A target detection method, apparatus, device and medium
By using millimeter-wave radar to detect the continuous entry time and motion information of point clouds in the direction of intersections, and combining the results from adjacent areas, the problem of misjudgment in video detection under severe weather conditions is solved, and accurate analysis of traffic congestion status is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING HURYS INTELLIGENT TECH CO LTD
- Filing Date
- 2023-07-13
- Publication Date
- 2026-07-03
AI Technical Summary
In adverse weather conditions or when large vehicles obstruct the view, video detection cannot accurately determine whether the intersection's incoming and outgoing areas are in a state of excessive queuing, leading to misjudgments of traffic congestion.
By using millimeter-wave radar to detect the continuous entry time and motion information of point clouds in the area of interest and adjacent areas, the detection range is expanded. Combined with the target detection results of adjacent areas, the queuing over-limit status of the intersection's incoming area is determined.
It can still provide accurate traffic congestion status assessments even in severe weather, improving the accuracy of target congestion status assessments for areas of interest and ensuring accurate detection of oncoming traffic at intersections.
Smart Images
Figure CN116863417B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of transportation, and more particularly to a target detection method, apparatus, electronic device, and medium. Background Technology
[0002] During peak traffic hours or due to inclement weather, vehicles accumulate at intersections, queuing in both oncoming and channelized sections. When the queue length reaches a certain value, traffic congestion is inevitable. Therefore, it is necessary to detect queue exceeding limits in the oncoming areas of intersections.
[0003] Existing technologies often use video detection to determine whether the queuing area of an intersection is in a state of excessive queuing. Specifically, this involves using video detection to identify vehicle information in a specific area of the intersection's queuing area to determine whether the queuing area is in a state of excessive queuing.
[0004] However, severe weather conditions such as rain, snow, and fog, or obstruction by large vehicles, can prevent the video from providing accurate detection information for the area, leading to misjudgments of congestion. Summary of the Invention
[0005] This application provides a target detection method, apparatus, electronic device, and medium to assist in the analysis of whether an area of interest is in a target congestion state by utilizing the target detection results of adjacent areas, thereby improving the accuracy of the target congestion state judgment of the area of interest, and determining whether the oncoming area of the intersection where the area of interest is located is in a queue exceeding the limit state.
[0006] According to one aspect of this application, a target detection method is provided, the method comprising:
[0007] A region of interest and at least one adjacent region of the region of interest are identified as regions to be detected; wherein, the region of interest is the region where target detection is required.
[0008] The detection device was used to detect the duration of point cloud continuously entering each area to be detected.
[0009] Based on the duration and the motion information of the point cloud in each detection area, the target detection result of each detection area is determined, and the target congestion status of the area of interest is determined based on the target detection result.
[0010] According to another aspect of this application, a target detection device is provided, the device comprising:
[0011] The region of interest determination module is used to determine the region of interest and at least one adjacent region of the region of interest as the region to be detected; wherein, the region of interest is the region that needs to be detected;
[0012] The duration determination module is used to detect the duration of continuous entry of point cloud into each detection area using a detection device.
[0013] The congestion status determination module is used to determine the target detection result of each target area based on the duration and the motion information of the point cloud in each target area, and to determine the target congestion status of the target area of interest based on the target detection result.
[0014] According to another aspect of this application, an electronic device is provided, the device comprising:
[0015] At least one processor; and
[0016] A memory that is communicatively connected to at least one processor; wherein,
[0017] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the target detection method of any embodiment of this application.
[0018] According to another aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the target detection method of any embodiment of this application.
[0019] The technical solution of this application embodiment determines the area of interest and at least one adjacent area of the area of interest as the area to be detected, thus expanding the detection range and combining the target detection results of adjacent areas for analysis. The area of interest is the area where target detection is required. A detection device detects the duration of continuous point cloud entry into each area to be detected, providing accurate detection information even in adverse weather conditions. Based on the duration and the movement information of the point cloud in each area to be detected, the target detection result of each area to be detected is determined, and the target congestion status of the area of interest is determined based on the target detection result. Through the technical solution of this application embodiment, the target detection results of adjacent areas can be used to assist in the analysis of whether the area of interest is in a target congestion state, improving the accuracy of judging the target congestion status of the area of interest, and thereby determining whether the intersection where the area of interest is located is in a queue exceeding the limit.
[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of a target detection method provided according to Embodiment 1 of this application;
[0023] Figure 2 This is a schematic diagram of the location of the region of interest and adjacent regions according to Embodiment 1 of this application;
[0024] Figure 3 This is a flowchart of a target detection method according to Embodiment 2 of this application;
[0025] Figure 4 This is a flowchart of a target detection method provided according to Embodiment 3 of this application;
[0026] Figure 5 This is a schematic diagram of the structure of a target detection device according to Embodiment 4 of this application;
[0027] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the target detection method provided in Embodiment 5 of this application. Detailed Implementation
[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0029] It should be noted that the terms "first," "second," "third," "fourth," "actual," "preset," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0030] Example 1
[0031] Figure 1 This is a flowchart illustrating a target detection method provided in Embodiment 1 of this application. This embodiment is applicable to detecting vehicles on roads. The method can be executed by a target detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:
[0032] S110. Determine the region of interest and at least one adjacent region of the region of interest as the region to be detected; wherein, the region of interest is the region where target detection is required.
[0033] The area of concern is typically located in the oncoming traffic area of a road intersection. When the queue length in this area exceeds the road capacity or the upper limit stipulated by the traffic light cycle, a queue exceeding the limit occurs at the intersection, potentially leading to road congestion, traffic delays, and increased traffic risks. Therefore, target detection is needed for the area of concern to determine the target congestion status of the area, and thus determine whether the oncoming traffic area of the intersection is in a queue exceeding the limit state.
[0034] In this embodiment, the region of interest and at least one adjacent region of the region of interest are determined as the region to be detected. Based on the region of interest, the detection range is expanded to combine the target detection results of adjacent regions for analysis, thereby improving the accuracy of judging the target congestion status of the region of interest.
[0035] There are at least two adjacent areas, and the adjacent areas are located on the same road as the area of interest and on both sides of the area of interest.
[0036] Figure 2A schematic diagram showing the location of the area of interest and adjacent areas is provided. As shown in the figure, the area of interest is located in the oncoming traffic area at a road intersection. The adjacent areas are located on either side of the area of interest. A detection device facing the oncoming traffic area is installed at the intersection to perform target detection on the area of interest and the adjacent areas, i.e., the area to be detected. It is understandable that... Figure 2 The roads in the middle are single-lane roads. In multi-lane roads, attention zones and adjacent zones can be set in each lane.
[0037] S120. The detection device detects the duration of point cloud continuously entering each detection area.
[0038] The detection device can be millimeter-wave radar. Millimeter waves have wavelengths between microwaves and centimeter waves, thus millimeter-wave radar combines the penetrating power and all-weather capability of microwave radar with the high resolution of photoelectric radar. Using millimeter-wave radar for traffic detection eliminates the need to cut or damage the road surface and is unaffected by inclement weather.
[0039] A point cloud is a data set composed of many three-dimensional coordinate points, which can represent the shape and surface features of an object, scene, or environment. In the embodiments of this application, a point cloud can be used to represent the target to be detected.
[0040] In this embodiment, millimeter-wave radar is used to detect the duration of continuous entry of point clouds into each detection area to determine whether a target has entered each detection area. Compared to traditional methods of detecting road traffic conditions through video, the solution provided in this embodiment can obtain accurate detection information even in adverse weather conditions.
[0041] S130. Based on the duration and the motion information of the point cloud in each detection area, determine the target detection result of each detection area, and determine the target congestion status of the area of interest based on the target detection result.
[0042] The duration is used to determine whether the target enters each detection area, while the motion information of the point cloud in each detection area is used to predict whether the target will stay in each detection area.
[0043] In this embodiment, the target detection result of each target area is determined based on the duration and the motion information of the point cloud in each target area, i.e., whether the target corresponding to the point cloud exists in each target area. Combining the target detection results of each target area with the target detection results of adjacent areas, the accuracy of judging the target congestion status of the target area can be improved, and it can be further determined whether the incoming area of the intersection where the target area is located is in a queue exceeding the limit.
[0044] The technical solution of this application embodiment determines the area of interest and at least one adjacent area of the area of interest as the area to be detected, thus expanding the detection range and combining the target detection results of adjacent areas for analysis. The area of interest is the area where target detection is required. A detection device detects the duration of continuous point cloud entry into each area to be detected, ensuring accurate detection information even in adverse weather conditions. Based on the duration and the movement information of the point cloud in each area to be detected, the target detection result of each area to be detected is determined, and the target congestion status of the area of interest is determined based on the target detection result. Through the technical solution of this application embodiment, the target detection results of adjacent areas can be used to assist in the analysis of whether the area of interest is in a target congestion state, improving the accuracy of judging the target congestion status of the area of interest, and thereby determining whether the intersection where the area of interest is located is in a queue exceeding the limit.
[0045] Example 2
[0046] Figure 3 This is a flowchart of a target detection method provided in Embodiment 2 of this application. This embodiment is an optimization based on the above embodiments. Solutions not described in detail in this embodiment are found in the above embodiments. Figure 3 As shown, the method in this embodiment of the application specifically includes the following steps:
[0047] S210. Determine the region of interest and at least one adjacent region of the region of interest as the region to be detected; wherein, the region of interest is the region where target detection is required.
[0048] S220, The number of frames of point clouds that continuously enter each area to be detected is detected by the detection device.
[0049] In this embodiment, millimeter-wave radar is used as the detection device. After determining the area to be detected, the millimeter-wave radar can detect point clouds continuously entering each area, and when the continuous entry of point clouds into each area is interrupted, the number of frames of the point clouds continuously entering each area is counted. Therefore, accurate detection information can be obtained even in adverse weather conditions.
[0050] S230. Determine the duration for which the point cloud continuously enters each detection area based on the period and frame number of the detection signal emitted by the detection device.
[0051] It is understandable that the interval between frames of point cloud images continuously entering each detection area is the period of the detection device transmitting the detection signal, which is also the period of the millimeter-wave radar transmitting the pulse signal. Therefore, after detecting the number of frames of point cloud images continuously entering each detection area by the detection device, the duration of continuous entry of point cloud images into each detection area can be determined based on the period of the detection device transmitting the detection signal and the number of frames of point cloud images continuously entering each detection area.
[0052] S240. Based on the duration and the motion information of the point cloud in each detection area, determine the target detection result of each detection area, and determine the target congestion status of the area of interest based on the target detection result.
[0053] In this embodiment, the target can be determined based on the duration and the motion information of the point cloud in each detection area, whether the target enters each detection area and whether the target will stay in each detection area, thereby determining the target detection result of each detection area.
[0054] Specifically, based on the duration and the motion information of the point cloud in each detection area, the target detection result for each detection area is determined, including:
[0055] If the duration exceeds the preset duration, the target corresponding to the point cloud is determined to have entered the detection area;
[0056] If it is determined that the target corresponding to the point cloud has entered the detection area, the target detection result of each detection area is determined based on the motion information of the point cloud in each detection area.
[0057] The preset duration represents the critical time required for the point cloud corresponding to the target to continuously enter each detection area. Therefore, when the duration for which the point cloud continuously enters the detection area exceeds the preset duration, it can be determined that the target corresponding to the point cloud has entered the detection area. At this point, it is also necessary to use the motion information of the point cloud in each detection area to predict whether the target will stay in each detection area, in order to determine the target detection result for each detection area.
[0058] Specifically, based on the motion information of the point cloud in each region to be detected, the target detection results for each region to be detected are determined, including:
[0059] If the point cloud is predicted to remain within the detection area based on its position and / or velocity, then the target detection result for that detection area is determined to be a target corresponding to the point cloud.
[0060] If the point cloud is predicted to leave the detection area based on its position and / or velocity, then the target detection result for the detection area is determined to be a target that does not exist in the point cloud.
[0061] The motion information of the point cloud in each detection area includes the position and / or velocity of the point cloud. In this embodiment, the point cloud's position and / or velocity can be used to predict whether it remains within the detection area or leaves the detection area, thereby determining the target detection result for each detection area.
[0062] Understandably, when the point cloud's position changes towards the opposite edge of the detection area, the probability of the point cloud leaving the detection area is higher; conversely, when the point cloud's position changes to remain in place, the probability of the point cloud remaining within the detection area is higher. Furthermore, the greater the point cloud's velocity, the higher the probability of it leaving the detection area; conversely, the closer the point cloud's velocity is to 0, the higher the probability of it remaining within the detection area. Therefore, the target detection results for each detection area can be obtained.
[0063] It should be noted that predicting whether a point cloud will remain within or leave the detection area based on its position and / or velocity can solve the occlusion problem that occurs when the detection device is a millimeter-wave radar that uses wave propagation to detect vehicles. For example, in the oncoming traffic area of an intersection, a large vehicle in front of a smaller vehicle can block the pulse signal emitted by the millimeter-wave radar. The technical solution of this application, by predicting whether a small vehicle will remain within or leave the detection area based on its corresponding point cloud position and / or velocity when it enters the detection area, obtains the target detection result. This solves the problem of inaccurate detection results caused by the pulse signal being blocked when a small vehicle passes a large vehicle.
[0064] Optionally, due to various uncontrollable factors in real driving scenarios, the target detection results of each area to be detected can be continuously acquired. When the target detection results of each area to be detected remain unchanged for a duration exceeding a preset duration threshold, the target detection results are taken as the final target detection results of each area to be detected, thereby eliminating the influence of uncontrollable factors and improving the accuracy of target detection results.
[0065] In this embodiment of the application, after obtaining the target detection results of each area to be detected, the target congestion status of the area of interest can be determined by combining the target detection results of each area.
[0066] Specifically, the congestion status of the target area of interest is determined based on the target detection results, including:
[0067] If the target detection result of the region of interest in the detection area to be tested is that there is a target corresponding to the point cloud, then the target congestion status of the region of interest is determined to be congested.
[0068] Otherwise, the target congestion status of the area of interest is determined based on the target detection results of adjacent areas in the area to be detected.
[0069] Understandably, when the target detection result of the region of interest in each region to be detected is that there is a target corresponding to the point cloud, the target congestion status of the region of interest can be directly determined as congested. However, when the target detection result of the region of interest is that there is no target corresponding to the point cloud, it is necessary to determine the target congestion status of the region of interest by using the target detection results of the adjacent regions of the region of interest in the region to be detected.
[0070] Specifically, based on the target detection results of adjacent areas in the area to be detected, the target congestion status of the area of interest is determined, including:
[0071] If the target detection results of adjacent areas in the area to be detected are all targets with corresponding point clouds, then the target congestion status of the area of interest is determined to be congested.
[0072] In this embodiment, when the target detection results in two adjacent regions of the region of interest both show targets corresponding to point clouds, even if the target detection result in the region of interest shows no targets corresponding to point clouds, the congestion status of the region of interest can still be determined. Therefore, the congestion status of the region of interest can be accurately determined, and this can be used to determine whether the oncoming traffic at the intersection where the region of interest is located is in a queue exceeding the limit.
[0073] This application provides a target detection method that identifies a region of interest and at least one adjacent region as a region to be detected, thus expanding the detection range and combining the target detection results of adjacent regions for analysis. The region of interest is the area requiring target detection. A detection device detects the number of frames of point clouds continuously entering each region to be detected, ensuring accurate detection information even in adverse weather conditions. The duration of continuous point cloud entry into each region to be detected is determined based on the period and number of frames emitted by the detection device. Based on the duration and the motion information of the point cloud in each region to be detected, the target detection result for each region to be detected is determined, and the target congestion status of the region of interest is determined based on the target detection results. Through the technical solution of this application, the target detection results of adjacent regions can be used to assist in the analysis of whether the region of interest is in a target congestion state, improving the accuracy of judging the target congestion status of the region of interest, and thereby determining whether the intersection where the region of interest is located is in a queue exceeding the limit.
[0074] Example 3
[0075] Figure 4 This is a flowchart of a target detection method provided in Embodiment 3 of this application. This embodiment is a parallel scheme to the above embodiments; schemes not described in detail in this embodiment can be found in the above embodiments. Figure 4As shown, the method in this embodiment of the application specifically includes the following steps:
[0076] S310. Determine the region of interest and at least one adjacent region of the region of interest as the region to be detected; wherein, the region of interest is the region where target detection is required.
[0077] S320, The number of frames of point clouds that continuously enter each area to be detected is detected by the detection device.
[0078] S330. Determine the duration for which the point cloud continuously enters each detection area based on the period and frame number of the detection signal emitted by the detection device.
[0079] S340. If the duration exceeds the preset duration, then the target corresponding to the point cloud is determined to have entered the detection area.
[0080] It is understood that, in the embodiments of this application, when using point clouds to represent the target to be detected, the target should correspond to a cluster of point clouds including continuous point clouds, rather than a single point cloud.
[0081] Therefore, the duration for which point clouds continuously enter each detection area can be used to determine whether the target corresponding to the point cloud has entered the detection area. Specifically, when the duration for which point clouds continuously enter the detection area exceeds a preset duration, it can be determined that the target corresponding to the point cloud has entered the detection area.
[0082] S350. If it is determined that the target corresponding to the point cloud has entered the detection area, the target detection result of each detection area is determined based on the motion information of the point cloud in each detection area.
[0083] After the target corresponding to the point cloud enters the detection area, the target can be predicted to stay in each detection area based on the motion information of the point cloud in each detection area, so as to determine the target detection result of each detection area.
[0084] Specifically, based on the motion information of the point cloud in each region to be detected, the target detection results for each region to be detected are determined, including:
[0085] Predict the relative position of the point cloud to the region to be detected based on the position and / or velocity of the point cloud; wherein, the relative position includes whether the point cloud is within the region to be detected or has moved outside the region to be detected.
[0086] The number of targets remaining in the detection area is determined based on the relative position of the point cloud and the area to be detected.
[0087] The target detection result for each area is determined based on the number of targets remaining in the detection area.
[0088] In this embodiment, the prediction of whether a point cloud will leave or remain within a detection area is made by detecting the positional change trend and velocity of the point cloud. Optionally, the probability of the point cloud leaving the detection area is higher when its positional change trend is closer to the other edge of the detection area, while the probability of the point cloud remaining within the detection area is higher when its positional change trend is stationary. The greater the velocity of the point cloud, the higher the probability of it leaving the detection area; the closer the velocity of the point cloud is to 0, the higher the probability of it remaining within the detection area. Therefore, the relative position of the point cloud to the detection area can be predicted, and the number of targets remaining within the detection area can be determined accordingly.
[0089] Specifically, the number of targets remaining within the detection area is determined based on the relative position of the point cloud and the detection area, including:
[0090] If the point cloud is determined to be within the detection area based on its relative position to the detection area, then the point cloud is clustered based on its actual position within the detection area and / or the position where the point cloud disappears from the detection area to obtain the target corresponding to the point cloud.
[0091] The number of targets remaining within the detection area is obtained by statistical analysis.
[0092] Clustering of point clouds is performed to divide them into groups or clusters with similar features, thereby identifying the target corresponding to the point cloud.
[0093] In real-world driving scenarios, large vehicles in front may obstruct smaller vehicles behind, preventing the detection device from detecting the smaller vehicles and leading to errors in the count of targets within the detection area. Therefore, in this embodiment, when counting targets within the detection area, if there is no obstruction, the point cloud is clustered based on its actual position within the detection area to obtain the corresponding targets; if obstruction exists, the point cloud is clustered based on its position when it disappears to obtain the corresponding targets. This solves the problem of large vehicles obstructing smaller vehicles behind, causing the detection device to fail to detect the smaller vehicles and resulting in errors in the count of targets within the detection area. Furthermore, the target detection results for each detection area can be determined based on the number of targets within the detection area.
[0094] Specifically, based on the number of targets remaining within the detection area, the target detection results for each detection area are determined, including:
[0095] If the number of targets remaining in the detection area is greater than the preset threshold, the target detection result in the detection area is determined to be in a clustered state.
[0096] Otherwise, the target detection result of the area to be detected is determined to be in a non-aggregated state.
[0097] In this embodiment, the target detection results in the detection area are divided into clustered and non-clustered states based on whether the number of targets remaining in the detection area is greater than a preset threshold. When the number of targets remaining in the detection area is greater than the preset threshold, the target detection results in the detection area are determined to be in a clustered state; otherwise, they are determined to be in a non-clustered state.
[0098] S360: Determine the congestion status of targets in the area of interest based on the target detection results.
[0099] After determining the target detection results for each area to be detected, the target congestion status of the area of interest can be determined based on the target detection results for each area to be detected.
[0100] Specifically, the congestion status of the target area of interest is determined based on the target detection results, including:
[0101] If the target detection result of the area of interest in the area to be detected is in a clustered state, then the target congestion state of the area of interest is determined to be congested.
[0102] Otherwise, the target congestion status of the area of interest is determined based on the target detection results of adjacent areas in the area to be detected.
[0103] Understandably, when the target detection result of the area of interest in each area to be detected is in a clustered state, the target congestion state of the area of interest can be directly determined as congested. However, when the target detection result of the area of interest is in a non-clustered state, it is necessary to determine the target congestion state of the area of interest by using the target detection results of the adjacent areas of the area of interest in the area to be detected.
[0104] Specifically, based on the target detection results of adjacent areas in the area to be detected, the target congestion status of the area of interest is determined, including:
[0105] If the target detection results of adjacent areas in the area to be detected are all in a clustered state, then the target congestion state of the area of interest is determined to be congested.
[0106] In this embodiment, when the target detection results in two adjacent areas of the area of interest are both in a clustered state, even if the target detection result in the area of interest is in a non-clustered state, the congestion status of the target in the area of interest can still be determined. Therefore, the congestion status of the target in the area of interest can be accurately determined, and this can be used to determine whether the queuing area at the intersection where the area of interest is located is in a queue exceeding the limit.
[0107] In this embodiment, a region of interest and at least one adjacent region of the region of interest are determined as regions to be detected. The region of interest is the region where target detection is required. A detection device detects the number of frames of point clouds continuously entering each region to be detected. Based on the period and number of frames of the detection signal emitted by the detection device, the duration of continuous entry of the point clouds into each region to be detected is determined. If the duration exceeds a preset duration, it is determined that the target corresponding to the point cloud has entered the region to be detected. If the target corresponding to the point cloud is determined to have entered the region to be detected, the target detection result for each region to be detected is determined based on the motion information of the point cloud in each region to be detected. The target congestion status of the region of interest is determined based on the target detection results. Through the technical solution of this embodiment, the target detection results of adjacent regions can be used to assist in the analysis of whether the region of interest is in a target congestion state, improving the accuracy of the judgment of the target congestion status of the region of interest, and thereby determining whether the intersection where the region of interest is located is in a queuing overload state.
[0108] Example 4
[0109] Figure 5 This is a schematic diagram of a target detection device provided in Embodiment 4 of this application. This device can execute the target detection method provided in any embodiment of this application, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 5 As shown, the device includes:
[0110] The region of interest determination module 410 is used to determine the region of interest and at least one adjacent region of the region of interest as the region to be detected; wherein, the region of interest is the region that needs to be detected.
[0111] The duration determination module 420 is used to detect the duration of continuous entry of the point cloud into each area to be detected by the detection device.
[0112] The congestion state determination module 430 is used to determine the target detection result of each detection area based on the duration and the motion information of the point cloud in each detection area, and to determine the target congestion state of the area of interest based on the target detection result.
[0113] In this embodiment of the application, the duration determination module 420 includes:
[0114] The frame count detection unit is used to detect the number of frames of point clouds that continuously enter each detection area through the detection device;
[0115] The duration determination unit is used to determine the duration of continuous entry of the point cloud into each detection area based on the period of the detection signal emitted by the detection device and the number of frames.
[0116] In this embodiment of the application, the congestion status determination module 430 includes:
[0117] The target location determination unit is used to determine that the target corresponding to the point cloud has entered the detection area if the duration is longer than a preset duration.
[0118] The target detection result determination unit is used to determine the target detection result of each detection area based on the motion information of the point cloud in each detection area if it is determined that the target corresponding to the point cloud has entered the detection area.
[0119] Optionally, the target detection result determination unit includes:
[0120] The first target detection result prediction subunit is used to determine the target detection result of the area to be detected as having a target corresponding to the point cloud if the point cloud is predicted to remain in the area to be detected based on the position and / or velocity of the point cloud.
[0121] The second target detection result prediction subunit is used to determine that the target detection result of the target area to be detected is that there is no target corresponding to the point cloud if the point cloud is predicted to leave the target area based on the position and / or velocity of the point cloud.
[0122] In this embodiment of the application, the congestion status determination module 430 includes:
[0123] The first congestion state determination unit is used to determine that the target congestion state of the area of interest is congested if the target detection result of the area of interest in the detection area to be tested is that there is a target corresponding to the point cloud.
[0124] The second congestion state determination unit is used to determine the target congestion state of the region of interest based on the target detection results of adjacent regions in the region to be detected, if otherwise.
[0125] Optionally, the second congestion state determination unit is specifically used for:
[0126] If the target detection results of all adjacent areas in the area to be detected are that the target corresponding to the point cloud exists, then the target congestion status of the area of interest is determined to be congested.
[0127] Optionally, there are at least two adjacent areas, which are located on the same road as the area of interest and on either side of the area of interest.
[0128] Optionally, the target detection result determination unit includes:
[0129] The third target detection result prediction subunit is used to predict the relative position of the point cloud and the area to be detected based on the position and / or velocity of the point cloud; wherein, the relative position includes staying within the area to be detected or leaving the area to be detected.
[0130] The target quantity determination subunit is used to determine the number of targets remaining in the detection area based on the relative position of the point cloud and the detection area;
[0131] The target detection result determination subunit is used to determine the target detection result of each detection area based on the number of targets remaining in the detection area.
[0132] Optionally, the target number of sub-units is determined, specifically for:
[0133] If it is determined that the point cloud is located within the detection area based on its relative position to the detection area, then the point cloud is clustered to obtain the target corresponding to the point cloud based on its actual location within the detection area and / or the location where the point cloud disappears.
[0134] The number of targets remaining within the detection area is obtained by statistical analysis.
[0135] Optionally, the target detection result determines the sub-unit, specifically used for:
[0136] If the number of targets remaining in the detection area is greater than a preset threshold, then the target detection result of the detection area is determined to be in a clustered state.
[0137] Otherwise, the target detection result of the area to be detected is determined to be in a non-aggregated state.
[0138] In this embodiment of the application, the congestion status determination module 430 includes:
[0139] The third congestion state determination unit is used to determine the target congestion state of the region of interest as congested if the target detection result of the region of interest in the region to be detected is in a clustered state.
[0140] The fourth congestion state determination unit is used to determine the target congestion state of the region of interest based on the target detection results of adjacent regions in the region to be detected, if otherwise.
[0141] Optionally, the fourth congestion state determination unit is specifically used for:
[0142] If the target detection results of adjacent areas in the area to be detected are all in a clustered state, then the target congestion state of the area of interest is determined to be congested.
[0143] The target detection device provided in this application embodiment can execute a target detection method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method.
[0144] Example 5
[0145] Figure 6 A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.
[0146] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0147] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0148] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as object detection methods.
[0149] In some embodiments, the target detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the target detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the target detection method by any other suitable means (e.g., by means of firmware).
[0150] Various embodiments of the methods and techniques described above herein can be implemented in digital electronic circuit methods, integrated circuit methods, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), methods-on-a-chip (SOCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable method including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage method, at least one input device, and at least one output device, and transmitting data and instructions to the storage method, the at least one input device, and the at least one output device.
[0151] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable target detection device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0152] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution method, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor methods, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0153] To provide interaction with a user, the methods and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0154] The methods and techniques described herein can be implemented in computing methods that include backend components (e.g., as a data server), or computing methods that include middleware components (e.g., an application server), or computing methods that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the methods and techniques described herein), or any combination of such backend, middleware, or frontend components. The components of the methods can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0155] Computational methods can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0156] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired information of the technical solution of this application can be achieved, and this is not limited herein.
[0157] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.
Claims
1. A target detection method, characterized in that, The method includes: A region of interest and at least two adjacent regions of the region of interest are identified as regions to be detected; wherein, the region of interest is the region where target detection is required; the adjacent regions are located on the same road as the region of interest and are located on both sides of the region of interest; The detection device was used to detect the duration of point cloud continuously entering each area to be detected. Based on the duration and the motion information of the point cloud in each detection area, the target detection result of each detection area is determined, and the target congestion status of the area of interest is determined based on the target detection result. Based on the duration and the motion information of the point cloud in each detection area, the target detection result for each detection area is determined, including: If the duration is longer than the preset duration, then the target corresponding to the point cloud is determined to have entered the detection area; If it is determined that the target corresponding to the point cloud has entered the detection area, the target detection result of each detection area is determined based on the motion information of the point cloud in each detection area. Based on the motion information of the point cloud in each region to be detected, the target detection results for each region to be detected are determined, including: If the point cloud is predicted to remain within the detection area based on its position and / or velocity, then the target detection result for the detection area is determined to be the presence of a target corresponding to the point cloud. If the point cloud is predicted to leave the detection area based on its position and / or velocity, then the target detection result for the detection area is determined to be that there is no target corresponding to the point cloud. Determining the target congestion status of the area of interest based on the target detection results includes: If the target detection result of the region of interest in the region to be detected is that the target corresponding to the point cloud exists, then the target congestion status of the region of interest is determined to be congested. Otherwise, the target congestion status of the area of interest is determined based on the target detection results of adjacent areas in the area to be detected. Based on the target detection results of adjacent areas in the area to be detected, the target congestion status of the area of interest is determined, including: If the target detection results of adjacent areas in the area to be detected all contain the target corresponding to the point cloud, then the target congestion status of the area of interest is determined to be congested.
2. The method according to claim 1, characterized in that, The detection device measures the duration of continuous point cloud entry into each detection area, including: The number of frames of point clouds continuously entering each area to be detected is detected by the detection device; The duration for which point clouds continuously enter each detection area is determined based on the period of the detection signal emitted by the detection device and the number of frames.
3. A target detection method, characterized in that, The method includes: A region of interest and at least two adjacent regions of the region of interest are identified as regions to be detected; wherein, the region of interest is the region where target detection is required; the adjacent regions are located on the same road as the region of interest and are located on both sides of the region of interest; The detection device was used to detect the duration of point cloud continuously entering each area to be detected. Based on the duration and the motion information of the point cloud in each detection area, the target detection result of each detection area is determined, and the target congestion status of the area of interest is determined based on the target detection result. Based on the duration and the motion information of the point cloud in each detection area, the target detection result for each detection area is determined, including: If the duration is longer than the preset duration, then the target corresponding to the point cloud is determined to have entered the detection area; If it is determined that the target corresponding to the point cloud has entered the detection area, the target detection result of each detection area is determined based on the motion information of the point cloud in each detection area. Based on the motion information of the point cloud in each region to be detected, the target detection results for each region to be detected are determined, including: The relative position of the point cloud to the region to be detected is predicted based on the position and / or velocity of the point cloud; wherein, the relative position includes being within the region to be detected or leaving the region to be detected. The number of targets remaining in the detection area is determined based on the relative position of the point cloud and the detection area. The target detection result for each detection area is determined based on the number of targets remaining in the detection area. Based on the number of targets remaining within the detection area, the target detection result for each detection area is determined, including: If the number of targets remaining in the detection area is greater than a preset threshold, then the target detection result of the detection area is determined to be in a clustered state. Otherwise, the target detection result of the area to be detected is determined to be in a non-aggregated state; Determining the target congestion status of the area of interest based on the target detection results includes: If the target detection result of the region of interest in the region to be detected is in a clustered state, then the target congestion state of the region of interest is determined to be congested. Otherwise, the target congestion status of the area of interest is determined based on the target detection results of adjacent areas in the area to be detected. Based on the target detection results of adjacent areas in the area to be detected, the target congestion status of the area of interest is determined, including: If the target detection results of adjacent areas in the area to be detected are all in a clustered state, then the target congestion state of the area of interest is determined to be congested.
4. The method according to claim 3, characterized in that, Determining the number of targets residing within the detection area based on the relative position of the point cloud and the detection area includes: If it is determined that the point cloud is located within the detection area based on the relative position of the point cloud and the detection area, then the point cloud is clustered to obtain the target corresponding to the point cloud based on the actual position of the point cloud located within the detection area and / or the position where the point cloud located within the detection area disappears. The number of targets remaining within the detection area is obtained by statistical analysis.
5. A target detection device, characterized in that, The device includes: The region of interest determination module is used to determine a region of interest and at least two adjacent regions of the region of interest as regions to be detected; wherein, the region of interest is the region where target detection is required; the adjacent regions are located on the same road as the region of interest and are located on both sides of the region of interest; The duration determination module is used to detect the duration of continuous entry of point cloud into each detection area using a detection device. The congestion status determination module is used to determine the target detection result of each detection area based on the duration and the motion information of the point cloud in each detection area, and to determine the target congestion status of the area of interest based on the target detection result. The congestion status determination module includes: The target location determination unit is used to determine that the target corresponding to the point cloud has entered the detection area if the duration is longer than a preset duration. The target detection result determination unit is used to determine the target detection result of each detection area based on the motion information of the point cloud in each detection area if it is determined that the target corresponding to the point cloud has entered the detection area. The target detection result determination unit includes: The first target detection result prediction subunit is used to determine the target detection result of the area to be detected as having a target corresponding to the point cloud if the point cloud is predicted to remain in the area to be detected based on the position and / or velocity of the point cloud. The second target detection result prediction subunit is used to determine that the target detection result of the target area to be detected is that there is no target corresponding to the point cloud if the point cloud is predicted to leave the target area based on the position and / or velocity of the point cloud. The congestion status determination module includes: The first congestion state determination unit is used to determine that the target congestion state of the area of interest is congested if the target detection result of the area of interest in the area to be detected is that there is a target corresponding to the point cloud. The second congestion state determination unit is used to determine the target congestion state of the region of interest based on the target detection results of adjacent regions in the region to be detected, if otherwise. The second congestion state determination unit is specifically used for: If the target detection results of all adjacent areas in the area to be detected are that the target corresponding to the point cloud exists, then the target congestion status of the area of interest is determined to be congested.
6. An electronic device, characterized in that, The device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target detection method according to any one of claims 1-2 or 3-4.
7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the target detection method according to any one of claims 1-2 or 3-4.