Video transmission method and system for law enforcement recorder based on intelligent police service cloud platform

Abstract

The invention relates to the technical field of video transmission of law enforcement recorders, in particular to a video transmission method and system for a law enforcement recorder based on an intelligent police service cloud platform. Comprising the following steps: S1, collecting video data shot by a law enforcement recorder, and detecting the network signal strength of connection between the law enforcement recorder and an intelligent police service cloud platform; s2, establishing a brake lamp recognition model, then dividing the vehicles into a to-be-detected vehicle and a driving vehicle in the video data according to the brake lamp recognition model, and performing license plate and portrait image extraction on the nearest to-be-detected vehicle; a transmission strategy is intelligently adjusted according to the network signal strength, so that effective transmission of video data can be ensured no matter in a high signal value area with good network signals or in medium and low signal value areas with weak signals, high-definition videos are transmitted in real time when the signals are high, compressed video clips are transmitted when the signals are medium, and the transmission efficiency is improved. And a mode of combining timed image extraction with video clip compression is adopted when the signal is low.

Description

Technical Field

[0001] The present invention relates to the technical field of law enforcement recorder video transmission, and in particular to a method and system for transmitting video for law enforcement recorders based on an intelligent police cloud platform. Background Art

[0002] As an important device in the law enforcement process, the law enforcement recorder plays a key role in recording on-site conditions, ensuring fair law enforcement, and collecting evidence. Its video transmission function is designed to transmit images and video data from the law enforcement scene to relevant platforms in real time or subsequently for storage, analysis, and subsequent processing.

[0003] At present, when law enforcement recorders transmit videos to the intelligent police cloud platform, they often lack flexible response strategies when faced with different network signal strengths. When the network signal is good, the video may be transmitted normally, but in areas with unstable or weak signals, such as remote areas, underground places or network congestion periods, video transmission interruptions, freezes or image quality degradation are prone to occur, which seriously affects the timely transmission and integrity of law enforcement information. Secondly, law enforcement personnel need to input the information of the vehicle to be detected into the intelligent police cloud platform, so as to obtain the complete information of the vehicle to be detected, which prolongs the detection efficiency of the vehicle and easily causes congestion on the road. Therefore, a video transmission method and system for law enforcement recorders based on the intelligent police cloud platform are proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a video transmission method and system for law enforcement recorders based on an intelligent police cloud platform to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, one of the purposes of the present invention is to provide a video transmission method for a law enforcement recorder based on an intelligent police cloud platform, comprising the following steps:

[0006] S1. Collect the video data captured by the law enforcement recorder and detect the network signal strength between the law enforcement recorder and the intelligent police cloud platform;

[0007] S2, establishing a brake light recognition model, and then dividing the vehicles in the video data into vehicles to be detected and moving vehicles according to the brake light recognition model, and extracting the license plate and portrait images of the nearest vehicle to be detected;

[0008] S3, when a portrait image is extracted, a detection start mark is performed in the video data according to the extracted time node, and an end time threshold is set at the same time, a detection end mark is performed according to the extracted new portrait image and the time threshold, and then video segments are segmented in the video data according to the time nodes of the detection start mark and the detection end mark;

[0009] S4, caching the video clips according to the network signal strength, compressing and packaging the video clips, and then allocating the priority transmission of the video clips and the license plate images and the portrait images;

[0010] S5. The intelligent police cloud platform receives the license plate image, portrait image and video clip, performs identity information recognition, and then feeds back the recognized identity information to the user corresponding to the law enforcement recorder according to the transmission source.

[0011] As a further improvement of the present technical solution, S1 establishes a network data transmission connection between the law enforcement recorder and the smart police cloud platform, and then the law enforcement recorder continuously provides the video data captured by the camera to the smart police cloud platform for collection.

[0012] As a further improvement of the technical solution, S1 divides the network signal strength into high, medium and low;

[0013] A high network signal strength means that the network speed can meet the requirements of real-time transmission of high-quality video data;

[0014] The network signal strength indicates that the network speed is sufficient for real-time transmission of low-quality video data, but not for high-quality video data.

[0015] Low network signal strength means that the network speed is not sufficient to transmit video data in real time.

[0016] As a further improvement of the technical solution, the steps of S2 are as follows:

[0017] S2.1. Collect vehicle data on the network, extract image data of the brake lights on the vehicle data, and then summarize the image data to establish a brake light recognition model;

[0018] S2.2. The video data captured by the law enforcement recorder is combined with the brake light recognition model to perform vehicle detection analysis. Vehicles are extracted from the video data separately, and then the extracted vehicles are identified by the brake light recognition model. When the brake light recognition model identifies that the brake lights of the vehicle are on, the vehicle is defined as a vehicle to be detected. Conversely, when the brake light recognition model identifies that the brake lights of the vehicle are not on, the vehicle is defined as a vehicle to be detected.

[0019] S2.3. Analyze the distance of the vehicle to be detected based on the real-time video data to determine the vehicle to be detected that is closest to the law enforcement recorder, and then identify the license plate and driver of the vehicle to be detected in the video data. When the license plate and driver of the vehicle to be detected are identified in the video data, extract the license plate image and the driver's portrait image.

[0020] As a further improvement of the technical solution, when S2.3 is performing image extraction, when there is no same segment that can simultaneously display the license plate and the driver, the license plate image and the driver's portrait image are extracted separately; when the license plate and the driver appear in the same segment, the segment is extracted as the image of the license plate and the driver;

[0021] At the same time, when the images of the license plate and the driver appearing in the same segment have been extracted, further extraction is stopped and the already extracted license plate image and driver's portrait image are overwritten.

[0022] As a further improvement of this technical solution, the steps of S3 are as follows:

[0023] S3.1, when a portrait image is extracted, a detection start mark is performed in the video data according to the extracted time node;

[0024] S3.2, set the end time threshold. When the detection start is marked in the video data, if the portrait image corresponding to the detection start mark does not appear in the video data, start calculation in combination with the end time threshold. When the end time threshold is exceeded, if the portrait image corresponding to the detection start mark still does not appear, the detection end mark is performed in the video data.

[0025] S3.3, when a new portrait image is extracted, the detection end is marked according to the extracted time node, and the new detection start is marked at the same time;

[0026] S3.4. When S3.2 and S3.3 perform detection end marking, segment the video data into video segments according to the time nodes of the detection start mark and the detection end mark to obtain a video segment exclusive to the portrait image.

[0027] As a further improvement of the technical solution, the step of S4 is as follows:

[0028] S4.1. Cache the video clips according to the network signal strength. When the network signal strength is high, the video clips are not saved. When the network signal strength is medium or low, the video clips are cached and compressed.

[0029] S4.2. Use the extra network space to send the cached video clips to the smart police cloud platform and delete them after sending;

[0030] S4.3. When the network signal strength is at a high signal value, the law enforcement recorder transmits the video clips in high quality to the smart police cloud platform in real time;

[0031] When the network signal strength is at a medium signal value, the law enforcement recorder transmits compressed and packaged video clips to the smart police cloud platform;

[0032] When the network signal strength is at a low signal value, the law enforcement recorder will extract the video clips at a high-definition timed image, and then transmit the extracted high-definition images in combination with the compressed and packaged video clips to the smart police cloud platform. The transmission priority of the high-definition images is higher than that of the compressed and packaged video clips.

[0033] As a further improvement of the technical solution, during the transmission process, S4 gives priority to transmitting the images of the license plate and the portrait extracted by S2, and then sorts the video clips and the high-quality images for transmission according to the signal strength.

[0034] The second object of the present invention is to provide a video transmission system for a law enforcement recorder based on an intelligent police cloud platform, including any one of the above-mentioned methods for transmitting video for a law enforcement recorder based on an intelligent police cloud platform, including a video acquisition unit, a video segmentation unit, and a feedback sending unit;

[0035] The video acquisition unit is used to collect video data captured by the law enforcement recorder and detect the network signal strength connecting the law enforcement recorder and the intelligent police cloud platform;

[0036] The video segmentation unit is used to establish a brake light recognition model, and then divide the vehicles into to-be-detected vehicles and moving vehicles in the video data according to the brake light recognition model, and simultaneously extract the images of the license plate and the portrait, and then perform detection start marking and detection end marking, thereby completing the video segmentation;

[0037] The feedback sending unit is used to allocate priority transmission according to the network signal strength, and then the intelligent police cloud platform feeds back the identified identity information based on the received data.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. A video transmission method and system for law enforcement recorders based on an intelligent police cloud platform, which intelligently adjusts the transmission strategy according to the network signal strength, can ensure the effective transmission of video data whether in a high signal value area with good network signals or in a medium or low signal value area with weak signals. When the signal is high, high-definition video is transmitted in real time, and compressed video clips are transmitted when the signal is medium. When the signal is low, timed image extraction combined with compressed video clips is used, and key images are transmitted first. Even if the network conditions are unstable, key information such as license plates and portrait images can be transmitted as quickly as possible, providing support for the command center's rapid decision-making, avoiding information delays caused by network problems, and thus improving the overall law enforcement response speed.

[0040] 2. A video transmission method and system for law enforcement recorders based on an intelligent police cloud platform, which utilizes excess network space to supplement the transmission of cached video clips, thereby avoiding the waste of network resources. At the same time, it dynamically adjusts the transmission content and priority according to the network status to ensure that when the network bandwidth is limited, important information such as high-definition license plates and portrait images are transmitted first, so that network resources are reasonably allocated and maximized, effectively avoiding network congestion, ensuring that key data at each law enforcement point can be transmitted in a timely manner, and improving the operating efficiency of the entire law enforcement system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is the overall flow chart of the present invention;

[0042] Figure 2 A flowchart of the present invention for establishing a brake light recognition model by summarizing image data;

[0043] Figure 3 A flowchart of setting the end time threshold of the present invention;

[0044] Figure 4 A flowchart of caching video clips according to network signal strength according to the present invention;

[0045] Figure 5 It is a structural schematic diagram of the video acquisition unit of the present invention.

[0046] The meaning of each number in the figure is:

[0047] 10. Video acquisition unit; 20. Video segment segmentation unit; 30. Feedback sending unit. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] like Figure 1-Figure 5 As shown, one of the purposes of the present invention is to provide a video transmission method for a law enforcement recorder based on an intelligent police cloud platform, comprising the following steps:

[0050] S1. Collect the video data captured by the law enforcement recorder and detect the network signal strength between the law enforcement recorder and the intelligent police cloud platform;

[0051] S1 establishes a network data transmission connection between the law enforcement recorder and the smart police cloud platform, and then the law enforcement recorder continuously provides the smart police cloud platform with the video data captured by the camera. The specific steps are as follows:

[0052] Video data collection: After the law enforcement recorder turns on the camera, the camera starts to continuously shoot video according to the preset parameters (such as resolution, frame rate, etc.), converts the light signal captured by the camera into a digital video signal, and performs preliminary processing, such as video encoding preprocessing (including color space conversion, denoising, etc.);

[0053] Video transmission: The law enforcement recorder encapsulates the encoded and compressed video data into a network data packet, which contains the video data, related metadata (such as timestamp, location information, device number, etc.) and the protocol header information required for network transmission. The data packet is sent to the smart police cloud platform through the established network connection (Wi-Fi or mobile network). The network transmission protocol used is usually a related protocol in the TCP / IP protocol stack, such as HTTP (Hypertext Transfer Protocol) or RTSP (Real-time Streaming Protocol). For video transmission with high real-time requirements, the RTSP protocol is used.

[0054] S1 divides the network signal strength into high, medium and low;

[0055] A high network signal strength means that the network speed can meet the requirements of real-time transmission of high-quality video data;

[0056] The camera captures video at the highest resolution (eg, 1920×1080 or higher) and the highest frame rate (eg, 30fps or higher) to obtain the clearest and smoothest video images.

[0057] The law enforcement recorder transmits the encoded high-definition video data to the smart police cloud platform through the network at a stable high rate, using real-time streaming protocols (such as RTSP) or HTTP-based dynamic adaptive streaming media technology (such as HLS or DASH) to ensure the real-time and continuity of video data.

[0058] The network signal strength indicates that the network speed is sufficient for real-time transmission of low-quality video data, but not for high-quality video data.

[0059] The law enforcement recorder automatically adjusts the camera's acquisition parameters, lowering the resolution (for example, to 1280×720) and frame rate (for example, to 15fps) to reduce the amount of video data.

[0060] The law enforcement camera transmits compressed and degraded video data at a lower rate. It also uses protocols suitable for real-time transmission, such as RTSP or HTTP streaming protocols, but allocates bandwidth reasonably according to current network conditions and video data volume.

[0061] Low network signal strength means that the network speed is not sufficient to transmit video data in real time;

[0062] The video data caching mechanism is enabled to temporarily store the video data that has been collected but not yet transmitted in a local cache area (eg, using a high-speed flash memory).

[0063] The law enforcement recorder has a built-in network signal monitoring module, which scans and obtains the signal strength index of the currently connected network in real time. This is achieved through communication interaction with the network base station or Wi-Fi access point, such as the power level of the received wireless signal, signal-to-noise ratio and other parameters.

[0064] The acquired signal strength values ​​are classified and judged according to the preset threshold range. Taking the signal strength RSSI (ReceivedSignalStrengthIndication) as an example, RSSI ≥ -60dBm can be set as high signal strength, -60dBm> RSSI ≥ -80dBm as medium signal strength, and RSSI < -80dBm as low signal strength. The actual threshold can be adjusted and optimized according to the specific network environment and device performance.

[0065] Once the network signal strength returns to medium or above levels, the law enforcement recorder will upload the cached video data to the cloud platform in a certain priority order.

[0066] S2, establishing a brake light recognition model, and then dividing the vehicles in the video data into vehicles to be detected and moving vehicles according to the brake light recognition model, and extracting the license plate and portrait images of the nearest vehicle to be detected;

[0067] The steps of S2 are as follows:

[0068] S2.1. Collect vehicle data on the network, extract image data of the brake lights on based on the vehicle data, and then summarize the image data to establish a brake light recognition model. The specific steps are as follows:

[0069] Vehicle data collection: Use traffic surveillance video data, vehicle driving record videos and other sources on the Internet to collect images and video data containing vehicles. These data cover different scenes (such as daytime, nighttime, sunny days, rainy days, etc.), different vehicle types and driving conditions;

[0070] Brake light image data extraction: For the collected vehicle video data, video frame extraction technology is used to extract video frame images at regular intervals (for example, one frame is extracted per second). Each frame of the image is analyzed using an image processing algorithm to detect the vehicle's position and the area of ​​the brake light. A color feature-based method can be used because brake lights usually have unique red color features. For example, the red color range is set to (150, 0, 0) to (255, 50, 50) in the RGB space. By traversing the image pixels, the area that meets the color range is screened out as a possible brake light area. The detected brake light area is further verified and confirmed, for example, by judging by shape features (brake lights are generally rectangular or approximately rectangular) and brightness features (the brightness is higher when the brake lights are on). If these features are met, the frame of the image is marked as an image with the brake lights on and stored in a special brake light image dataset.

[0071] Establishment of brake light recognition model: Annotate the extracted brake light image data set, mark the images with the brake lights on as "positive samples", extract effective features for model training based on the annotated image data, and then select the features that contribute most to brake light recognition through feature selection algorithms, such as principal component analysis (PCA) and mutual information, so as to reduce feature dimensions and improve model training efficiency and accuracy;

[0072] According to the characteristics of the task and the size of the data, select a suitable machine learning or deep learning model. Taking CNN as an example, input the labeled image data into the network for training. During the training process, the network parameters are continuously adjusted through the back propagation algorithm so that the model can learn the characteristic pattern of the brake light, thereby accurately classifying the on state of the brake light. Finally, use a part of the image data that has not participated in the training as a test set to evaluate the trained brake light recognition model. According to the evaluation results, analyze the shortcomings of the model, such as overfitting or underfitting. If there is overfitting, you can use methods such as increasing data enhancement (such as random rotation, scaling, cropping, etc.) and adding regularization terms (such as L1, L2 regularization) to optimize; if there is underfitting, you can try to increase the complexity of the model (such as increasing the number of network layers, increasing the number of neurons, etc.), adjust the learning rate, etc. Continuously optimize the model until satisfactory performance indicators are achieved.

[0073] S2.2. Combine the video data captured by the law enforcement recorder with the brake light recognition model to perform vehicle detection analysis. Extract the vehicles separately from the video data, and then identify the extracted vehicles through the brake light recognition model. When the brake light recognition model recognizes that the brake lights of the vehicle are on, the vehicle is defined as a vehicle to be detected. Conversely, when the brake light recognition model recognizes that the brake lights of the vehicle are not on, the vehicle is defined as a vehicle to be detected. The specific steps are as follows:

[0074] Video frame decomposition: Decompose the video captured by the law enforcement recorder into continuous image frames at a fixed frame rate (for example, 30 frames per second). This can be achieved through functions in the video processing library (such as OpenCV);

[0075] Vehicle detection: Use the target detection algorithm to detect vehicles in each frame. The formula is as follows:

[0076] B ij = ( x ij1 ,y ij1 ,x ij2 ,y ij2 )

[0077] Among them, j is the vehicle serial number detected in the current frame, i is the frame, B ij is the coordinate X of the upper left corner of the rectangular bounding box of vehicle j in frame i ij1 ,y ij1 and the lower right corner coordinate X ij2 ,y ij2 ;

[0078] Set the confidence threshold T (based on experience, such as 0.5) to filter out reliable vehicle detection results. ij ≥T, C ij A confidence score is calculated, and the detected vehicle is considered valid and extracted from the image;

[0079] Then, the extracted vehicle image is preprocessed, and the same feature extraction method as that used in the brake light recognition model training (such as the color features, texture features, etc. mentioned above) is used to extract features from the vehicle image to obtain a feature vector, which is then input into the trained brake light recognition model.

[0080] Assume that the brake light recognition model outputs the vehicle brake light on state probability as P ij ;

[0081] P ij > 0.5, vehicle j is defined as a “vehicle to be detected” in frame i, indicating that the brake lights are on;

[0082] P ij When ≤0.5, vehicle j is defined as a “non-detected vehicle” in frame i, indicating that the brake lights are not on.

[0083] S2.3. Analyze the distance of the vehicle to be detected based on the real-time video data to determine the vehicle to be detected that is closest to the law enforcement recorder, and then identify the license plate and driver of the vehicle to be detected in the video data. When the license plate and driver of the vehicle to be detected are identified in the video data, extract the license plate image and the driver's portrait image. The specific steps are as follows:

[0084] Target detection and tracking: Continuously detect vehicles in the video using a target detection algorithm. For each frame of the video image, obtain the detection frame information of the vehicle. At the same time, use a target tracking algorithm to track the detected vehicles and assign a unique identifier to each vehicle so that the same vehicle can be associated in consecutive frames.

[0085] Distance estimation: Assuming that the camera parameters of the law enforcement recorder are known, such as focal length f, pixel size p, etc., for the detected vehicle, measure its pixel height h in the image ij According to the principle of similar triangles, the distance from the vehicle to the law enforcement camera can be estimated. Assume that the actual height of the vehicle is H. For common vehicle types, their average height can be used as prior knowledge. For example, the average height of a small car is about 1.5 meters. The formula is as follows:

[0086] Solved

[0087] In each frame, traverse the distance values ​​d of all vehicles marked as to-be-detected vehicles (i.e. vehicles with brake lights on) ij , find the vehicle with the minimum distance and record it as the nearest vehicle to be detected;

[0088] License plate recognition: For the nearest vehicle to be detected, its license plate area is located in the video frame. Once the license plate area is detected, the license plate image is extracted.

[0089] Driver identification: Face recognition technology is used to identify the vehicle driver. When the driver's face is detected, the license plate image is extracted.

[0090] S2.3 When performing image extraction, when there is no same segment that can simultaneously display the license plate and the driver, the license plate image and the driver's portrait image are extracted separately; when the license plate and the driver appear in the same segment, the segment is extracted as the license plate and the driver's image;

[0091] At the same time, when the images of the license plate and the driver appearing in the same segment have been extracted, further extraction is stopped and the already extracted license plate image and driver's portrait image are overwritten.

[0092] S3, when a portrait image is extracted, a detection start mark is performed in the video data according to the extracted time node, and an end time threshold is set at the same time, a detection end mark is performed according to the extracted new portrait image and the time threshold, and then video segments are segmented in the video data according to the time nodes of the detection start mark and the detection end mark;

[0093] The steps for S3 are as follows:

[0094] S3.1, when a portrait image is extracted, a detection start mark is performed in the video data according to the extracted time node;

[0095] S3.2, set the end time threshold, which can be determined according to actual needs and scenarios, for example, it can be set to 60 seconds (indicates that if the corresponding portrait image does not appear again within 60 seconds after the start of the detection, the detection is considered to be over). When the detection start is marked in the video data, if the portrait image corresponding to the detection start mark does not appear in the video data, the end time threshold is combined to start the calculation. When the end time threshold is exceeded, the portrait image corresponding to the detection start mark still does not appear, that is, the detection end mark is performed in the video data;

[0096] S3.3, when a new portrait image is extracted, the detection end is marked according to the extracted time node, and the new detection start is marked at the same time;

[0097] S3.4. When S3.2 and S3.3 perform detection end marking, segment the video data into video segments according to the time nodes of the detection start mark and the detection end mark to obtain a video segment exclusive to the portrait image.

[0098] S4, caching the video clips according to the network signal strength, compressing and packaging the video clips, and then allocating the priority transmission of the video clips and the license plate images and the portrait images;

[0099] The steps of S4 are as follows:

[0100] S4.1. Cache the video clips according to the network signal strength. When the network signal strength is high, the video clips are not saved. When the network signal strength is medium or low, the video clips are cached and compressed.

[0101] S4.2. Use the extra network space to send the cached video clips to the smart police cloud platform and delete them after sending;

[0102] Evaluate the current network usage to determine whether there is excess network space available for video clip transmission. For example, if the current network bandwidth utilization is below a threshold of 70%, it is considered that there is excess network space;

[0103] Delete the cached video clips that have been supplemented and sent;

[0104] S4.3. When the network signal strength is at a high signal value, the law enforcement recorder transmits the video clips in high quality to the smart police cloud platform in real time;

[0105] When the network signal strength is at a medium signal value, the law enforcement recorder transmits compressed and packaged video clips to the smart police cloud platform;

[0106] When the network signal strength is at a low signal value, the law enforcement recorder will extract the video clips at a high-definition timed image, and then transmit the extracted high-definition images in combination with the compressed and packaged video clips to the smart police cloud platform. The transmission priority of the high-definition images is higher than that of the compressed and packaged video clips.

[0107] During the transmission process, S4 gives priority to transmitting the images of license plates and portraits extracted by S2, and then sorts the video clips and high-quality images for transmission according to the signal strength.

[0108] S4 establishes a transmission queue and puts the video clips, high-definition images, etc. to be transmitted into the queue in sequence according to the transmission priority. Whenever there is new video data to be transmitted, the queue order is adjusted according to the current network signal strength and priority rules.

[0109] S5. After receiving the license plate image, portrait image and video clip, the intelligent police cloud platform performs identity information recognition, and then feeds back the recognized identity information to the user corresponding to the law enforcement recorder according to the sending source. The specific steps are as follows:

[0110] Data reception: The smart police cloud platform is equipped with a dedicated data reception service, which monitors specific network ports and waits for license plate images, portrait images and video clips uploaded by law enforcement recorders;

[0111] Identity information recognition: The license plate recognition algorithm is used to process the received license plate image. Based on image processing technology and machine learning models, it can recognize the characters and numbers on the license plate, and compare the recognized license plate information with the vehicle management database to obtain relevant information about the vehicle, such as the owner's name, vehicle model, etc.

[0112] Use face recognition technology to analyze portrait images. By extracting the feature vector of the portrait and comparing it with a known face database, the identity information of the person can be determined;

[0113] Information feedback: The identified identity information is sorted out, including the owner information corresponding to the license plate and the person identity information corresponding to the portrait, and this information is associated with the identification of the sending source (law enforcement recorder) so as to accurately feedback to the corresponding user so that law enforcement personnel can understand the relevant situation in a timely manner.

[0114] The second object of the present invention is to provide a video transmission system for a law enforcement recorder based on an intelligent police cloud platform, including any one of the above-mentioned methods for transmitting video for a law enforcement recorder based on an intelligent police cloud platform, including a video acquisition unit 10, a video segmentation unit 20, and a feedback sending unit 30;

[0115] The video acquisition unit 10 is used to collect video data captured by the law enforcement recorder and detect the network signal strength connecting the law enforcement recorder and the intelligent police cloud platform;

[0116] The video segmentation unit 20 is used to establish a brake light recognition model, and then divide the vehicles into vehicles to be detected and moving vehicles in the video data according to the brake light recognition model, and extract the images of license plates and portraits at the same time, and then perform detection start marking and detection end marking, thereby completing video segmentation;

[0117] The feedback sending unit 30 is used to allocate priority transmission according to the network signal strength, and then the intelligent police cloud platform feeds back the identified identity information based on the received data.

[0118] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A video transmission method for law enforcement recorders based on an intelligent police cloud platform, characterized in that: The steps include: S1. Collect the video data captured by the law enforcement recorder and detect the network signal strength between the law enforcement recorder and the intelligent police cloud platform; S2, establishing a brake light recognition model, and then dividing the vehicles in the video data into vehicles to be detected and moving vehicles according to the brake light recognition model, and extracting the license plate and portrait images of the nearest vehicle to be detected; S3, when a portrait image is extracted, a detection start mark is performed in the video data according to the extracted time node, and an end time threshold is set at the same time, a detection end mark is performed according to the extracted new portrait image and the time threshold, and then video segments are segmented in the video data according to the time nodes of the detection start mark and the detection end mark; S4, caching the video clips according to the network signal strength, compressing and packaging the video clips, and then allocating the priority transmission of the video clips and the license plate images and the portrait images; S5. The intelligent police cloud platform receives the license plate image, portrait image and video clip, performs identity information recognition, and then feeds back the recognized identity information to the user corresponding to the law enforcement recorder according to the transmission source.

2. According to claim 1, a video transmission method for a law enforcement recorder based on an intelligent police cloud platform is characterized in that: The S1 establishes a network data transmission connection between the law enforcement recorder and the smart police cloud platform, and then the law enforcement recorder continuously provides the smart police cloud platform with the video data captured by the camera.

3. According to claim 1, a video transmission method for a law enforcement recorder based on an intelligent police cloud platform is characterized in that: The S1 classifies the network signal strength into high, medium and low; A high network signal strength means that the network speed can meet the requirements of real-time transmission of high-quality video data; The network signal strength indicates that the network speed is sufficient for real-time transmission of low-quality video data, but not for high-quality video data. Low network signal strength means that the network speed is not sufficient to transmit video data in real time.

4. According to claim 1, a video transmission method for a law enforcement recorder based on an intelligent police cloud platform is characterized in that: The steps of S2 are as follows: S2.

1. Collect vehicle data on the network, extract image data of the brake lights on the vehicle data, and then summarize the image data to establish a brake light recognition model; S2.

2. The video data captured by the law enforcement recorder is combined with the brake light recognition model to perform vehicle detection analysis. Vehicles are extracted from the video data separately, and then the extracted vehicles are identified by the brake light recognition model. When the brake light recognition model identifies that the brake lights of the vehicle are on, the vehicle is defined as a vehicle to be detected. Conversely, when the brake light recognition model identifies that the brake lights of the vehicle are not on, the vehicle is defined as a vehicle to be detected. S2.

3. Analyze the distance of the vehicle to be detected based on the real-time video data to determine the vehicle to be detected that is closest to the law enforcement recorder, and then identify the license plate and driver of the vehicle to be detected in the video data. When the license plate and driver of the vehicle to be detected are identified in the video data, extract the license plate image and the driver's portrait image.

5. According to claim 4, a video transmission method for a law enforcement recorder based on an intelligent police cloud platform is characterized in that: When performing image extraction, S2.3 extracts the license plate image and the driver's portrait image separately when there is no same segment that can simultaneously display the license plate and the driver; when the license plate and the driver appear in the same segment, the segment is extracted as the image of the license plate and the driver; At the same time, when the images of the license plate and the driver appearing in the same segment have been extracted, further extraction is stopped and the already extracted license plate image and driver's portrait image are overwritten.

6. The video transmission method for a law enforcement recorder based on an intelligent police cloud platform according to claim 1 is characterized in that: The steps of S3 are as follows: S3.1, when a portrait image is extracted, a detection start mark is performed in the video data according to the extracted time node; S3.2, set the end time threshold. When the detection start is marked in the video data, if the portrait image corresponding to the detection start mark does not appear in the video data, start calculation in combination with the end time threshold. When the end time threshold is exceeded, if the portrait image corresponding to the detection start mark still does not appear, the detection end mark is performed in the video data. S3.3, when a new portrait image is extracted, the detection end is marked according to the extracted time node, and the new detection start is marked at the same time; S3.

4. When S3.2 and S3.3 perform detection end marking, segment the video data into video segments according to the time nodes of the detection start mark and the detection end mark to obtain a video segment exclusive to the portrait image.

7. The video transmission method for a law enforcement recorder based on an intelligent police cloud platform according to claim 1 is characterized in that: The steps of S4 are as follows: S4.

1. Cache the video clips according to the network signal strength. When the network signal strength is high, the video clips are not saved. When the network signal strength is medium or low, the video clips are cached and compressed. S4.

2. Use the extra network space to send the cached video clips to the smart police cloud platform and delete them after sending; S4.

3. When the network signal strength is at a high signal value, the law enforcement recorder transmits the video clips in high quality to the intelligent police cloud platform in real time; When the network signal strength is at a medium signal value, the law enforcement recorder transmits compressed and packaged video clips to the smart police cloud platform; When the network signal strength is at a low signal value, the law enforcement recorder will extract the video clips at a high-definition timed image, and then transmit the extracted high-definition images in combination with the compressed and packaged video clips to the smart police cloud platform. The transmission priority of the high-definition images is higher than that of the compressed and packaged video clips.

8. The video transmission method for a law enforcement recorder based on an intelligent police cloud platform according to claim 1 is characterized in that: During the transmission process, S4 gives priority to transmitting the images of the license plate and the portrait extracted by S2, and then arranges the transmission order of the video clips and the high-quality images according to the signal strength.

9. A video transmission system for a law enforcement recorder based on an intelligent police cloud platform is used to implement the video transmission system for a law enforcement recorder based on an intelligent police cloud platform, comprising a video transmission method for a law enforcement recorder based on an intelligent police cloud platform as described in any one of claims 1 to 8, characterized in that: It comprises a video acquisition unit (10), a video segmentation unit (20) and a feedback sending unit (30); The video acquisition unit (10) is used to collect video data captured by the law enforcement recorder and detect the network signal strength between the law enforcement recorder and the intelligent police cloud platform; The video segmentation unit (20) is used to establish a brake light recognition model, and then divide vehicles into to-be-detected vehicles and running vehicles in the video data according to the brake light recognition model, and simultaneously extract images of license plates and portraits, and then perform detection start marking and detection end marking, thereby completing video segmentation; The feedback sending unit (30) is used to perform priority transmission allocation according to the network signal strength, and then the intelligent police cloud platform feeds back the identified identity information based on the received data.

Images