Surveillance video synthesis method and surveillance video processing system

Abstract

The present application discloses a surveillance video synthesis method and a surveillance video processing system. The present application relates to the field of video storage technology. The method comprises: obtaining a time sequence of a target vehicle passing through each license plate recognition checkpoint, and determining a time interval according to the time sequence; according to the time interval, intercepting a video clip associated with the target vehicle from a video file collected by a monitoring device, and generating a full-process video corresponding to the target vehicle according to the video clip and the time interval; and saving the full-process video to reduce the storage overhead of the vehicle recorded video.

Description

Technical Field

[0001] The present application relates to the field of video storage technology, and in particular to a surveillance video synthesis method and a surveillance video processing system. Background Art

[0002] In order to realize the video recording of the vehicle's entry and exit process in a closed place, generally after the vehicle enters the closed place, a high-altitude Hawkeye camera is used to record the entire park. Then, according to the time when the vehicle enters and leaves the park, the video clips of the corresponding time interval are intercepted and stored in association with the vehicle information.

[0003] In actual application, due to the different panoramic camera clarity of the high-altitude Hawkeye camera and the large range of recorded scenes, it is difficult to focus on other irrelevant elements in the captured content. Therefore, when saving the recorded video, a large amount of storage space is required to store the video file because the recorded video contains a lot of irrelevant information, which leads to a large storage overhead for the vehicle recorded video in the relevant solution.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The present application provides a surveillance video synthesis method and a surveillance video processing system, aiming to solve the problem of high storage overhead of vehicle recorded videos in related solutions.

[0006] To achieve the above object, the present application provides a surveillance video synthesis method, which comprises the following steps:

[0007] Obtaining a time sequence of the target vehicle passing through each of the license plate recognition checkpoints, and determining a time interval according to the time sequence;

[0008] According to the time interval, a video clip associated with the target vehicle is intercepted from a video file collected by a monitoring device, and a full-process video corresponding to the target vehicle is generated according to the video clip and the time interval;

[0009] Save the video of the whole process.

[0010] In one embodiment, after the step of obtaining the time sequence of the target vehicle passing through the license plate recognition checkpoint and determining the time interval according to each time sequence, the step further includes:

[0011] Receiving the license plate recognition result sent by the license plate recognition card port;

[0012] When the target vehicle passes through the license plate recognition checkpoint, marking the path point of the target vehicle in the preset park model;

[0013] Generate a motion path of the target vehicle according to the path points and the preset park model;

[0014] The motion path is associated with the vehicle identification of the target vehicle and stored.

[0015] In one embodiment, the method comprises:

[0016] When the target vehicle passes through a first target license plate recognition checkpoint, determining an adjacent license plate recognition checkpoint corresponding to the first target vehicle recognition checkpoint;

[0017] If the neighboring license plate recognition checkpoint fails to detect the target vehicle within a preset time period, it is determined that the target vehicle has abnormal behavior;

[0018] When the second target license plate recognition checkpoint detects that the target vehicle passes by, it is determined that the target vehicle has abnormal behavior.

[0019] In one embodiment, the method comprises:

[0020] When the initial license plate recognition checkpoint detects the target vehicle, starting a timer and associating the timer with the vehicle identification of the target vehicle;

[0021] When the time in the timer is equal to the preset time, detecting whether the license plate recognition checkpoint detects the target vehicle is finished;

[0022] If not, the vehicle identification of the target vehicle is fed back to the client.

[0023] In one embodiment, the step of intercepting the video segment associated with the target vehicle from the video file collected by the monitoring device according to the time interval includes:

[0024] Determine a first license plate recognition checkpoint and a second license plate recognition checkpoint corresponding to the time interval;

[0025] Determining the monitoring device between the first license plate recognition checkpoint and the second license plate recognition checkpoint;

[0026] The video file collected by the monitoring device is obtained, and the video segment is extracted from the video file according to the time interval.

[0027] In one embodiment, the step of intercepting a video clip associated with the target vehicle from a video file collected by a monitoring device according to the time interval, and generating a full-process video corresponding to the target vehicle according to the video clip and the time interval includes:

[0028] Obtaining a video file collected by the monitoring device;

[0029] Sending the video file and the time interval to a sub-video processing server, wherein the sub-video processing server intercepts a video segment associated with the target vehicle from the video file collected by the monitoring device according to the time interval, and generates a full-process video corresponding to the target vehicle according to the video segment and the time interval;

[0030] Control the sub-video processing server to send the whole process video to the storage server.

[0031] In one embodiment, after the step of obtaining the video file collected by the monitoring device, the method further includes:

[0032] Determining each of the video files and an associated time interval;

[0033] Determine a vehicle identification of each vehicle, and create a preset queue according to each vehicle identification, wherein the preset queue is associated with the vehicle identification;

[0034] The video file and the associated time interval are placed in a preset queue associated with the corresponding vehicle identification.

[0035] In one embodiment, the method further comprises:

[0036] The license plate recognition checkpoints are set at the starting point and the ending point, and a first preset number of license plate recognition checkpoints are set on the path between the starting point and the ending point;

[0037] The monitoring device is arranged between the license plate recognition bayonet and an adjacent license plate recognition bayonet, and a second preset number of the monitoring devices are arranged.

[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a surveillance video processing system, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the surveillance video synthesis method as described above.

[0039] The surveillance video synthesis method and surveillance video processing system provided in the present application obtain the time series of the target vehicle passing through each license plate recognition checkpoint, and determine the time interval based on the time series, and then, based on the time interval, intercept the video clip associated with the target vehicle from the video file collected by the monitoring equipment, and generate the full process video corresponding to the target vehicle based on the video clip and the time interval, and finally save the full process video to reduce the storage overhead of the vehicle recorded video. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for synthesizing surveillance videos of the present application;

[0043] Figure 2 A diagram showing the arrangement of a license plate recognition bayonet and monitoring equipment involved in the embodiment of the present application;

[0044] Figure 3 This is an overview of the park involved in the embodiment of this application;

[0045] Figure 4 A schematic diagram of a flow chart of a second embodiment of a method for synthesizing surveillance videos of the present application;

[0046] Figure 5 A schematic diagram of a flow chart of a third embodiment of the method for synthesizing surveillance videos of the present application;

[0047] Figure 6 This is a schematic diagram of the architecture of the hardware operating environment of the monitoring video processing system involved in the embodiment of the present application.

[0048] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] In order to better understand the above technical solution, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0051] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0052] The main solution of the present application is: by obtaining the time series of the target vehicle passing through each license plate recognition checkpoint, and determining the time interval based on the time series, and then according to the time interval, intercepting the video clip associated with the target vehicle from the video file collected by the monitoring equipment, and generating the full process video corresponding to the target vehicle based on the video clip and the time interval, and finally saving the full process video.

[0053] At present, in order to realize the video recording of the vehicle's entry and exit process in a closed place, a high-altitude Hawkeye camera is generally used to record the entire park after the vehicle enters the closed place. Then, according to the time when the vehicle enters and leaves the park, the video clips of the corresponding time interval are intercepted and stored in association with the vehicle information.

[0054] In actual application, due to the different panoramic camera clarity of the high-altitude Hawkeye camera and the large range of recorded scenes, it is difficult to focus on other irrelevant elements in the captured content. Therefore, when saving the recorded video, a large amount of storage space is required to store the video file because the recorded video contains a lot of irrelevant information, which leads to a large storage overhead for the vehicle recorded video in the relevant solution.

[0055] The present application obtains the time series of the target vehicle passing through the license plate recognition checkpoint, determines the time interval according to each time series, and then, based on the time interval, captures the video clip associated with the target vehicle from the video file collected by the monitoring equipment, and generates the full-process video corresponding to the target vehicle based on the video clip and the time interval, and finally saves the full-process video, thereby reducing the storage overhead of the vehicle recorded video.

[0056] It should be noted that the execution subject of this embodiment can be a monitoring video processing system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a monitoring video synthesis device capable of realizing the above functions, etc., and this embodiment does not specifically limit this. The following takes the monitoring video processing system as the execution subject as an example to illustrate this embodiment and the following embodiments.

[0057] Embodiment 1

[0058] Please refer to Figure 1 In a first embodiment, the surveillance video synthesis method comprises the following steps:

[0059] Step S10: Obtain the time sequence of the target vehicle passing through each of the license plate recognition checkpoints, and determine the time interval according to the time sequence.

[0060] In this embodiment, the processing action is performed by a monitoring video processing system, wherein the monitoring video processing system includes a license plate recognition checkpoint, a monitoring device, and a video processing server, and the video processing server is connected to the license plate recognition checkpoint and the monitoring device. When the target vehicle enters the park, the license plate recognition checkpoint can recognize the license plate number of the target license plate and record the time point when the target vehicle passes through the license plate recognition checkpoint, wherein the license plate recognition checkpoint includes a camera (including an ordinary camera and an infrared camera to adapt to different light conditions), an image acquisition device, image processing software, a license plate recognition algorithm, a data storage module, and related network communication facilities. There is at least one license plate recognition checkpoint, and the passing time points of the target vehicle are recorded by multiple license plate recognition checkpoints, so that the time points are composed into the time series, and the time points of two adjacent license plate recognition checkpoints in the time series are merged into a time interval.

[0061] Specifically, the workflow of the license plate recognition checkpoint is to continuously capture images of passing vehicles through a camera, and analyze these images with image processing software. First, the license plate position is located and the time when the vehicle enters the park is recorded. Then, character segmentation and recognition technology is used to extract the license plate number from the license plate image. Finally, the recognition result is compared with the vehicle information in the database to confirm the identity of the vehicle.

[0062] Optionally, in this embodiment, the method further includes:

[0063] The license plate recognition checkpoints are set at the starting point and the end point, and a first preset number of the license plate recognition checkpoints are set on the path between the starting point and the end point; the monitoring device is set between the license plate recognition checkpoint and the adjacent license plate recognition checkpoint, and a second preset number of the monitoring devices are set.

[0064] Specifically, the starting point and the ending point are the starting point and the ending point of the park. A license plate recognition checkpoint is set at the starting point and the ending point respectively, so that the recording can start as soon as the vehicle enters the park, and the last time point is recorded when the vehicle reaches the ending point. The first preset number is the number that can evenly cover the park. The specific setting can be the number determined by the staff according to the actual evaluation of the road conditions in the park. The monitoring equipment is set between the license plate recognition checkpoint and the adjacent license plate recognition checkpoint, and the second preset number is less than the first preset number.

[0065] It is understandable that the camera should be matched according to the shooting range and clarity requirements required by the camera, and surveillance cameras of uniform specifications should be used. And according to the speed limit of the roads in the park, the corresponding performance specifications should be matched. The upper limit of the vehicle speed supported by the license plate recognition bayonet must be higher than the speed limit of the roads in the park. It is required that vehicles in the park should maintain a certain distance to prevent vehicles from blocking each other's license plate recognition bayonet, resulting in abnormal alarms. In a specific park, the distance between vehicles can be manually intervened by setting some speed bumps or some additional gates.

[0066] For example, Figure 2 As shown, Figure 2 This is a diagram of the license plate recognition checkpoints and monitoring equipment settings involved in the implementation scheme of the present application. A group of surveillance cameras is used to fully monitor and cover the internal roads within the park and maintain continuous recording. Vehicle license plate recognition checkpoints are set up at certain intervals throughout the road range to ensure that there is a surveillance camera covering every two license plate recognition checkpoints. Assume that the park uses 10 surveillance cameras to cover the roads in the park from the time the vehicle enters the park to the time the vehicle exits the park, and the cameras maintain normal all-weather surveillance recording. From the entrance of the park to the exit of the park, at least 11 license plate recognition checkpoints (usually the first and last two checkpoints are the parking gates of the park) are used to segment the park roads to ensure that the roads between every two adjacent license plate recognition checkpoints can be covered by the recording range of a surveillance camera.

[0067] Step S20: According to the time interval, a video clip associated with the target vehicle is intercepted from the video file collected by the monitoring device, and a full-process video corresponding to the target vehicle is generated according to the video clip and the time interval.

[0068] In this embodiment, a monitoring device is set in the two license plate recognition checkpoints. In the above step S10, the time point when the target vehicle passes through the license plate recognition checkpoint is captured by the license plate recognition checkpoint, and the time points of the two adjacent license plate recognition checkpoints are merged into a time interval. The video file contains the video files of all vehicles passing in this time interval, so it is necessary to intercept the video clip of the target vehicle in the video file. According to the video clips associated with the target vehicle intercepted by multiple monitoring devices, the video clips are spliced ​​based on the corresponding time interval to generate the full process video corresponding to the target vehicle.

[0069] Specifically, the video processing server obtains the "segments of the 'video recording' recorded by the camera covering the start time to the end time of the vehicle's passage through each road segment" in the video surveillance recorder through the SDK of the monitoring device, forming a sequence of video clip groups, connecting the video clips in chronological order, and re-encoding the video using an encoder to generate the corresponding "full process video of the vehicle from the entry to the exit position", and store it separately for viewing and calling. In addition, all monitoring and identification equipment are connected to a single NTP time synchronization server. Under normal use, the timestamps in all synthesized videos of the entire vehicle driving process can remain consistent, and finally the generated second video file is saved in the file storage server.

[0070] Optionally, in this embodiment, the step of intercepting the video segment associated with the target vehicle from the video file collected by the monitoring device according to the time interval includes:

[0071] Determine the first license plate recognition checkpoint and the second license plate recognition checkpoint corresponding to the time interval; determine the monitoring device between the first license plate recognition checkpoint and the second license plate recognition checkpoint; obtain the video file collected by the monitoring device, and extract the video clip from the video file according to the time interval.

[0072] Specifically, the first license plate recognition checkpoint and the second license plate recognition checkpoint are the license plate recognition checkpoints corresponding to the start time point and the end time point in the target time interval. Therefore, the first video file collected by the monitoring device is the video file of the target time interval where the first license plate recognition checkpoint and the second license plate recognition checkpoint are the start time point and the end time point in the target time interval.

[0073] Exemplarily, all surveillance cameras operate in the general surveillance camera mode, maintain continuous recording, and store the surveillance video data in the surveillance video recorder. Assume that when a vehicle enters the park and leaves the park, n time points will be obtained from the license plate recognition checkpoint. The n time points are the time when the vehicle passes through each license plate recognition checkpoint, which are recorded as T1, T2, T3, ..., Tn-1, Tn respectively. These n time points will form n-1 time intervals: (T1~T2), (T2~T3), (T3~T4), ..., (Tn-2~Tn-1), (Tn-1~Tn), that is, the "entry time" and "exit time" when the vehicle passes through each "road segment divided by the license plate recognition checkpoint into which the vehicle passes in the park".

[0074] Step S30: Save the whole process video.

[0075] In this embodiment, the whole process video can be stored in the database of the video processing server, or in the storage medium of the video processing server. In addition, a storage server can be added to store the whole process video of the vehicle and its entry into the park, and a timed cleanup function is set to automatically delete the video files that have been stored for more than a preset time, so as to increase the storage space of the server.

[0076] Optionally, in this embodiment, after the step of obtaining the time sequence of the target vehicle passing through the license plate recognition checkpoint and determining the time interval according to each time sequence, the step further includes:

[0077] Receive the license plate recognition result sent by the license plate recognition checkpoint; when the target vehicle passes the license plate recognition checkpoint, mark the path points of the target vehicle in the preset park model; generate the movement path of the target vehicle according to the path points and the preset park model; associate the movement path with the vehicle identification of the target vehicle and save it.

[0078] Specifically, when the target vehicle passes through the license plate recognition checkpoint, the license plate recognition checkpoint is marked. Similarly, all the license plate recognition checkpoints passed by the target vehicle are marked and determined as path points in the preset park model, so that the movement path of the target vehicle can be outlined in the preset park model according to the marked path points.

[0079] For example, Figure 3 As shown, Figure 3 This is an overview of the park involved in the embodiment of this application. Assuming that there are several forked roads in the park, when a vehicle enters the park and leaves the park, it will pass through a sequence of license plate recognition checkpoints. By reasonably arranging the license plate recognition checkpoints, the path of the vehicle can be determined by the order in which the vehicle is recognized by the highlighted license plate recognition checkpoints. The surveillance video covering the roads between the corresponding checkpoints in the corresponding time interval is intercepted for synthesis.

[0080] Furthermore, the whole process video may be encoded based on a preset encoding algorithm and in accordance with a target encoding protocol, and the encoded second video file may be stored in a database.

[0081] Specifically, the decoding and encoding speeds can be increased by using GPU (graphics processing unit) and GPU-related algorithms to greatly improve video processing efficiency. The cost between "video processing rate" and "storage capacity occupied by synthesized video files" can be fully balanced by using appropriate encoding protocols / formats (such as H.264, H.265, AV1, etc.) and encoding configurations (such as frame rate, resolution, bit rate, etc.). Combining the above optimization measures, ensure that in the entire operating system, the "average processing generation rate of the video processing equipment for the 'full process video of each vehicle from the entrance to the exit position'" is higher than the "frequency of vehicle visits to the park".

[0082] In the technical solution provided in this embodiment, the time point when the target vehicle passes through the license plate recognition checkpoint is captured by each license plate recognition checkpoint, and the corresponding time interval is determined according to each time point, and then the first video file collected by the monitoring device between the first license plate recognition checkpoint and the second license plate recognition checkpoint is obtained, and the first video file is associated with the target time interval corresponding to the first license plate recognition checkpoint and the second license plate recognition checkpoint, and the first license plate recognition checkpoint and the second license plate recognition checkpoint are the license plate recognition checkpoints corresponding to the start time point and the end time point in the target time interval. Finally, according to the target time interval associated with each first video file, each first video file is formed into a sequence of video clip groups, and according to the order of each target time interval, the video clips are spliced ​​to generate a corresponding second video file, and the second video file is a full process video from the initial license plate recognition checkpoint to the end license plate recognition checkpoint, thereby improving the processing efficiency of vehicle recording video. In addition, due to the different panoramic camera clarity of the high-altitude Hawkeye camera and the large range of recorded scenes, it is difficult to focus the shooting content. Therefore, staff are required to search for the target vehicle in the video and organize the scattered video clips into a video recording file of the target vehicle's movement from entry to exit. This results in low processing efficiency of vehicle recorded videos in related schemes. The present application can also solve the problem of low processing efficiency of the above-mentioned vehicle recorded videos to improve the processing efficiency of vehicle recorded videos.

[0083] Embodiment 2

[0084] Please refer to Figure 4 In a second embodiment, the method comprises:

[0085] Step S40: When the target vehicle passes through a first target license plate recognition checkpoint, an adjacent license plate recognition checkpoint corresponding to the first target vehicle recognition checkpoint is determined.

[0086] Step S50: within a preset time period, the neighboring license plate recognition checkpoint does not detect the target vehicle, and determines that the target vehicle has abnormal behavior.

[0087] Step S60: When the second target license plate recognition checkpoint detects that the target vehicle passes by, it is determined that the target vehicle has abnormal behavior.

[0088] In this embodiment, when the target vehicle passes through the first target license plate recognition checkpoint, the current time point is recorded, and all license plate recognition checkpoints associated with the first target license plate recognition checkpoint are obtained, that is, all adjacent license plate recognition checkpoints adjacent to the first target license plate recognition checkpoint. Monitor whether the adjacent license plate recognition checkpoint passes through the target vehicle, and count the monitoring time according to the time point. When the monitoring time is longer than the preset time, it is determined that the target vehicle has abnormal behavior. The abnormal behavior may indicate that the target vehicle has stopped for a long time between the two checkpoints, or that the target vehicle has performed other operations between the two checkpoints. The location of the vehicle in the park can be determined based on the location of the checkpoint.

[0089] Specifically, the second target license plate recognition port is a license plate recognition port that is not adjacent to the first target license plate recognition port. When a single vehicle passes through the recognition sequence of license plate recognition ports, if a non-adjacent port detects the target vehicle, the abnormal behavior includes abnormal vehicle driving, such as the vehicle has left the park road, the vehicle is speeding, or the vehicle is too close when passing the port, resulting in the vehicle not being recognized, or the license plate recognition port is faulty and should be repaired in time.

[0090] Furthermore, in this embodiment, the method includes:

[0091] When the initial license plate recognition checkpoint monitors the target vehicle, a timer is started and the timer is associated with the vehicle identification of the target vehicle; when the duration in the timer is equal to the preset duration, detection is completed to determine whether the license plate recognition checkpoint monitors the target vehicle; if not, the vehicle identification of the target vehicle is fed back to the client.

[0092] Specifically, if a single target vehicle has only passed through one entrance, the abnormal behavior includes that the target vehicle has not left for a long time after entering, the park management has abnormally released the vehicle, and there are other unsupervised exits in the park. At this time, the vehicle identification is fed back to the client so that the staff can troubleshoot the corresponding fault.

[0093] In the technical solution provided in this embodiment, when the target vehicle passes through the first target license plate recognition checkpoint, the first time point when the target vehicle passes through the first target vehicle recognition checkpoint is recorded, and then the adjacent license plate recognition checkpoint adjacent to the first target license plate recognition checkpoint is monitored. If the monitoring time is greater than or equal to the preset time length and the target vehicle is not monitored to pass through the adjacent license plate recognition checkpoint, it is determined that the target vehicle has abnormal behavior, so that it can be checked whether the entering target vehicle has abnormal behavior, so as to improve the control efficiency of the vehicles in the park.

[0094] Embodiment 3

[0095] Please refer to Figure 5 In the third embodiment, the step S20 includes:

[0096] Step S70: Obtain the video file collected by the monitoring device.

[0097] Step S80: Send the video file and the time interval to a sub-video processing server, wherein the sub-video processing server extracts the video clip associated with the target vehicle from the video file collected by the monitoring device according to the time interval, and generates a full-process video corresponding to the target vehicle according to the video clip and the time interval.

[0098] Step S90: Control the sub-video processing server to send the whole process video to the storage server.

[0099] In this embodiment, the video processing server includes a main video processing server and a sub-video processing server, and the main video processing server is responsible for summarizing the video files of all time intervals and distributing and processing the summarized video files. The main video processing server obtains all associated video files and time intervals, and first saves all the associated video files and time intervals as files to be processed. The main video processing server reasonably distributes the files to be processed according to the service status of the sub-video processing server, or first determines the service status of the sub-video processing server, and when the service status is a preset state, sends the video file and the time interval to the sub-video processing server, wherein the preset state is that the processing volume of the sub-video processing server is lower than its own threshold processing volume. When the sub-video processing server receives the video file and the time interval, it executes the action of intercepting the video clip associated with the target vehicle from the video file collected by the monitoring device according to the time interval, and generating the full process video corresponding to the target vehicle according to the video clip and the time interval, and after the processing is completed, the full process video of the vehicle is associated with the vehicle identification and sent to the storage server.

[0100] Optionally, in this embodiment, after step S70, the following steps are further included:

[0101] Determine each of the video files and the associated time interval; determine the vehicle identification of each vehicle, and create a preset queue based on each of the vehicle identifications, wherein the preset queue is associated with the vehicle identification; place the video files and the associated time interval into the preset queue associated with the corresponding vehicle identification.

[0102] Specifically, a preset queue is set for all video files of a vehicle, and the preset queue may be a cache queue. By placing the video files and time intervals associated with the vehicle identification in the corresponding cache queue, the transmission efficiency of the video files may be improved.

[0103] As an optional implementation method, the Round-Robin alternating allocation method can be used to allocate pending files. First, the pending files that need to be allocated are placed in a circular queue. The system allocates a unit of fixed time length for each pending file, called a time slice. When the time slice of a pending file is used up, the system will pause it and immediately start executing the task of the next pending file. If a pending file is completed within its time slice, it can exit the queue; if it is not completed, it will wait in the queue for its next turn to continue execution. This process will be repeated continuously to form a loop until all pending files are served or a specific condition triggers a stop, thereby ensuring that each process has the opportunity to use the CPU, avoiding the "starvation" problem caused by some processes monopolizing the CPU for a long time.

[0104] As another optional implementation, a Fair allocation method may be used to allocate the video files to be processed. The files to be processed are allocated one by one according to the principle of equality, that is, for each sub-video processing server, the files to be processed are allocated in sequence according to the status of each sub-video processing server.

[0105] Specifically, by running multiple video processing servers alternately (video processing tasks can be processed in parallel using distribution methods such as Round-Robin alternating distribution and Fair distribution), the computational pressure of video synthesis is shared, the single-machine performance requirements and procurement costs of video processing servers are reduced, and elastic expansion of computing power is achieved.

[0106] In the technical solution provided in this embodiment, all associated video files and time intervals are obtained through the main video processing server, and all the associated video files and time intervals are saved as files to be processed, and then each of the files to be processed is placed in a preset queue according to the time interval, and the service status of the sub-video processing server is obtained. Finally, when the service status is in a preset state, the files to be processed in the preset queue are allocated to the sub-video processing server, thereby sharing the computational pressure of video synthesis, reducing the single-machine performance requirements and procurement costs of the video processing server, and realizing elastic expansion of computing power.

[0107] Since the system introduced in the embodiment of the present application is a system used to implement the method of the embodiment of the present application, based on the method introduced in the embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the system, so it is not repeated here. All systems used in the method of the embodiment of the present application belong to the scope of protection of this application.

[0108] The present application provides a surveillance video processing system, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the surveillance video synthesis method in the above-mentioned embodiment one.

[0109] Reference below Figure 6 , which shows a schematic diagram of the structure of a monitoring video processing system suitable for implementing the embodiment of the present application. The monitoring video processing system in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The surveillance video processing system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0110] like Figure 6As shown, the processing system of the monitoring video may include a processing device 1001 (such as a core processor, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the processing system of the monitoring video are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the processing system of the monitoring video to communicate with other devices wirelessly or by wire to exchange data. Although the processing system of the monitoring video with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0111] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0112] The monitoring video processing system provided by the present application adopts the monitoring video synthesis method in the above embodiment, which can solve the technical problem that the related solution has a large storage overhead for vehicle recorded videos. Compared with the prior art, the beneficial effects of the monitoring video processing system provided by the present application are the same as the beneficial effects of the monitoring video synthesis method provided by the above embodiment, and other technical features in the monitoring video processing system are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0113] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0115] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the surveillance video synthesis method in the above-mentioned embodiment.

[0116] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0117] The computer-readable storage medium may be included in the monitoring video processing system; or may exist independently without being assembled into the monitoring video processing system.

[0118] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the monitoring video processing system, the monitoring video processing system: obtains the time series of the target vehicle passing through each license plate recognition checkpoint, and determines the time interval according to the time series; according to the time interval, intercepts the video clip associated with the target vehicle from the video file collected by the monitoring equipment, and generates the full process video corresponding to the target vehicle according to the video clip and the time interval; and saves the full process video.

[0119] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0120] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0122] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned surveillance video synthesis method, and can solve the technical problem that the related solutions have large storage overhead for vehicle recorded videos. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the surveillance video synthesis method provided by the above-mentioned embodiment, and will not be repeated here.

[0123] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the above-mentioned surveillance video synthesis method when executed by a processor.

[0124] The computer program product provided by the present application can solve the technical problem that the storage overhead of the vehicle recorded video is large in the related solutions. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the synthesis method of the surveillance video provided by the above embodiment, which will not be repeated here.

[0125] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A surveillance video synthesis method, characterized in that: The invention is applied to a video processing server, the video processing server includes a main video processing server and a sub-video processing server, the video processing server is connected to a license plate recognition port and a monitoring device, wherein the license plate recognition port is set at a starting point and an ending point, and a first preset number of the license plate recognition ports are set on a path between the starting point and the ending point, the monitoring device is set between the license plate recognition port and an adjacent license plate recognition port, and a second preset number of the monitoring devices are set, and the synthesis method of the monitoring video includes the following steps: Obtaining a time sequence of the target vehicle passing through each of the license plate recognition checkpoints, and determining a time interval according to the time sequence; Determine a first license plate recognition checkpoint and a second license plate recognition checkpoint corresponding to the time interval; Determining the monitoring device between the first license plate recognition checkpoint and the second license plate recognition checkpoint; Obtaining video files collected by the monitoring device, wherein the main video processing server is responsible for aggregating video files of all time intervals and distributing and processing the aggregated video files; Determine the service status of the sub-video processing server, and when the service status is a preset status, send the video file and the time interval to the sub-video processing server, wherein the preset status is that the processing amount of the sub-video processing server is lower than its own threshold processing amount, and the sub-video processing server intercepts the video clip associated with the target vehicle from the video file collected by the monitoring device according to the time interval, and generates a full-process video corresponding to the target vehicle according to the video clip and the time interval; Controlling the sub-video processing server to send the whole process video to the storage server; Saving the video of the whole process; When the target vehicle passes through a first target license plate recognition checkpoint, determining an adjacent license plate recognition checkpoint corresponding to the first target license plate recognition checkpoint; If the adjacent license plate recognition checkpoint does not detect the target vehicle within a preset time period, it is determined that the target vehicle has abnormal behavior, wherein the abnormal behavior indicates that the target vehicle has been parked for a long time between the two checkpoints, or the target vehicle has performed other operations between the two checkpoints; When the second target license plate recognition checkpoint detects that the target vehicle passes by, it is determined that the target vehicle has abnormal behavior.

2. The method according to claim 1, characterized in that After the step of obtaining the time sequence of the target vehicle passing through the license plate recognition checkpoint and determining the time interval according to each time sequence, the method further includes: Receiving the license plate recognition result sent by the license plate recognition card port; When the target vehicle passes through the license plate recognition checkpoint, marking the path point of the target vehicle in the preset park model; Generate a motion path of the target vehicle according to the path points and the preset park model; The motion path is associated with the vehicle identification of the target vehicle and stored.

3. The method according to claim 1, characterized in that The method comprises: When the initial license plate recognition checkpoint detects the target vehicle, starting a timer and associating the timer with the vehicle identification of the target vehicle; When the time in the timer is equal to the preset time, detecting whether the license plate recognition checkpoint detects the target vehicle is finished; If not, the vehicle identification of the target vehicle is fed back to the client.

4. The method according to claim 1, characterized in that After the step of obtaining the video file collected by the monitoring device, the method further includes: Determining each of the video files and an associated time interval; Determine a vehicle identification of each vehicle, and create a preset queue according to each vehicle identification, wherein the preset queue is associated with the vehicle identification; The video file and the associated time interval are placed in a preset queue associated with the corresponding vehicle identification.

5. A monitoring video processing system, characterized in that: The monitoring video processing system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the monitoring video synthesis method as described in any one of claims 1 to 4.

Images