A camera video processing method, device and medium

Abstract

The application relates to the technical field of camera video processing, in particular to a camera video processing method, device and medium. The method comprises the following steps: acquiring the state of a monitoring area corresponding to each camera in a target camera set in a target time period; the state of the monitoring area corresponding to any camera in the target time period is obtained based on preset type data of the monitoring area corresponding to the camera in the target time period, and the preset type data does not include the video of the camera; if the state of the monitoring area corresponding to a certain camera in the target time period is abnormal, a preset video processor is used to process the video collected by the camera in the target time period; and if the state of the monitoring area corresponding to a certain camera in the target time period is normal, the preset video processor is not used to process the video collected by the camera in the target time period. The application can process the video in a targeted manner, reduce the waste of computing power and reduce the video detection cost.

Description

Technical Field

[0001] This invention relates to the field of camera video processing technology, and in particular to a method, device and medium for processing camera video. Background Technology

[0002] Highways are equipped with numerous cameras that capture live footage, generating a vast amount of video. Current technology either uploads all this video indiscriminately to the cloud for processing, or it equips each camera with a video processor to handle its corresponding video in real time. However, since only a few cameras on highways typically monitor areas experiencing anomalies for short periods, and video processing often requires significant computing power and is costly, this indiscriminate processing of all video from all cameras across all time periods results in substantial wasted computing power and high video processing costs. Summary of the Invention

[0003] The purpose of this invention is to provide a method, device, and medium for processing camera video, so as to process the video in a targeted manner, reduce the waste of computing power, and lower the video processing cost.

[0004] According to a first aspect of the present invention, a method for processing camera video is provided, the method comprising the following steps: The status of the monitoring area corresponding to each camera in the target camera set during the target time period is obtained; the status of the monitoring area corresponding to any camera during the target time period is obtained based on the preset type data of the monitoring area corresponding to that camera during the target time period, wherein the preset type data does not include the video of the camera; the status of the monitoring area corresponding to any camera during the target time period is abnormal or normal.

[0005] If the monitoring area corresponding to a certain camera is in an abnormal state during the target time period, the video captured by that camera during the target time period is processed using a preset video processor; if the monitoring area corresponding to a certain camera is in a normal state during the target time period, the video captured by that camera during the target time period is not processed using the preset video processor; the preset video processor is a shared video processor for cameras in the target camera set, and the preset video processor is a cloud video processor or an edge video processor; the edge video processor is set on the side of some cameras in the target camera set.

[0006] Furthermore, obtaining the state of the monitoring area corresponding to each camera in the target camera set during the target time period includes: Obtain an initial set of vehicles that pass through the monitoring area corresponding to a specified camera within a target time period; the specified camera is any camera in the target camera set.

[0007] Get the number of vehicles included in the initial vehicle set.

[0008] The system obtains the specified speed of vehicles in the target vehicle set as they pass through the monitoring area corresponding to the specified camera, the first speed as they pass through the monitoring area corresponding to the first camera, and the second speed as they pass through the monitoring area corresponding to the second camera. The first camera is a camera adjacent to the specified camera and located upstream of the specified camera's driving direction, and the second camera is a camera adjacent to the specified camera and located downstream of the specified camera's driving direction. The target vehicle set is obtained by filtering the initial vehicle set, and the filtering conditions include passing through the monitoring area corresponding to the first camera and passing through the monitoring area corresponding to the second camera.

[0009] The state of the monitoring area corresponding to the specified camera during the target time period is obtained based on the number of vehicles, the specified speed, the first speed, and the second speed.

[0010] Furthermore, obtaining the state of the monitoring area corresponding to the designated camera during the target time period based on the number of vehicles, the designated speed, the first speed, and the second speed includes: The speed difference of a specified vehicle is obtained based on a specified speed, a first speed, and a second speed; the specified vehicle is any vehicle in the target vehicle set.

[0011] The mean and variance of the speed differences of vehicles in the target vehicle set are obtained based on the weight and speed difference of each vehicle in the target vehicle set.

[0012] The state of the monitoring area corresponding to the specified camera during the target time period is obtained based on the mean speed difference, the preset speed difference threshold, the speed difference variance, and the preset difference variance threshold; the speed difference threshold is positively correlated with the number of vehicles, and the speed difference variance is positively correlated with the number of vehicles.

[0013] Furthermore, obtaining the speed difference of the specified vehicle based on the specified speed, the first speed, and the second speed includes: The first speed of the designated vehicle is corrected based on the speed limit of the monitoring area corresponding to the first camera and the speed limit of the monitoring area corresponding to the designated camera, so as to obtain the third speed of the designated vehicle.

[0014] The second speed of the designated vehicle is corrected based on the upper speed limit of the monitoring area corresponding to the second camera and the upper speed limit of the monitoring area corresponding to the designated camera to obtain the fourth speed of the designated vehicle.

[0015] Get the average speed of the third speed and the fourth speed of the specified vehicle.

[0016] The absolute value of the difference between the average speed and the specified speed is determined as the speed difference of the specified vehicle.

[0017] Furthermore, obtaining the state of the monitoring area corresponding to the specified camera during the target time period based on the mean speed difference, the preset speed difference threshold, the speed difference variance, and the preset difference variance threshold includes: If the mean of the speed difference is greater than or equal to a preset speed difference threshold, or the variance of the speed difference is greater than or equal to a preset speed variance threshold, or the mean of the speed difference is greater than or equal to a preset speed difference threshold and the variance of the speed difference is greater than or equal to a preset speed variance threshold, then the monitoring area corresponding to the specified camera is determined to be in an abnormal state during the target time period.

[0018] Furthermore, the weight of any vehicle in the target vehicle set is negatively correlated with the time difference corresponding to that vehicle, which is the difference between the time it takes for the vehicle to pass through the monitoring area corresponding to the designated camera and the center time of the target time period.

[0019] Furthermore, the method also includes: if the result of processing the video of the target time period captured by the camera using a preset video processor is that there are no abnormalities, then the preset video processor is used to process the video of the adjacent time period of the target time period captured by the camera or the video of the target time period captured by the adjacent camera.

[0020] Furthermore, processing the video of the target time period captured by the camera using a preset video processor includes: when the preset video processor is a cloud video processor, uploading the video of the target time period captured by the camera to the cloud video processor for processing; when the preset video processor is an edge video processor, calling the edge video processor to process the video of the target time period captured by the camera.

[0021] According to a second aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described camera video processing method.

[0022] According to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described camera video processing method.

[0023] Compared with the prior art, the present invention has at least the following beneficial effects: This invention acquires the status of the monitoring area corresponding to each camera in the target camera set during a target time period. Only when the status of the monitoring area corresponding to a certain camera is abnormal during the target time period is a preset video processor used to process the video of the target time period collected by that camera. The status is obtained based on other types of data besides video (such as data with low processing cost obtained by sensors). Therefore, it is possible to predict whether there are anomalies in the video before analyzing the video. It can achieve targeted processing of only a portion of the video (corresponding to a higher probability of anomalies). Compared with the existing technology that processes all videos from all cameras indiscriminately, this invention can reduce the computing power and cost of video processing.

[0024] Furthermore, the preset video processor used in this invention is a shared video processor for the cameras in the target camera set. The preset video processor is either a cloud video processor or an edge video processor set only on some camera sides. Based on this, it is not necessary to set an edge video processor for each camera side in the target camera set. Compared with the prior art, which sets an edge video processor for each camera side, this invention can be seen to reduce the cost of setting an edge video processor. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a camera video processing method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of the steps for obtaining the state of the monitoring area corresponding to each camera in the target camera set during a target time period, as provided in Embodiment 1 of the present invention. Figure 3 This is a flowchart of the steps for obtaining the state of the monitoring area corresponding to a specified camera during a target time period, as provided in Embodiment 1 of the present invention. Figure 4 This is a flowchart illustrating the steps for obtaining the speed difference of a specified vehicle according to Embodiment 1 of the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Example 1: According to this embodiment, as Figure 1 As shown, a method for processing camera video is provided, the method including the following steps: S100, obtain the status of the monitoring area corresponding to each camera in the target camera set during the target time period; the status of the monitoring area corresponding to any camera during the target time period is obtained based on the preset type data of the monitoring area corresponding to that camera during the target time period, wherein the preset type data does not include the video of the camera; the status of the monitoring area corresponding to any camera during the target time period is abnormal or normal.

[0029] In this embodiment, the target camera set is a set of cameras sharing a preset video processor; as a specific implementation, the target camera set is a set of cameras on a high-speed route. In this embodiment, the target camera set includes at least two cameras.

[0030] In this embodiment, the target time period is any preset time period, and the duration of the target time period can be set according to needs, such as 1 minute or 10 minutes.

[0031] In this embodiment, considering the high cost of video processing, the aim is to use other lower-cost methods to first determine the status of the monitoring area corresponding to each camera in the target camera set during the target time period. Specifically, the determination is made using preset type data instead of camera video. That is, the preset type data does not include camera video. Optionally, the preset type data includes data obtained through radar, lidar, or RFID (Radio Frequency Identification) systems, such as vehicle speed or vehicle identity information.

[0032] As a specific implementation method, obtaining the state of the monitoring area corresponding to each camera in the target camera set during the target time period includes, for example: Figure 2 As shown: S110, Obtain the initial set of vehicles that pass through the monitoring area corresponding to the specified camera within the target time period; the specified camera is any camera in the target camera set.

[0033] In this embodiment, the initial vehicle set is also known as the vehicle set. The "initial" in the initial vehicle set is only used to distinguish the target in the target vehicle set. The initial vehicle set is the vehicle set before filtering, and the target vehicle set is the vehicle set after filtering.

[0034] Those skilled in the art will understand that, besides analyzing video captured by cameras, there are many existing methods to obtain an initial set of vehicles passing through the monitoring area corresponding to a designated camera within a target time period. For example, each monitoring area corresponding to a camera in the target camera set is equipped with a radar module and RFID. When a vehicle passes through the monitoring area of ​​a designated camera, an RFID reader reads the vehicle tag ID, recording the vehicle ID and its corresponding timestamp; the radar module records the vehicle's speed and its corresponding timestamp, and then binds the speed to the vehicle ID using the timestamp (binding the speed with the closest timestamp to the vehicle ID). Based on this, an initial set of vehicles passing through the monitoring area corresponding to the designated camera within the target time period can be obtained, as well as the vehicle IDs and speeds within the initial set. Therefore, vehicle identification can be quickly achieved based on RFID, and vehicle speed can be quickly obtained based on radar, eliminating the need to analyze video captured by cameras. This allows for low-cost acquisition of vehicle samples, providing a data foundation for subsequent analysis.

[0035] S120, obtain the number of vehicles included in the initial vehicle set.

[0036] As a specific implementation, the vehicle IDs recorded in S110 are deduplicated, and the number of deduplicated vehicle IDs is determined as the number of vehicles included in the initial vehicle set.

[0037] In this embodiment, the number of vehicles can reflect the traffic density of the monitoring area and can help determine the status.

[0038] S130, obtain the specified speed of vehicles in the target vehicle set passing through the monitoring area corresponding to the specified camera, the first speed passing through the monitoring area corresponding to the first camera, and the second speed passing through the monitoring area corresponding to the second camera; the first camera is a camera adjacent to the specified camera and located upstream of the specified camera's driving direction, and the second camera is a camera adjacent to the specified camera and located downstream of the specified camera's driving direction; the target vehicle set is obtained by filtering the initial vehicle set, and the filtering conditions include passing through the monitoring area corresponding to the first camera and passing through the monitoring area corresponding to the second camera.

[0039] As a specific implementation, a target vehicle set can be obtained by filtering vehicles from the initial vehicle set that pass through the monitoring area corresponding to the first camera and those that pass through the monitoring area corresponding to the second camera (by matching vehicle IDs). Specifically, it can be determined whether a vehicle in the initial vehicle set has passed through the monitoring area corresponding to the first camera by comparing the vehicle IDs appearing in the monitoring area corresponding to the first camera within the candidate time period with the vehicle IDs in the initial vehicle set. The candidate time period is a time period derived from the target time. For example, if the target time period is T1 to T2 of the current day, the candidate time period is T'1 to T'2. T'1 is obtained by subtracting t1 from T1, and T'2 is obtained by subtracting t2 from T2. t1 is a preset first duration, and t2 is a preset second duration. T1 is earlier than T2, and T'1 is earlier than T'2. Optionally, t1 and t2 are empirical values, or t1 = k1 × D / V. min t2=k2×D / V max Where D is the distance between the first camera and the designated camera head, and V min and V max The system defines the lower and upper speed limits for the route between the first camera and the designated camera. k1 and k2 are preset magnification and reduction coefficients, respectively, where k1 > 1 and k2 < 1. Optionally, k1 and k2 can be empirical values, such as k1 = 2 and k2 = 0.8. Therefore, this candidate time period can balance the efficiency and accuracy of vehicle matching.

[0040] In this embodiment, the method for determining whether a vehicle in the initial vehicle set has passed through the monitoring area corresponding to the second camera is similar to the method for determining whether a vehicle has passed through the monitoring area corresponding to the second camera, and will not be described again here.

[0041] S140: Obtain the status of the monitoring area corresponding to the specified camera during the target time period based on the number of vehicles, the specified speed, the first speed, and the second speed.

[0042] In this embodiment, the monitoring area corresponding to the first camera, the monitoring area corresponding to the designated camera, and the monitoring area corresponding to the second camera are the areas that vehicles in the target set pass through sequentially. Based on the first vehicle speed when passing through the monitoring area corresponding to the first camera and the second vehicle speed when passing through the monitoring area corresponding to the second camera, it can be determined whether the speed of the vehicle passing through the monitoring area corresponding to the designated camera is abnormal. As a specific implementation, S140 includes, for example... Figure 3 As shown: S141, obtain the speed difference of the specified vehicle based on the specified speed, first speed and second speed of the specified vehicle; the specified vehicle is any vehicle in the target vehicle set.

[0043] In this embodiment, the difference between the vehicle's specified speed when passing through the monitoring area corresponding to the specified camera and the vehicle's first speed when passing through the monitoring area corresponding to the first camera and the second speed when passing through the monitoring area corresponding to the second camera can determine whether the vehicle's speed when passing through the monitoring area corresponding to the specified camera is abnormal. As a specific implementation, obtaining the speed difference of the specified vehicle based on the specified speed, the first speed, and the second speed includes, for example... Figure 4 As shown: S1411, the first speed of the designated vehicle is corrected based on the upper speed limit of the monitoring area corresponding to the first camera and the upper speed limit of the monitoring area corresponding to the designated camera to obtain the third speed of the designated vehicle.

[0044] In one specific implementation, the third speed of the vehicle is designated as V3, where V3 = V1 × (1 + b × (L2 - L1)), and V1 is the first speed of the vehicle, L2 is the upper speed limit of the monitoring area corresponding to the designated camera, L1 is the upper speed limit of the monitoring area corresponding to the first camera, and b is the influence coefficient of the preset upper speed limit on the actual speed of the vehicle, where b > 0. Optionally, b is an empirical value, for example, b = 0.2.

[0045] In this embodiment, correcting the first speed of the designated vehicle can reduce the speed difference between the two areas caused by the speed limit difference between the monitoring area corresponding to the first camera and the monitoring area corresponding to the designated camera.

[0046] S1412, the second speed of the designated vehicle is corrected based on the upper speed limit of the monitoring area corresponding to the second camera and the upper speed limit of the monitoring area corresponding to the designated camera to obtain the fourth speed of the designated vehicle.

[0047] In this embodiment, the upper speed limit of the monitoring area corresponding to the second camera and the upper speed limit of the monitoring area corresponding to the designated camera can respectively reflect the driving difficulty of the monitoring area corresponding to the second camera and the driving difficulty of the monitoring area corresponding to the designated camera. As a specific implementation, the third speed of the designated vehicle is V4, V4=V2×(1+b×(L2-L3)), where V2 is the second speed of the designated vehicle and L3 is the upper speed limit of the monitoring area corresponding to the second camera.

[0048] In this embodiment, correcting the second speed of the designated vehicle can reduce the speed difference between the two areas caused by the speed limit difference between the monitoring area corresponding to the second camera and the monitoring area corresponding to the designated camera.

[0049] S1413, obtain the average speed of the third and fourth speeds of the specified vehicle.

[0050] S1414, the absolute value of the difference between the average speed and the specified speed is determined as the speed difference of the specified vehicle.

[0051] In this embodiment, the average speed of the third and fourth speeds of the specified vehicle is used as the estimated speed of the specified vehicle when there are no abnormalities in the monitoring area corresponding to the specified camera. The absolute value of the difference between the average speed and the specified speed is determined as the speed difference of the specified vehicle. This speed difference can be used to characterize the magnitude of the difference between the estimated speed and the actual speed.

[0052] Based on S1411-S1414, the speed difference of each vehicle in the target vehicle set can be obtained.

[0053] S142, obtain the mean and variance of the speed difference of the vehicles in the target vehicle set based on the weight and speed difference of each vehicle in the target vehicle set.

[0054] In one specific implementation, each vehicle in the target vehicle set has an equal weight. The mean speed difference of the vehicles in the target vehicle set is the ratio of the sum of the speed differences of the vehicles in the target vehicle set to the number of vehicles in the target vehicle set. The variance of the speed difference is the square of the difference between the speed difference of each vehicle in the target vehicle set and the mean, divided by the number of vehicles in the target vehicle set.

[0055] In one specific implementation, the closer the time of a vehicle passing through the monitoring area corresponding to a designated camera is to the midpoint of the target time period, the more representative the speed anomaly of that monitoring area is to the overall state of the monitoring area during the target time period; conversely, the further the time of a vehicle passing through the monitoring area corresponding to a designated camera is from the midpoint of the target time period, the more likely its speed anomaly is to be influenced by transitional states or accidental factors. That is, the weight of any vehicle in the target vehicle set is negatively correlated with its corresponding time difference, which is the difference between the time the vehicle passes through the monitoring area corresponding to the designated camera and the midpoint of the target time period. In one specific implementation, the mean speed difference of the vehicles is μ, where μ = (∑ n j=1 w j ×f j ) / ∑ n j=1 w j f j Let w be the speed difference of the j-th vehicle in the target vehicle set. j Let be the weight of the j-th vehicle in the target vehicle set, where j ranges from 1 to n, and n is the number of vehicles in the target vehicle set. The variance of the vehicle speed difference is (∑ n j=1 w j ×(f j -μ) 2) / ∑ n j=1 w j As a specific implementation method, w j =1 / (1+a×|x j -x0|), x j Let x0 be the time when the j-th vehicle in the target vehicle set passes through the monitoring area corresponding to the designated camera, x0 be the midpoint of the target time period, and 'a' be a preset time influence coefficient (a>0, optional, or an empirical value, e.g., a=0.2). Based on the above formula, vehicles whose passing time through the monitoring area corresponding to the designated camera is closer to the midpoint of the target time period have a higher weight. This reduces the impact of occasional fluctuations at the beginning and end of the time period on the overall judgment, making the abnormal speed differences of vehicles whose passing time through the monitoring area corresponding to the designated camera is closer to the midpoint of the target time period have a greater impact on the overall judgment, thus improving the accuracy of subsequent judgments.

[0056] S143, obtain the state of the monitoring area corresponding to the specified camera in the target time period based on the mean speed difference, the preset speed difference threshold, the speed difference variance, and the preset difference variance threshold; the speed difference threshold is positively correlated with the number of vehicles, and the difference variance threshold is positively correlated with the number of vehicles.

[0057] As a specific implementation, S143 includes: if the mean speed difference is greater than or equal to a preset speed difference threshold, or the variance of the speed difference is greater than or equal to a preset speed variance threshold, or the mean speed difference is greater than or equal to a preset speed difference threshold and the variance of the speed difference is greater than or equal to a preset speed variance threshold, then the monitoring area corresponding to the specified camera is determined to be abnormal in the target time period.

[0058] In this embodiment, the preset speed difference threshold and the preset speed variance threshold are affected by the number of vehicles in the initial vehicle set. Specifically, the more vehicles in the initial vehicle set, the greater the vehicle density, and the greater the speed fluctuation of vehicles may be under normal conditions. As a specific implementation, the speed difference threshold is y, y = y0 + p1 × q, and the speed variance threshold is z, z = z0 + p2 × q, where y0 is the preset speed difference baseline value, p1 is the preset influence coefficient of vehicle density on the speed difference threshold (p1 > 0), z0 is the preset speed variance baseline value, p2 is the influence coefficient of vehicle density on the speed variance threshold (p2 > 0), and q is the number of vehicles in the initial vehicle set. Therefore, this embodiment can adaptively adjust the thresholds according to vehicle density, improving the robustness of state judgment and reducing misjudgments.

[0059] As a specific implementation, if the average speed difference is less than a preset speed difference threshold and the variance of the speed difference is less than a preset speed variance threshold, then the monitoring area corresponding to the designated camera is determined to be in a normal state during the target time period. Alternatively, if the average speed difference is less than a preset speed difference threshold and the variance of the speed difference is less than a preset speed variance threshold, then the state of the monitoring area corresponding to the designated camera during the target time period is further determined using other methods. It should be understood that these other methods are different from those described in S110-S140 above. For example, these other methods include: determining whether abnormal information about the monitoring area corresponding to the designated camera reported by the vehicle driver is received; if received, then the state of the monitoring area corresponding to the designated camera during the target time period is determined to be abnormal. If not received, then the state of the monitoring area corresponding to the designated camera during the target time period is determined to be normal, or the state of the monitoring area corresponding to the designated camera during the target time period is further determined.

[0060] S200: If the monitoring area corresponding to a certain camera is in an abnormal state during the target time period, then a preset video processor is used to process the video of the target time period captured by that camera; if the monitoring area corresponding to a certain camera is in a normal state during the target time period, then the preset video processor is not used to process the video of the target time period captured by that camera; the preset video processor is a shared video processor for cameras in the target camera set, and the preset video processor is a cloud video processor or an edge video processor; the edge video processor is set on the side of some cameras in the target camera set.

[0061] As a specific implementation, processing the video of the target time period captured by the camera using a preset video processor includes: when the preset video processor is a cloud video processor, uploading the video of the target time period captured by the camera to the cloud video processor for processing; when the preset video processor is an edge video processor, calling the edge video processor to process the video of the target time period captured by the camera.

[0062] As a specific implementation, the method further includes: if the result of processing the video of the target time period captured by the camera using a preset video processor is that there are no abnormalities, then processing the video of the candidate time period captured by the adjacent camera using the preset video processor. The process for determining the candidate time period is the same as the process for determining T'1 and T'2 described above, and will not be repeated here. "No abnormalities" (i.e., normal) means that no accidents or heavy traffic causing abnormal vehicle speeds are detected. Based on this, this embodiment can solve the problem of misjudging the state of the monitoring area corresponding to a specified camera when the state of the monitoring area corresponding to the first or second camera is abnormal.

[0063] This embodiment obtains the status of the monitoring area corresponding to each camera in the target camera set during the target time period. Only when the status of the monitoring area corresponding to a certain camera is abnormal during the target time period is the video of the target time period collected by the camera processed by the preset video processor. The status is obtained based on other types of data besides video (such as data with low processing cost obtained by sensors). Therefore, it is possible to predict whether there is anomaly in the video before analyzing the video. It can achieve targeted processing of only a part of the video (corresponding to a higher probability of anomaly). Compared with the existing technology that processes all videos of all cameras indiscriminately, this embodiment can reduce the computing power of video processing and reduce the cost of video processing.

[0064] Moreover, the preset video processor used in this embodiment is a shared video processor for the cameras in the target camera set. The preset video processor is a cloud video processor or an edge video processor set only on some camera sides. Based on this, there is no need to set an edge video processor for each camera side in the target camera set. Compared with the prior art, which sets an edge video processor for each camera side, this embodiment can be seen to reduce the cost of setting an edge video processor.

[0065] Example 2: This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it performs the following steps: The status of the monitoring area corresponding to each camera in the target camera set during the target time period is obtained; the status of the monitoring area corresponding to any camera during the target time period is obtained based on the preset type data of the monitoring area corresponding to that camera during the target time period, wherein the preset type data does not include the video of the camera; the status of the monitoring area corresponding to any camera during the target time period is abnormal or normal.

[0066] If the monitoring area corresponding to a certain camera is in an abnormal state during the target time period, the video captured by that camera during the target time period is processed using a preset video processor; if the monitoring area corresponding to a certain camera is in a normal state during the target time period, the video captured by that camera during the target time period is not processed using the preset video processor; the preset video processor is a shared video processor for cameras in the target camera set, and the preset video processor is a cloud video processor or an edge video processor; the edge video processor is set on the side of some cameras in the target camera set.

[0067] Example 3: This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: The status of the monitoring area corresponding to each camera in the target camera set during the target time period is obtained; the status of the monitoring area corresponding to any camera during the target time period is obtained based on the preset type data of the monitoring area corresponding to that camera during the target time period, wherein the preset type data does not include the video of the camera; the status of the monitoring area corresponding to any camera during the target time period is abnormal or normal.

[0068] If the monitoring area corresponding to a certain camera is in an abnormal state during the target time period, the video captured by that camera during the target time period is processed using a preset video processor; if the monitoring area corresponding to a certain camera is in a normal state during the target time period, the video captured by that camera during the target time period is not processed using the preset video processor; the preset video processor is a shared video processor for cameras in the target camera set, and the preset video processor is a cloud video processor or an edge video processor; the edge video processor is set on the side of some cameras in the target camera set.

[0069] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0070] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. It should also be understood that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for processing camera video, characterized in that, The method includes the following steps: The status of the monitoring area corresponding to each camera in the target camera set during the target time period is obtained; the status of the monitoring area corresponding to any camera during the target time period is obtained based on the preset type data of the monitoring area corresponding to that camera during the target time period, wherein the preset type data does not include the video of the camera; the status of the monitoring area corresponding to any camera during the target time period is abnormal or normal. If the monitoring area corresponding to a certain camera is in an abnormal state during the target time period, the video captured by that camera during the target time period is processed using a preset video processor; if the monitoring area corresponding to a certain camera is in a normal state during the target time period, the video captured by that camera during the target time period is not processed using the preset video processor; the preset video processor is a shared video processor for cameras in the target camera set, and the preset video processor is a cloud video processor or an edge video processor; the edge video processor is set on the side of some cameras in the target camera set; Obtaining the status of the monitoring area corresponding to each camera in the target camera set during the target time period includes: Obtain an initial set of vehicles that pass through the monitoring area corresponding to a specified camera within a target time period; the specified camera is any camera in the target camera set. Get the number of vehicles included in the initial vehicle set; The system obtains the specified speed of vehicles in the target vehicle set as they pass through the monitoring area corresponding to a specified camera, the first speed as they pass through the monitoring area corresponding to a first camera, and the second speed as they pass through the monitoring area corresponding to a second camera. The first camera is an adjacent camera located upstream of the specified camera in its direction of travel, and the second camera is an adjacent camera located downstream of the specified camera in its direction of travel. The target vehicle set is obtained by filtering an initial vehicle set, and the filtering conditions include passing through the monitoring area corresponding to the first camera and passing through the monitoring area corresponding to the second camera. The state of the monitoring area corresponding to the specified camera during the target time period is obtained based on the number of vehicles, the specified speed, the first speed, and the second speed. The state of the monitoring area corresponding to the specified camera during the target time period is obtained based on the number of vehicles, the specified speed, the first speed, and the second speed, including: The speed difference of a specified vehicle is obtained based on a specified speed, a first speed, and a second speed; the specified vehicle is any vehicle in the target vehicle set. Based on the weight and speed difference of each vehicle in the target vehicle set, obtain the mean and variance of the speed difference of the vehicles in the target vehicle set. The state of the monitoring area corresponding to the specified camera during the target time period is obtained based on the mean speed difference, the preset speed difference threshold, the speed difference variance, and the preset difference variance threshold; the speed difference threshold is positively correlated with the number of vehicles, and the difference variance threshold is positively correlated with the number of vehicles.

2. The method for processing camera video according to claim 1, characterized in that, The speed difference of a specified vehicle is obtained based on its specified speed, first speed, and second speed, including: The first speed of the designated vehicle is corrected based on the speed limit of the monitoring area corresponding to the first camera and the speed limit of the monitoring area corresponding to the designated camera to obtain the third speed of the designated vehicle. The second speed of the designated vehicle is corrected based on the upper speed limit of the monitoring area corresponding to the second camera and the upper speed limit of the monitoring area corresponding to the designated camera to obtain the fourth speed of the designated vehicle. Get the average speed of the third speed and the fourth speed of the specified vehicle; The absolute value of the difference between the average speed and the specified speed is determined as the speed difference of the specified vehicle.

3. The method for processing camera video according to claim 1, characterized in that, The state of the monitoring area corresponding to the specified camera during the target time period is obtained based on the mean speed difference, the preset speed difference threshold, the speed difference variance, and the preset difference variance threshold, including: If the mean of the speed difference is greater than or equal to a preset speed difference threshold, or the variance of the speed difference is greater than or equal to a preset speed variance threshold, or the mean of the speed difference is greater than or equal to a preset speed difference threshold and the variance of the speed difference is greater than or equal to a preset speed variance threshold, then the monitoring area corresponding to the specified camera is determined to be in an abnormal state during the target time period.

4. The method for processing camera video according to claim 1, characterized in that, The weight of any vehicle in the target vehicle set is negatively correlated with the time difference of that vehicle. The time difference of that vehicle is the difference between the time it takes for the vehicle to pass through the monitoring area corresponding to the designated camera and the center time of the target time period.

5. The method for processing camera video according to claim 1, characterized in that, The method further includes: if the result of processing the video of the target time period captured by the camera using a preset video processor is that there are no abnormalities, then the preset video processor is used to process the video of the adjacent time period of the target time period captured by the camera or the video of the target time period captured by the adjacent camera of the camera.

6. The method for processing camera video according to claim 1, characterized in that, Processing the video of the target time period captured by the camera using a preset video processor includes: when the preset video processor is a cloud video processor, uploading the video of the target time period captured by the camera to the cloud video processor for processing; when the preset video processor is an edge video processor, calling the edge video processor to process the video of the target time period captured by the camera.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the camera video processing method as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the camera video processing method as described in any one of claims 1 to 6.

Images