, so that only the detection results of the detection type can be displayed, thereby automatically avoiding mutual occlusion of the detection results; at the same time, if the user operates the interactive interface, the detection type can be filtered according to the operation, so as to manually intervene in the display of the detection type, thereby avoiding occlusion of the detection results. Attached Figure Description

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram illustrating an application scenario of a detection result display method provided in an embodiment of this application; Figure 2 This is a first flowchart illustrating a detection result display method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the second process of a detection result display method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the third process of a detection result display method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the fourth process of a detection result display method provided in an embodiment of this application; Figure 6This is a schematic diagram of the fifth process of a detection result display system provided in an embodiment of this application; Figure 7 This is a schematic diagram of the sixth process of a detection result display system provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of a detection result display device provided in an embodiment of this application; Figure 9 This is a hardware structure block diagram of a server for a detection result display method provided in an embodiment of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely one embodiment of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0025] The term "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of this application. In the description of the embodiments of this application, it should be understood that the terms "upper," "lower," "left," "right," "top," "bottom," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device / system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first" and "second" may explicitly or implicitly include one or more of that feature. Moreover, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms “comprising” and “having” / “being” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system / apparatus, product or device that includes a series of steps or units / modules is not necessarily limited to those steps or units / modules that are explicitly listed, but may include other steps or units / modules that are not explicitly listed or that are inherent to such process, method, product or device.

[0026] The following describes a specific embodiment of a detection result display method provided in this application. Please refer to... Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of a detection result display method provided in an embodiment of this application. For example... Figure 1 As shown, it includes server 101 and terminal 102. Optionally, server 101 and terminal 102 can be connected via a wireless link or a wired link, which is not limited herein.

[0027] Specifically, server 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the operating system running on server 101 may include, but is not limited to, iOS, Linux, Windows, Unix, Android, etc.

[0028] Specifically, terminal 102 may include, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, and Windows.

[0029] In one optional implementation, server 101 can determine the display detection type from preset detection types; obtain the detection result file of the display detection type; the detection result file is obtained by detecting the display video through the target detection model, and the detection result file includes the detection results of the display detection type for all frames of the display video, and the detection results are used to identify the detection objects of the display detection type in the display video; based on the detection result file, the detection result of the display detection type of the current frame is displayed on the upper layer of the display video.

[0030] In addition, it should be noted that, Figure 1 The example shown is merely one application environment of the detection result display method provided in this disclosure. In practical applications, other application environments may also be included, but this embodiment does not limit this.

[0031] The following describes an exemplary process for a detection result display method provided in this application. Figure 2This is a first flowchart illustrating a detection result display method provided in an embodiment of this application. This specification provides the method or process steps shown in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer steps may be included. The order of steps listed in the embodiments is merely one of many execution orders and does not represent the only execution order. In actual execution, the method or process can be executed in the order shown in the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as shown... Figure 2 As shown, the method includes: Step S201: Determine the display detection type from the preset detection types.

[0032] In one optional implementation, the display detection type can be determined from preset detection types. Optionally, the preset detection types may include one or more of the following: pedestrians, cyclists, vehicle front and rear, traffic lights, road signs, lane lines, and vehicle 3D detection frames. The display detection type may include one or more of the preset detection types mentioned above.

[0033] In one alternative implementation, each display detection type may correspond to each detection result file.

[0034] The following is based on Figure 3 To elaborate further.

[0035] Figure 3 This is a schematic diagram of the second process of a detection result display method provided in an embodiment of this application. Specifically, as shown below... Figure 3 As illustrated, prior to step S201, the method may further include: Step S301: Detect the displayed video using the target detection model and obtain the detection results for each preset detection type in the preset detection types.

[0036] Optionally, the object detection model can be used to perform object detection based on the input display video, and the object detection model can output detection results of a preset detection type; the display video can be one of the candidate videos. In this embodiment, step S201 may further include: selecting the display video to be backtracked from the candidate videos.

[0037] The following is based on Figure 4 To elaborate further.

[0038] Figure 4 This is a schematic diagram of the third process of a detection result display method provided in an embodiment of this application. Specifically, as shown below... Figure 4 As illustrated, an exemplary process for step S301 may include: Step S401: Determine the target detection model corresponding to each preset detection type in the preset detection types.

[0039] In one optional implementation, a target detection model corresponding to each preset detection type can be determined. Optionally, there may be multiple target detection models, where each target detection model can be used to detect objects of one or more preset detection types in the displayed video.

[0040] In one optional implementation, a single target detection model may be included. In another optional implementation, multiple target detection models may be included, which may include a target detection model that outputs the detection results of a single preset detection type of object, or a target detection model that outputs the detection results of multiple preset detection types of objects. In embodiments where the preset detection types include pedestrians, cyclists, vehicle front and rear, traffic lights, road signs, lane lines, and vehicle 3D detection boxes, optionally, the multiple target detection models may include a first model, a second model, a third model, and a fourth model; wherein, the first model can be used to output the detection results of pedestrians and cyclists, i.e., the first model corresponds to pedestrians and cyclists; the second model can be used to output the detection results of vehicle front, rear, and vehicle 3D detection boxes, i.e., the second model corresponds to vehicle front, rear, and vehicle 3D detection boxes; the third model can be used to output the detection results of traffic lights, i.e., the third model corresponds to traffic lights; and the fourth model can be used to output the detection results of road signs, i.e., the fourth model corresponds to road signs. It should be noted that the embodiments of this application do not limit the number and correspondence of preset detection types and target detection models. In some other optional implementations, the preset detection type may be other optional detection types, the number of target detection models may be other optional numbers, and the correspondence between target detection models and preset detection types may be other optional correspondences.

[0041] Step S402: Detect the displayed video using the target detection model and obtain the detection results for each preset detection type.

[0042] In one optional implementation, the displayed video can be detected using an object detection model to obtain detection results of a preset detection type. Optionally, the object detection model can be a deep learning algorithm model. Optionally, the displayed video can be detected using each of multiple object detection models to obtain detection results of a preset detection type corresponding to each object detection model.

[0043] In this embodiment, the target detection model is used to detect the display video in advance and output the detection result file. This allows for the convenient acquisition of the corresponding detection result file with low latency based on the actual selected display detection type during the display, and the desired algorithm result is displayed in real time. This ensures that the display effect can efficiently respond to the selected result while filtering the detection object type in real time, so as to facilitate the user's analysis of the algorithm recognition result.

[0044] Step S302: Generate a detection result file based on the detection results of each preset detection type.

[0045] In one optional implementation, a detection result file can be generated based on the detection results of each preset detection type. Optionally, there can be a one-to-one correspondence between preset detection types and detection result files, and each detection result file can contain the detection results of one preset detection type.

[0046] The following continues based on Figure 2 To elaborate: In one optional implementation, step S201 may further include: determining a display video; and determining a preset detection type based on the display video. Optionally, the preset type may be the type of detection object output by the object detection algorithm in advance of the display video. It should be noted that the embodiments of this application do not limit the types included in the preset detection type. In some other optional implementations, the preset detection type may also be the type of detection object that can be output by other optional detection models.

[0047] In one optional implementation, step S201 may include: determining a display detection type from preset detection types in response to a confirmation command from the interactive interface. Optionally, the confirmation command may be generated based on user actions. Optionally, virtual buttons for each preset detection type may be generated on the interactive interface. It should be noted that this application embodiment does not limit the generation method of the confirmation command. In some other optional implementations, the confirmation command may also be generated based on other operations set in other interactive interfaces, such as drop-down menu selection. In one optional implementation, the interactive interface may be displayed in the same visual interface as the displayed video; in another optional implementation, the interactive interface may be located on a different interface than the displayed video, or on a different terminal device than the displayed video playback device.

[0048] In this embodiment of the application, for the same playing display video, whether the video is paused or during playback, the display detection type can be selected from the preset detection types to display the detection results of the detection objects of the display detection type in real time. Furthermore, the displayed detection results can be changed according to the real-time adjusted display detection type to control the display and hiding of the target algorithm output results in real time, thereby improving the flexibility of the display.

[0049] Step S202: Obtain the detection result file that displays the detection type.

[0050] In one alternative implementation, the detection result file of the display detection type can be obtained according to the display detection type.

[0051] Optionally, the detection result file is obtained by detecting the display video using an object detection model. The detection result file includes the detection results of all frames of the display video for the display detection type. The detection results are used to identify the detected objects of the display detection type in the display video. Optionally, the detection result file may include an index file; the object detection model may output multiple index files, wherein each index file in the multiple index files may correspond to a preset detection type. Specifically, at least one display detection type may correspond to at least one index file, and step S202 may include: obtaining at least one index file corresponding to at least one display detection type.

[0052] The following is based on Figure 5 Step S202 will be further explained.

[0053] Figure 5 This is a schematic diagram of the fourth process of a detection result display method provided in an embodiment of this application. Specifically, as shown below... Figure 5 As illustrated, in one optional implementation, each detection result file corresponds to an index number, and an exemplary process for step S202 may include: Step S501: Determine the index number of the detection type to be displayed.

[0054] In one optional implementation, at least one preset detection type can correspond one-to-one with at least one index number, and the index number corresponding to the display detection type can be determined from at least one index number.

[0055] Step S502: Read the detection result file based on the index number.

[0056] In one optional implementation, the detection result file can be read based on the index number. Optionally, if there are multiple index numbers, the detection result file corresponding to each index number can be read based on each of the multiple index numbers, resulting in multiple detection result files.

[0057] Optionally, the detection result file read in step S502 corresponds to the display detection type in step S501; each detection result file may include the detection results of each display detection type for all frames of the displayed video, specifically, the detection results of each video image in all frames.

[0058] Step S203: Based on the detection result file, display the detection result of the current frame's display detection type on top of the display video.

[0059] In one optional implementation, display data can be generated based on the detection result file, and the detection result of the display detection type of the current frame can be displayed on top of the displayed video. Specifically, the detection result file may include the detection result of the display detection type of each frame of the displayed video. Display data for all frames can be generated based on the detection result file, and the detection result of the display detection type of the current frame can be displayed on top of the current frame based on the display data of the current frame.

[0060] Optionally, the interactive interface includes a progress bar, which can be generated based on all frames of the displayed video. The progress bar includes a movable slider, the position of which represents the current frame. This slider can move automatically frame by frame over time, and users can also move the slider through the interactive interface. By moving the slider, the current frame can be determined from all frames based on the slider's position, allowing selection of the video image to be played and the detection results. The front-end webpage display module can display the video image of the current frame in the displayed video, and display the target detection results of the current frame on top of the video image. By manipulating the slider on the progress bar, the displayed video can be forwarded and rewound. Specifically, the displayed video can start playing from the frame corresponding to the position after the slider is dragged, and the algorithm results are displayed frame by frame. By clicking the pause button on the interactive interface, the displayed video can be paused. That is, when the pause button is clicked, the slider on the progress bar stops moving, the displayed video pauses at the frame corresponding to the slider's current position, and the algorithm results of the current frame are continuously displayed.

[0061] In this embodiment, a single video test can yield detection results for all preset detection types. Different display scenarios may have different display type requirements. The detection result display method provided in this embodiment allows for the acquisition of all required detection result files for a single video test, regardless of the application scenario. Subsequent testing only requires obtaining the corresponding detection result files for the specific required display detection type, generating display data, and then displaying the detection results on top of the video. This makes the display of detection results more convenient and faster, while saving manpower and time costs.

[0062] The following is based on Figure 6Step S203 will be further explained.

[0063] Figure 6 This is a schematic diagram of the fifth step in a detection result display method provided in an embodiment of this application. Specifically, as shown below... Figure 6 As illustrated, step S203 may include: Step S601: If the number of objects detected by the display detection type in the current frame is greater than the threshold, determine the display detection type from the display detection types according to the priority of the preset detection types.

[0064] In one alternative implementation, if the number of detected objects of the display detection type in the current frame is greater than a threshold, the display prediction type can be determined from the display detection types according to the priority of the preset detection types.

[0065] Optionally, the priority of preset detection types can be pre-configured. In embodiments where preset detection types include pedestrians, cyclists, vehicle front and rear, traffic lights, road signs, lane lines, and vehicle 3D detection boxes, the priority order from high to low can optionally be pedestrians, cyclists, vehicle 3D detection boxes, vehicle front and rear, traffic lights, road signs, and lane lines. Optionally, types with a priority higher than the preset priority among the display detection types can be determined as display prediction types.

[0066] Optionally, the numerical value of the detected object for the prediction type can be less than or equal to the threshold.

[0067] Optionally, step S601 may further include: if a confirmation command generated by the interactive interface is detected, determining a display detection type from the preset detection types based on the confirmation command.

[0068] Step S602: Based on the detection result file, display the detection result of the current frame's display detection type on top of the displayed video.

[0069] In one alternative implementation, the detection results of the current frame's display detection type can be displayed on top of the displayed video, based on the detection result file.

[0070] In this embodiment, when there are too many detection results that may cause occlusion, the detection types to be displayed can be automatically filtered according to a preset priority, so that only the detection results of the detection types to be displayed are shown, thereby automatically avoiding mutual occlusion of the detection results; at the same time, if the user operates the interactive interface, the detection types to be displayed can also be filtered according to the operation, so as to manually intervene in the display of detection types and thus avoid occlusion of the detection results.

[0071] The following is based on Figure 7 Step S203 will be further explained.

[0072] Figure 7 This is a schematic diagram of the sixth process of a detection result display method provided in an embodiment of this application. Specifically, as shown below... Figure 7 As illustrated, optionally, the preset detection type includes a first detection type and a second detection type, and step S203 may include: Step S701: If there is a detection object of the first detection type in the current frame, display the detection result of the second detection type of the current frame on the upper layer of the display video based on the detection result file of the second detection type.

[0073] In one alternative implementation, if a detection object of the first detection type exists in the current frame, the detection result of the second detection type of the current frame can be displayed on top of the displayed video based on the detection result file of the second detection type.

[0074] In one optional implementation, the first detection type may include traffic lights, and the second detection type may include pedestrians and cyclists. Alternatively, the first detection type may include traffic lights, and the second detection type may include pedestrians, cyclists, vehicle front and rear. Optionally, if the number of objects detected by the display detection type in the current frame exceeds a threshold, and the current frame contains objects detected by the first detection type, the objects detected by the second detection type in the current frame can be displayed on top of the displayed video. If the number of objects detected by the display detection type in the current frame exceeds a threshold, and the current frame does not contain objects detected by the first detection type, the display detection type can be determined according to its priority, and the detection result of the display detection type of the current frame can be displayed on top of the displayed video.

[0075] In this embodiment, the detection objects corresponding to the displayed detection results can be automatically adjusted to be the key detection objects according to the real-time scene of the displayed video, thereby improving the display efficiency of the algorithm recognition results.

[0076] Accordingly, this application also provides a device for displaying detection results. Figure 8 This is a schematic diagram of the structure of a detection result display device provided in an embodiment of this application. Figure 8 As illustrated, the test result display device 800 may include: Type module 801 is used to determine the display detection type from preset detection types; The acquisition module 802 is used to acquire the detection result file of the display detection type. The detection result file is obtained by detecting the display video through the target detection model. The detection result file includes the detection results of the display detection type for all frames of the display video. The detection results are used to identify the detection objects of the display detection type in the display video. The display module 803 is used to display the detection results of the current frame on top of the display video based on the detection result file.

[0077] Optionally, each display detection type corresponds to each detection result file; the device may also include a detection module, used to detect the display video through a target detection model before determining the display detection type from the preset detection types, to obtain the detection result of each preset detection type in the preset detection types; and to generate a detection result file based on the detection result of each preset detection type.

[0078] Optionally, each detection result file corresponds to an index number; the acquisition module 801 is used to: determine the index number of the detection type to be displayed; and read the detection result file based on the index number.

[0079] Optionally, the display module 803 is used to: determine the target detection model corresponding to each preset detection type in the preset detection types; detect the display video through the target detection model to obtain the detection result of each preset detection type.

[0080] Optionally, the type module 801 is used to: determine the display detection type from the preset detection types in response to the confirmation command of the interactive interface; the interactive interface is used to play the display video.

[0081] Optionally, the display module 803 is used to: determine the display detection type from the display detection types according to the priority of the preset detection types when the number of detected objects of the display detection type in the current frame is greater than the threshold; and display the detection results of the display detection type of the current frame on the upper layer of the display video based on the detection result file.

[0082] Optionally, the preset detection types include a first detection type and a second detection type. The display module 803 is used to: if a detection object of the first detection type exists in the current frame, display the detection result of the second detection type of the current frame on top of the display video based on the detection result file of the second detection type.

[0083] The device and method embodiments provided in this application can be based on the same concept.

[0084] Accordingly, embodiments of this application also provide a detection result display system. Optionally, the system may include an algorithm parsing module and an algorithm backtracking module.

[0085] In one optional implementation, the algorithm parsing module may include a front-end webpage display module and a back-end algorithm parsing module. Optionally, the front-end webpage display module may be used to select an algorithm model and upload the video to be displayed; the back-end algorithm parsing module may be used to apply the selected algorithm model to parse the uploaded video and generate a result index file.

[0086] Optionally, the algorithm parsing module can be used to detect the displayed video using an object detection model, obtaining the detection results for each preset detection type; and generating a detection result file based on the detection results for each preset detection type. Optionally, the front-end webpage display module can be used to select the object detection model corresponding to each preset detection type; the back-end algorithm parsing module can be used to detect the displayed video using the object detection model, obtaining the detection results for each preset detection type, and generating a detection result file based on the detection results for each preset detection type. Optionally, the detection result file may include a result index file.

[0087] The algorithm backtracking module can include a front-end page display module and a back-end result generation module.

[0088] In one optional implementation, the front-end page display module can select the video to be retraced from the candidate videos based on page operations, generate a progress bar, determine the result index file based on the retraced video, and generate an interactive interface based on the determined result index file. The interactive interface is used to generate a confirmation command based on user operations, which can be used to determine the display detection type from preset detection types. Optionally, the progress bar is generated based on all frames of the displayed video. The progress bar includes a movable slider, the position of which represents the current frame. The slider can move automatically frame by frame over time, and the user can also move the slider through the interactive interface. By moving the slider, the current frame can be determined from all frames based on the slider's position to select the video image to play and the detection result; the front-end webpage display module can display the video image of the current frame in the displayed video and display the target detection result of the current frame on top of the video image. By operating the slider on the progress bar, the displayed video can also be forwarded and rewound. Specifically, the displayed video can start playing from the frame corresponding to the position after the slider is dragged, and the algorithm results are displayed frame by frame. By clicking the pause button on the interactive interface, you can pause the displayed video. In other words, when you click the pause button, the slider on the progress bar stops moving, the video pauses at the frame corresponding to the slider's current position, and the algorithm result for the current frame is continuously displayed.

[0089] The backend result generation module can be used to read all the contents of the result index file of the display detection type, generate data, and return it to the front-end page for display.

[0090] Optionally, the algorithm backtracking module can be used to determine the display detection type from preset detection types; obtain the detection result file of the display detection type; the detection result file is obtained by detecting the display video through the target detection model, and the detection result file includes the detection results of the display detection type for all frames of the display video, and the detection results are used to identify the detection objects of the display detection type in the display video; based on the detection result file, the detection result of the display detection type of the current frame is displayed on top of the display video. Optionally, the front-end page display module can be used to play the display video, determine the display detection type from preset detection types, and display the detection result of the display detection type. The back-end result generation module can be used to obtain the detection result file of the display detection type. Optionally, obtaining the detection result file of the display detection type may include: determining the index number of the display detection type; reading the detection result file based on the index number. Determining the display detection type from preset detection types may include: responding to the confirmation command of the interactive interface to determine the display detection type from preset detection types.

[0091] The system embodiments provided in this application can be based on the same concept as the method embodiments.

[0092] Accordingly, this disclosure also provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The processor loads and executes the at least one instruction, at least one program, code set, or instruction set to implement the above-described detection result display method.

[0093] The methods and embodiments provided in this application can be executed on a computer terminal, server, or similar computing device. Taking running on a server as an example, Figure 9 This is a hardware structure block diagram of the server for the detection result display method provided in this application embodiment. For example... Figure 9As shown, the server 900 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 910 (CPUs 910 may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory 930 for storing data, and one or more storage media 920 (e.g., one or more mass storage devices) for storing application programs 923 or data 922. The memory 930 and storage media 920 may be temporary or persistent storage. The program stored in the storage media 920 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 910 may be configured to communicate with the storage media 920 and execute the series of instruction operations stored in the storage media 920 on the server 900. Server 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input / output interfaces 940, and / or one or more operating systems 921, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0094] The input / output interface 940 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 900. In one example, the input / output interface 940 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 940 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0095] Those skilled in the art will understand that Figure 9 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 900 may also include... Figure 9 The more or fewer components shown, or having the same Figure 9 The different configurations shown.

[0096] This application provides a storage medium that can be located in a server to store at least one instruction, at least one program, code set, or instruction set related to the detection result display method in the method embodiment. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the above-mentioned detection result display method.

[0097] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Alternatively, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), portable hard drives, magnetic disks, or optical disks.

[0098] In this invention, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the connection within two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0099] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, while this specification describes specific embodiments, other embodiments are also within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in the order shown in different embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific order or sequence of connections to achieve the desired results; in some implementations, parallel processing of multiple tasks is possible or may be advantageous.

[0100] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of the apparatus / system are relatively simple in description because they are based on similarity to the method embodiments; relevant parts can be referred to the descriptions of the method embodiments.

[0101] The above are preferred embodiments of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for displaying test results, characterized in that, include: In response to the confirmation command from the interactive interface, determine the detection type to display from the preset detection types; The interactive interface is used to play and display videos; The interactive interface includes a progress bar, which is generated based on all frames of the displayed video. The progress bar includes a movable slider, the position of which represents the current frame. Determine the index number of the display detection type; Based on the index number, read the detection result file corresponding to the display detection type; The detection result file is obtained by detecting the display video through the target detection model. The detection result file includes the detection results of the display detection type for all frames of the display video. The detection results are used to identify the detection objects of the display detection type in the display video. If the number of objects detected by the display detection type in the current frame is greater than a threshold, a display detection type is determined from the display detection types according to the priority of the preset detection types; the preset detection types include a first detection type and a second detection type. The second detection type has a higher priority than the first detection type; If the current frame contains a detection object of the first detection type, the detection result of the second detection type of the current frame is displayed on top of the displayed video based on the detection result file of the second detection type.

2. The method for displaying detection results according to claim 1, characterized in that, Each of the aforementioned display detection types corresponds to each of the aforementioned detection result files; Before determining the display detection type from the preset detection types, the method further includes: The displayed video is detected using an object detection model, and the detection results for each of the preset detection types are obtained. The detection result file is generated based on the detection results of each preset detection type.

3. The method for displaying detection results according to claim 2, characterized in that, Each of the aforementioned test result files corresponds to an index number.

4. The method for displaying detection results according to claim 2, characterized in that, The step of detecting the displayed video using a target detection model to obtain the detection result for each preset detection type in the preset detection types includes: Determine the target detection model corresponding to each preset detection type in the preset detection types; The target detection model is used to detect the displayed video, and the detection results of each preset detection type are obtained.

5. A device for displaying test results, characterized in that, include: The type module is used to determine the display detection type from the preset detection types in response to the confirmation command of the interactive interface; The interactive interface is used to play and display videos; The interactive interface includes a progress bar, which is generated based on all frames of the displayed video. The progress bar includes a movable slider, the position of which represents the current frame. The acquisition module is used to determine the index number of the display detection type; and based on the index number, read the detection result file corresponding to the display detection type. The detection result file is obtained by detecting the display video using a target detection model. The detection result file includes the detection results of the display detection type for all frames of the display video. The detection results are used to identify the detection objects of the display detection type in the display video. The display module is configured to, when the number of detected objects of the display detection type in the current frame is greater than a threshold, determine a display detection type from the display detection types according to the priority of the preset detection types; the preset detection types include a first detection type and a second detection type; the priority of the second detection type is higher than the priority of the first detection type; when there are detected objects of the first detection type in the current frame, display the detection results of the second detection type of the current frame on the upper layer of the display video based on the detection result file of the second detection type.

6. An electronic device, characterized in that, The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the processor loads and executes the at least one instruction, at least one program, code set, or instruction set to implement the detection result display method of any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the detection result display method as described in any one of claims 1-4.

Images