Target detection method and device, electronic equipment and medium

Through the coordinated work of the detection device and the target image collector, the visual range of the target is determined and the appropriate collector is selected for detection, which solves the problem of target detection by the radar but cannot be detected by the ball machine, and improves the detection accuracy and efficiency.

CN119007090APending Publication Date: 2024-11-22ZHEJIANG UNIVIEW TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202310576773.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-19
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the existing radar and ball machine linkage detection, the radar detects the target but the ball machine cannot detect it, especially when there are obstacles within the field of view of the ball machine, resulting in inaccurate target detection.

Method used

The target is detected by the detection device, the detection information of the target is determined, and its visual range is determined based on the detection results of the target image collector, and a suitable target image collector is selected for detection to ensure that the target is detected within the visual range.

Benefits of technology

It improves the accuracy and success rate of target detection, avoids detection failure caused by the target being invisible range, and improves detection efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007090A_ABST
    Figure CN119007090A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a target detection method and device, electronic equipment and a medium. The method comprises the steps that a target is detected through a detection device, and detection information of the target is determined; determining a target image collector corresponding to the target, detecting the target through the target image collector, and determining a target detection result; and according to the detection information of the target and the target detection result, determining a visual range detection result of the target image collector, determining a new target image collector corresponding to a new target according to the visual range detection result, and detecting the new target. According to the scheme, the visual range detection result of the target image collector can be determined and continuously updated, so that a new target image collector is conveniently determined to detect a new target according to the visual range detection result in the subsequent target detection process, and the probability of detecting the target and the target detection efficiency are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of target detection technology, and in particular to a target detection method, device, electronic equipment and medium. Background Art

[0002] At present, a defense zone is usually set in a monitoring scene, which refers to an area where preset targets are prohibited from entering. In order to improve the accuracy of detecting targets entering the defense zone, a detection device (such as a radar) and an image collector (such as a ball camera) are usually used for linkage monitoring and detection.

[0003] Specifically, for example, target detection is performed by radar. When the radar detects a target, radar detection data is obtained, and the coordinate information of the target in the radar coordinate system is determined based on the radar detection data. The coordinate information is mapped to the PTZ (Pan Tilt Zoom, pan-tilt all-round movement and lens zoom control) parameters of the ball camera according to the parameter mapping matrix. The ball camera is rotated into place and the shooting parameters are adjusted according to the PTZ parameters of the ball camera, and the adjusted ball camera is rotated to shoot. On this basis, target detection can be performed on the captured image, such as detecting whether the target is a preset target, so as to determine whether an alarm prompt needs to be executed.

[0004] However, currently the radar and the ball camera are bound one by one, and the models of the radar and the ball camera must be fixedly matched. In addition, the visual range of the ball camera is limited, and there is a situation where the radar detects the target but the ball camera cannot detect the target. When there is an obstacle blocking the field of view of the ball camera, the preset target cannot be accurately detected by the ball camera. Summary of the invention

[0005] The present application provides a target detection method, device, electronic device and medium to determine a visible range detection result based on a target detection result of a target image collector, to select a target image collector for target detection based on the visible range result, and to improve detection accuracy and success rate.

[0006] According to one aspect of the present application, a target detection method is provided, the method comprising:

[0007] Detecting the target through the detection device and determining the detection information of the target;

[0008] Determine a target image collector corresponding to the target, detect the target through the target image collector, and determine a target detection result;

[0009] According to the detection information of the target and the target detection result, the visual range detection result of the target image collector is determined, so as to determine a new target image collector corresponding to a new target according to the visual range detection result, and detect the new target.

[0010] According to another aspect of the present application, a target detection device is provided, the device comprising:

[0011] A detection module, used to detect a target through a detection device and determine the detection information of the target;

[0012] A target detection module is used to determine a target image collector corresponding to the target, detect the target through the target image collector, and determine a target detection result;

[0013] The visual range detection module is used to determine the visual range detection result of the target image collector according to the detection information of the target and the target detection result, so as to determine a new target image collector corresponding to a new target according to the visual range detection result and detect the new target.

[0014] According to another aspect of the present application, an electronic device is provided, the device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the target detection method of any embodiment of the present application.

[0018] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the target detection method of any embodiment of the present application when executed.

[0019] The technical solution of the embodiment of the present application is to detect the target through a detection device and determine the detection information of the target; determine the target image collector corresponding to the target, detect the target through the target image collector, and determine the target detection result; determine the visible range detection result of the target image collector according to the detection information of the target and the target detection result, so as to determine a new target image collector corresponding to a new target according to the visible range detection result, and detect the new target. The above scheme can timely and accurately determine the visible range detection result of the target image collector according to the target detection result obtained by detecting the target by the target image collector, so as to determine the target image collector to detect the target according to the visible range detection result in the subsequent detection process, thereby avoiding the problem that the target cannot be detected when the target is in the invisible range of the image collector and the image collector is used for target detection, thereby improving the target detection success rate and detection efficiency.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a target detection method provided according to Embodiment 1 of the present application;

[0023] Figure 2 This is a schematic diagram of an obstruction blocking the field of view provided in Example 1 of the present application;

[0024] Figure 3 is a schematic diagram of the visual range detection result provided according to the first embodiment of the present application;

[0025] Figure 4 is a flow chart of a target detection method provided according to Embodiment 2 of the present application;

[0026] Figure 5 is a critical line segment schematic diagram provided according to Embodiment 2 of the present application;

[0027] Figure 6 This is a schematic diagram of the range boundary provided according to the second embodiment of the present application;

[0028] Figure 7 This is a schematic diagram of the visible range and the invisible range provided according to the second embodiment of the present application;

[0029] Figure 8 is a schematic diagram of at least two critical line segments provided according to Embodiment 2 of the present application;

[0030] Fig. 9 is a flow chart of a target detection method provided according to Embodiment 3 of the present application;

[0031] Fig.10 is a flow chart of a target detection method provided according to Embodiment 4 of the present application;

[0032] Fig.11 is a schematic diagram of an equivalent target area provided according to the fourth embodiment of the present application;

[0033] Fig.12is a structural schematic diagram of a target detection device provided according to Embodiment 5 of the present application;

[0034] Fig.13 It is a structural diagram of an electronic device that implements a target detection method provided in Example 6 of the present application. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0036] It should be noted that the terms "first", "second", "third", "fourth", "actual", "preset", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment 1

[0038] Figure 1 The flowchart of a target detection method provided in the first embodiment of the present application is applicable to the case of detecting a target. Typically, it can be applicable to the case of detecting a target using a detection device and an image collector. The method can be executed by a target detection device, which can be implemented in the form of hardware and / or software, and the target detection device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0039] S110: Detect the target by using a detection device, and determine the detection information of the target.

[0040] Among them, the detection device can be a device capable of detecting a target, for example, a radar, a sound wave detection device, an infrared detection device, etc. In an embodiment of the present application, the detection device can be used to detect a target in a preset area, so that the target can be detected in time when the target enters the preset area. The detection information may include the location information, type information, size information, etc. of the target. The detection device can detect the target and determine the detection information of the target. For example, the electromagnetic wave emitted by the radar is reflected by the target, and the existence of the target is detected. According to the time when the radar emits the electromagnetic wave, the time when the electromagnetic wave reflected by the target is received, and the transmission speed of the electromagnetic wave, the distance of the target relative to the radar is determined. According to the direction of the electromagnetic wave emitted by the radar, the direction of the target can be determined. According to the range of the electromagnetic wave emitted by the radar, the size information and type information of the target are determined.

[0041] In the embodiment of the present application, if the detection device is a radar, when the radar detects the target, the coordinates of the target in the radar coordinate system can be determined. The longitude and latitude of the target can be determined based on the longitude and latitude of the radar, the detection angle of the radar, and the coordinates of the target in the radar coordinate system.

[0042] S120, determining a target image collector corresponding to the target, detecting the target through the target image collector, and determining a target detection result.

[0043] The target image collector corresponding to the target may be an image collector used to detect the target, and the target image collector is not limited to one, and may be two or more. If the number of target image collectors is two or more, one target image collector may be selected in sequence to detect the target, or at least two target image collectors may be used to detect the target at the same time.

[0044] In an embodiment of the present application, the target is detected by a target image collector to determine the target detection result. If the target image collector is an intelligent image collector, the target detection result can be obtained by the target image collector. If the target image collector is a non-intelligent image collector, the image of a preset area can be collected by the target image collector, and the image can be sent to a processor corresponding to the target image collector, and the processor performs target detection.

[0045] S130. Determine a visible range detection result of the target image collector according to the detection information of the target and the target detection result, determine a new target image collector corresponding to a new target according to the visible range detection result, and detect the new target.

[0046] For example, Figure 2As shown in the figure, it may be difficult for the target image collector to capture images based on the current installation height, and there may be invisible areas blocked by obstructions. In this case, the visible range and invisible range of the target image collector are shown in the top view as follows: Figure 3 As shown. Among them, the areas in the field of view other than those marked with visible range and invisible range are areas with undetermined visible range. After the detection device detects the target and determines the position of the target, when the target is detected by the target image collector, the target should theoretically be detected at the position of the target. By detecting the target through the target image collector, it can be determined whether the target image collector detects the target according to the target detection result, thereby determining whether the target is within the visible range of the target image collector, and then determining the visible range detection result of the target image collector. For example, if the target image collector adjusts the image collector parameters to meet the position of the viewing angle toward the target and the magnification meets the requirements, the target image collector can detect the target, then it is determined that the target is within the visible range of the target image collector. If the target cannot be detected, then it is determined that the target is within the invisible range of the target image collector, and the visible range detection result of the target image collector is determined accordingly.

[0047] In an embodiment of the present application, after determining the visible range detection result of the target image collector, the visible range detection result of the target image collector can be recorded. When the subsequent detection device detects a new target and needs to detect the new target, the target image collector whose position is within the visible range can be selected according to the recorded visible range detection result, the new target can be detected, and S130 can be continued to be executed to update the visible range detection result of the target image collector. After multiple target detections, the visible range detection results of each target image collector and the visible range detection results within the entire visible range of the target image collector can be determined. Exemplarily, if the target image collector is a ball camera, the position of the target has been determined, and when the target is detected by the target image collector, the target image collector is only controlled to turn to a fixed angle to detect the target, so the visible range detection result is also only the visible range detection result corresponding to the fixed angle. The ball camera can rotate 360 ​​degrees. After detecting multiple targets, the ball camera can be controlled to rotate to multiple fixed angles for target detection, and the corresponding visual range detection results at multiple fixed angles can be determined. Furthermore, if the number of target detections is large enough, the visual range detection results corresponding to the field of view of the ball camera rotating 360 degrees can be determined.

[0048] The technical solution of the embodiment of the present application is to detect the target through a detection device and determine the detection information of the target; determine the target image collector corresponding to the target, detect the target through the target image collector, and determine the target detection result; determine the visible range detection result of the target image collector according to the detection information of the target and the target detection result, so as to determine a new target image collector corresponding to a new target according to the visible range detection result, and detect the new target. The above scheme can timely and accurately determine the visible range detection result of the target image collector according to the target detection result obtained by detecting the target by the target image collector, so as to determine the target image collector to detect the target according to the visible range detection result in the subsequent detection process, thereby avoiding the problem that the target cannot be detected when the target is in the invisible range of the image collector and the image collector is used for target detection, thereby improving the target detection success rate and detection efficiency.

[0049] Embodiment 2

[0050] Figure 4 This is a flow chart of a target detection method provided in Example 2 of the present application. The present application example is optimized based on the above example. For solutions not described in detail in the present application example, see the above example. Figure 4 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0051] S210: Detect the target by using a detection device, and determine detection information of the target.

[0052] S220: If the target detection result is that the target is detected, determine a critical line segment according to the detection information of the target, and determine a visible range of the target image collector according to the critical line segment.

[0053] Exemplarily, if the target detection result is that the target is detected, it means that the target is within the visible range of the target image collector, and the critical line segment can be determined according to the position and size of the target, and the visible range of the target image collector can be determined according to the critical line segment.

[0054] In an embodiment of the present application, the detection information includes location information and type information of the target;

[0055] Determining a critical line segment according to the detection information of the target includes steps A1-A2:

[0056] A1: Determine the size information of the target according to the type information of the target;

[0057] A2: According to the position information and the size information, determine a critical line segment with the position of the target as the center and the length of the target perpendicular to the center line as the length of the line segment; wherein the center line is the line connecting the target and the target image collector.

[0058] The type information of the target can be detected and determined by the detection device. For example, if the type of the target detected by the detection device is a vehicle, the size information of the target can be determined based on the conventional size of the vehicle, such as 6 meters * 3 meters. If the type of the target detected by the detection device is a person, the size information of the target can be determined based on the conventional height and width of the person, such as 1.7 meters * 0.8 meters.

[0059] The size information of the target can also be directly obtained through detection by the detection device. For example, the detection device emits a scanning detection light and determines the size information of the target based on the range of the light reflected back by the target.

[0060] In the embodiments of the present application, Figure 5 As shown in the figure, a is the center of the target image collector, and b is the center of the target, that is, the position of the target. Connect a and b to get the center line. The length of the target perpendicular to the center line is Figure 5 The length cd of the target in the critical line segment is the length of the target perpendicular to the center line, with the target position as the center. The target can be a target detected by the detection device and detected by the target image collector, or a target detected by the detection device but not detected by the target image collector.

[0061] In an embodiment of the present application, determining the visible range of the target image collector according to the critical line segment includes:

[0062] The closed area formed by the critical line segment, the first straight line and the second straight line is used as the visible range;

[0063] The first straight line is a straight line where the target image collector and one endpoint of the critical line segment are located, and the second straight line is a straight line where the target image collector and the other endpoint of the critical line segment are located.

[0064] For example, the straight line between the target image collector and one end point of the critical line segment can be used as the first straight line, and the straight line between the target image collector and the other end point of the critical line segment can be used as the second straight line. Figure 6The line where ac is located is taken as the first line, and the line where ad is located is taken as the second line. Alternatively, the line where ac is located can be taken as the second line, and the line where ad is located can be taken as the first line. If the target is a target that can be detected by the target image collector, it means that the target is within the visible range of the target image collector, and the closed area formed by the critical line segment, the first line and the second line is taken as the visible range, that is, Figure 6 The range within the triangle acd in is taken as the visible range.

[0065] S230: If the target detection result is that the target is not detected, determine a critical line segment according to the detection information of the target, and determine the invisible range of the target image collector according to the critical line segment.

[0066] For example, if the target detection result is that the target is not detected, but the detection device has detected the target and determined the position of the target, it means that the target is located in the invisible range of the target image collector. The critical line segment can be determined according to the position and size of the target, and the invisible range of the target image collector can be determined according to the critical line segment. The method for determining the critical line segment is shown in the solution in S220.

[0067] In an embodiment of the present application, determining the invisible range of the target image collector according to the critical line segment includes:

[0068] The closed area formed by the critical line segment, the first straight line, the second straight line and the edge line of the field of view of the target image collector is used as the invisible range; wherein the first straight line is the straight line where the target image collector and one endpoint of the critical line segment are located, and the second straight line is the straight line where the target image collector and the other endpoint of the critical line segment are located.

[0069] For example, Figure 6 As shown in FIG. 1 , if the target is a target that is not detected by the target image collector, the critical line segment, the first straight line, and the second straight line can be determined by the same scheme as described above. The edge line of the field of view range is the edge line formed by the farthest position that can be captured during the rotation of the image collector. Similarly, Figure 6 The line where ac is located is taken as the first line, and the line where ad is located is taken as the second line. Alternatively, the line where ac is located is taken as the second line, and the line where ad is located is taken as the first line. The closed area formed by the critical line segment, the first line, the second line, and the edge line of the field of view is taken as the invisible range, such as Figure 6 The closed area cdfe formed by the line segment cd, line segment ce, line segment df and arc ef is used as the invisible range.

[0070] After determining the visible range and invisible range according to the above scheme, the visible range and invisible range of the target image collector can be determined as shown in the following figure: Figure 7 As shown, the area within the edge line of the field of view except the visible range and the invisible range can be an area with an uncertain visible range.

[0071] In an embodiment of the present application, when recording the visible range detection result of the target image collector, it can be recorded according to the critical line segment used to distinguish the visible range from the invisible range. For example, the visible range detection result is recorded as the visible range detection result of the target image collector A = {visible range, invisible range}, visible range = {{point1-1, point1-2},…, {pointx-1, pointx-2,…, pointx-r}}, invisible range = {{point1-x1, point1-x2},…, {pointx-x1, pointx-x2,…, pointx-r}, where pointx-r represents the longitude and latitude of the endpoints of the critical line segment.

[0072] S240. Determine a visible range detection result of the target image collector according to the detection information of the target and the target detection result, determine a new target image collector corresponding to a new target according to the visible range detection result, and detect the new target.

[0073] An embodiment of the present application provides a target detection method. If the target detection result is that the target is detected, a critical line segment is determined according to the detection information of the target, and the visible range of the target image collector is determined according to the critical line segment; if the target detection result is that the target is not detected, a critical line segment is determined according to the detection information of the target, and the invisible range of the target image collector is determined according to the critical line segment. The visible range detection result of the target image collector is determined and updated in real time according to the target detection result, so as to facilitate the subsequent accurate selection of the target image collector to perform precise detection of the target, thereby improving the target detection success rate and detection efficiency.

[0074] In the embodiment of the present application, if there are at least two critical line segments, the method further includes steps B1-B6:

[0075] B1: Sending a scanning ray from the target image collector to scan the critical line segments, and determining whether there are at least two intersection points between the scanning ray and at least two critical line segments;

[0076] B2: If it exists, determine the number of intersections of the same scan ray with at least two critical line segments;

[0077] B3: If the number is one, then the intersection point is taken as the first intersection point;

[0078] B4: If the number is at least two, and at least two critical line segments are determined according to the detected target, the intersection point farthest from the target image collector is used as the second intersection point;

[0079] B5: If the number is at least two, and at least two critical line segments are determined based on undetected targets, the intersection point closest to the target image collector is used as the second intersection point;

[0080] B6: Take the line segment formed by the first intersection points and the line segment formed by the second intersection points as new critical line segments.

[0081] For example, a scanning ray may be emitted from the target image collector to scan the critical line segment, and the angle of the scanning ray may be as small as possible to make the scanning range as large as possible. Determine whether there are at least two intersections between the scanning ray and at least two critical line segments. For example, Figure 8 As shown, a scanning ray is emitted from the target image collector. When the scanning ray intersects with critical line segment 3, the same scanning ray has only one intersection with critical line segment 3. When the scanning ray intersects with critical line segment 1 and critical line segment 2, there is a same scanning ray that has two intersections with critical line segment 1 and critical line segment 2. Then, for all the scanning rays, the number of intersections of the same scanning ray with critical line segment 1 and critical line segment 2 is determined. If there is one intersection, the intersection is taken as the first intersection. If there are at least two intersections, the intersections are selected based on the target determination of the critical line segment. If the critical line segment is determined by the target detected by the target image collector, the intersection farthest from the target image collector is taken as the second intersection, and the line segment formed by all the first intersections and the line segment formed by all the second intersections are taken as new critical line segments. As shown Figure 8 As shown, if critical line segment 1 and critical line segment 2 are both determined by the target detected by the target image collector, the line segments formed by the first intersection points are hi and mn, and the line segment formed by the second intersection point farthest from the target image collector is ij, so the new critical line segment can be determined as hjnm. If the critical line segment is determined by the target not detected by the target image collector, the intersection point closest to the target image collector is taken as the second intersection point, and the line segments formed by all the first intersection points and the line segments formed by all the second intersection points are taken as the new critical line segment. Figure 8 As shown, if both critical line segment 1 and critical line segment 2 are determined by the target detected by the target image collector, the line segments formed by the first intersection are hi and mn, and the line segment formed by the second intersection closest to the target image collector is kn, so the new critical line segment can be determined to be hikm. Through the above scheme, critical line segments that overlap in the field of view of the target image collector can be merged to improve the accuracy of the critical line segments and avoid redundancy and overlap of critical line segments.

[0082] Embodiment 3

[0083] Fig. 9 This is a flow chart of a target detection method provided in Example 2 of the present application. The present application example is optimized based on the above example. For solutions not described in detail in the present application example, see the above example. Fig. 9 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0084] S310: Detect the target through a detection device and determine the detection information of the target.

[0085] S320: Select a preset number of candidate image collectors according to the position information in the detection information and the position information of the image collector to obtain a candidate image collector group.

[0086] Exemplarily, an image collector located near the target can be selected as a candidate image collector based on the position information of the target in the detection information. Specifically, it can be determined whether the position of the image collector is within a preset range centered on the target. If so, the image collector is used as a candidate image collector. In addition, the image collectors can be sorted according to the distance between the image collector and the target, and a preset number of image collectors closest to the target are selected as candidate image collectors. The preset number can be determined according to actual conditions.

[0087] S330: If it is determined according to the position information of the target that the target is located within the invisible range of the candidate image collector, remove the candidate image collector from the group of candidate image collectors.

[0088] Exemplarily, for each candidate image collector, it can be determined according to the position of the target whether the target is located in the invisible range of the candidate image collector. If so, the candidate image collector is removed from the candidate image collector group.

[0089] In the embodiment of the present application, the process of determining whether the position of the target is within the invisible range of the candidate image collector can be as follows: determining whether the intersection of the candidate image collector and the target intersects with the critical line segment of the invisible range. Specifically, assuming that the coordinates of the target are (x1, y1), the coordinates of the candidate image collector are (x2, y2), one endpoint of the critical line segment of the invisible range is (x3, y3), and the other endpoint is (x4, y4).

[0090] deno=(x4–x3)*(y2-y1)-(y4-y3)*(x2-x1);

[0091] mem1=(y3-y1)*(x2-x1)-(x3-x1)*(y2-y1);

[0092] mem2=(y3-y1))*(x4-x3)-(x3-x1)*(y3-y1);

[0093] r = mem1 / deno;

[0094] s = mem2 / deno;

[0095] Among them, || means "or".

[0096] In an embodiment of the present application, if the target is located in an area where the visible range of the candidate image collector is uncertain, that is, the target is neither in the visible range nor in the invisible range, the candidate image collector is retained and not removed, so that the target is detected through the candidate image collector, and the visible range of the candidate image collector is updated according to the target detection result.

[0097] S340, determining the predicted position of the target according to the moving direction of the target, and selecting a target image collector from the candidate image collector group according to the positional relationship between the predicted position and the invisible range of the candidate image collectors in the candidate image collector group.

[0098] Specifically, multiple positions of the target movement and the corresponding time can be determined based on the multiple frames of images collected when the target image collector detects the target, and then the direction and speed of the target movement can be predicted. The position along the moving direction and at a preset distance (for example, 1000 meters) from the current position of the target can be used as the predicted position of the target. According to the positional relationship between the predicted position and the invisible range of the candidate image collector, the target image collector is selected from the candidate image collector group. Exemplarily, the candidate image collectors can be sorted according to the distance between the predicted position and the invisible range, and the order of distance from small to large is used as the priority sorting, and the candidate image collector with a small distance is preferentially selected as the target image collector. The preset distance can be determined according to the actual situation.

[0099] In an embodiment of the present application, selecting a target image collector from the candidate image collector group according to the positional relationship between the predicted position and the invisible range of the candidate image collector in the candidate image collector group includes steps C1-C3:

[0100] C1: if the target does not enter the invisible range during the process of moving from the current position to the predicted position, the candidate image collectors are sorted according to the position information of the candidate image collectors and the position information of the target to obtain a first candidate group;

[0101] C2: Otherwise, for each candidate image collector, determine the time when the target enters the invisible range of the candidate image collector during the process of moving from the current position to the predicted position, and sort the candidate image collectors according to the time to obtain a second candidate group;

[0102] C3: Selecting a target image collector from the first candidate group and the second candidate group according to the ranking.

[0103] Exemplarily, if the target does not enter the invisible range during the process of moving from the current position to the predicted position, the candidate image collector is selected, and the candidate image collectors are sorted according to the position information of the candidate image collector and the position information of the target to obtain the first candidate group, for example, the first candidate group CamArr1 is obtained by sorting them in order of distance from the target from small to large. The number of intersections between the line connecting the current position of the target and the predicted position and the invisible range can be determined to determine whether the target will enter the invisible range during the process of moving from the current position to the predicted position. If the intersection is 0, it is determined that it will not enter the invisible range, otherwise, it is determined that it will enter the invisible range. If the target will enter the invisible range during the process of moving from the current position to the predicted position, the candidate image collector is taken out, and the time from the current position to the time when the target just enters the invisible range of the candidate image collector during the process of moving from the current position to the preset position is determined. The candidate image collectors are sorted according to the time, for example, the candidate image collectors are sorted in order of time from large to small, to obtain the second candidate group CamArr2. There is no duplication of candidate image collectors in CamArr1 and CamArr2. The target image collector is selected from CamArr1 and CamArr2 according to their respective rankings. Among them, it is selected from CamArr1 first, and then from CamArr2. The above scheme can comprehensively consider the visible range of the candidate image collectors, and give priority to selecting the target image collector whose target falls within the visible range, so as to ensure that this part of the image collectors successfully detects the target when the visible range does not change, thereby improving the target detection success rate and detection efficiency. In addition, considering the distance between the target position and the visible range, the target image collector is adaptively selected to give priority to selecting the candidate image collector that is not easy to enter its invisible range as the target image collector to detect the target, thereby improving the target detection success rate and avoiding the situation where the target image collector is selected and the target quickly enters the invisible range as the target moves, resulting in target detection failure.

[0104] In the embodiment of the present application, after determining the target detection result, the method further includes:

[0105] If the target detection result is that the target is not detected, a new target image collector is selected from the first candidate group and the second candidate group according to the sorting, and the process of detecting the target through the new target image collector and determining the visible range detection result is executed.

[0106] If the target detection result is that the target is not detected, the invisible range of the target image collector is updated according to the detection information of the target, and the target image collector is replaced to continue to detect the target. If there is a candidate image collector that has not been selected in the first candidate group, the target image collector is selected from the first candidate group according to the ranking; if there is no candidate image collector that has not been selected in the first candidate group, the target image collector is selected from the second candidate group according to the ranking.

[0107] S350: Detect the target through a target image collector to determine a target detection result.

[0108] S360: Determine the visible range detection result of the target image collector according to the detection information of the target and the target detection result, determine a new target image collector corresponding to the new target according to the visible range detection result, and detect the new target.

[0109] An embodiment of the present application provides a target detection method. If the target does not enter the invisible range during the process of moving from the current position to the predicted position, the candidate image collectors are sorted according to the position information of the candidate image collectors and the position information of the target to obtain a first candidate group; otherwise, for each candidate image collector, the time when the target enters the invisible range of the candidate image collector during the process of moving from the current position to the predicted position is determined, and the candidate image collectors are sorted according to the time to obtain a second candidate group; the target image collector is selected from the first candidate group and the second candidate group according to the sorting, thereby comprehensively considering the positional relationship between the target and the invisible range during the movement process, selecting the target image collector to identify the target, and avoiding the situation where the target recognition fails due to the target moving to the invisible area after the target image collector is selected, thereby improving the target recognition success rate and detection efficiency.

[0110] Embodiment 4

[0111] Fig.10 This is a flow chart of a target detection method provided in Example 4 of the present application. The present application example is optimized based on the above example. For solutions not described in detail in the present application example, see the above example. Fig.10 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0112] S410: Detect the target by using a detection device, and determine the detection information of the target.

[0113] S420: Determine a target image collector corresponding to the target.

[0114] S430: Determine an adjustment angle of the target image collector according to a relative position between the target and the target image collector.

[0115] Exemplarily, the detection device detects the target to determine the position of the target, and can determine the adjustment angle of the target image collector based on the position of the target and the position of the target image collector, so that the target image collector can rotate according to the adjustment angle and the field of view can face the target to detect the target.

[0116] Specifically, assuming that the longitude and latitude of the target are (α1, β1), and the longitude and latitude of the target image collector are (α2, β2), the adjustment angle of the target image collector in the horizontal direction is angel_level = arctan2((Cosα2*Sinα1-Sinα2*Cosα1*Cos(β1-β2)). Assuming that the distance from the target to the target image collector is dis, and the height of the target image collector is H, the pitch angle adjustment angle of the target image collector can be calculated as angel_vertical = arctan(H / dis).

[0117] In the embodiment of the present application, before adjusting the angle of the target image collector, the zero point of the target image collector may be calibrated to determine its orientation when it is rotated 0 degrees.

[0118] S440, according to the size information of the target, magnify the target by a preset multiple to obtain an enlarged target area, and determine the local field of view angle required for the target image collector to capture the enlarged target area.

[0119] S450, determining the magnification of the target image collector according to the global field of view of the target image collector and the preset proportion of the enlarged target area in the image collected by the target image collector.

[0120] For example, in order to improve the display effect of the target in the image collected by the target image collector, to avoid the situation where the target is too small in the image to be viewed, or the situation where the target is too large in the image to be completely contained in the image, the proportion of the target in the image can be preset, for example, the target occupies 1 / 3 of the image, so that the equivalent target area L*D after the target is enlarged can be determined. Assuming that L is the length of the equivalent target area perpendicular to the center line, the theoretical field of view of the target image collector is calculated based on this length. For example, Fig.11As shown, ab is the distance dis from the target to the target image collector, c'd' is the length of the equivalent target area perpendicular to the center line, and the length is L. θ is the local field of view corresponding to the target image collector being able to capture the complete equivalent target area. θ = 2arctan(L / 2dis). Since the proportion of the equivalent target area in the entire image area is a preset ratio, the ratio of the local field of view angle to the theoretical value of the global field of view angle is also a preset ratio, and the theoretical value of the global field of view angle can be determined. The magnification can be calculated based on the current global field of view angle of the target image collector and the theoretical value of the global field of view angle.

[0121] S460: Send the adjustment angle and the magnification to a target image collector, so that the target image collector detects the target after adjusting parameters based on the adjustment angle and the magnification.

[0122] Exemplarily, the adjustment angle and magnification can be sent to the target image collector, so that the target image collector is rotated according to the adjustment angle to make the field of view face the target direction, and the magnification of the target image collector is adjusted according to the magnification to adjust the size of the captured target.

[0123] In an embodiment of the present application, the method further includes:

[0124] If a new target is detected by the detection device, and the target image collector corresponding to the new target is the same as the target image collector corresponding to the previous target, then a new adjustment angle and a new magnification of the target collector are determined;

[0125] If the change angle of the new adjustment angle relative to the previous adjustment angle is greater than the preset angle threshold, the new adjustment angle is sent to the target image collector, so that the target image collector performs parameter adjustment based on the new adjustment angle;

[0126] If the change ratio of the new magnification relative to the previous magnification is greater than the preset magnification threshold, the new magnification is sent to the target image collector so that the target image collector performs parameter adjustment based on the new magnification.

[0127] If a new target is detected by the detection device, and the target image collector corresponding to the new target is the same as the target image collector corresponding to the previous target, the adjustment angle and magnification of the target image collector are recalculated according to S430-S450 to obtain a new adjustment angle and a new magnification. If the change angle of the new adjustment angle relative to the previous adjustment angle is greater than the preset angle threshold, the new adjustment angle is sent to the target image collector so that the target image collector performs parameter adjustment based on the new adjustment angle. If the change angle of the new adjustment angle relative to the previous adjustment angle is less than or equal to the preset angle threshold, it means that the position and size of the new target relative to the previous target are not much changed, and the new target can be detected without adjusting the adjustment angle of the target image collector. In this case, the adjustment angle of the target image collector is not adjusted to reduce the mechanical rotation wear of the target image collector. The previous target is the target detected by the detection device last time, and the previous adjustment angle is the adjustment angle of the target image collector calculated based on the previous target. If the change ratio of the new magnification relative to the previous magnification is greater than the preset magnification threshold, the new magnification is sent to the target image collector so that the target image collector adjusts parameters based on the new magnification. If the change ratio of the new magnification relative to the previous magnification is less than or equal to the preset magnification threshold, it means that the position and size of the new target relative to the previous target are not much changed, and the new target can be detected without adjusting the magnification of the target image collector. In this case, the magnification of the target image collector is not adjusted to reduce the mechanical rotation wear of the target image collector. The previous magnification is the magnification of the target image collector calculated based on the previous target.

[0128] S470. Determine a visible range detection result of the target image collector according to the detection information of the target and the target detection result, determine a new target image collector corresponding to a new target according to the visible range detection result, and detect the new target.

[0129] The embodiment of the present application provides a target detection method, which determines the adjustment angle of the target image collector according to the relative position of the target and the target image collector; according to the size information of the target, the target is magnified by a preset multiple to obtain the enlarged target area, and the local field of view angle required for the target image collector to collect the enlarged target area is determined; according to the global field of view angle of the target image collector and the preset proportion of the enlarged target area in the image collected by the target image collector, the magnification of the target image collector is determined; the adjustment angle and the magnification are sent to the target image collector, so that the target image collector detects the target after adjusting the parameters based on the adjustment angle and the magnification, thereby getting rid of the problem of limited target detection angle caused by the one-to-one binding of the detection device and the target image collector, and releasing the binding relationship, by adaptively selecting the target image collector and calculating the adjustment angle and magnification, controlling the target image collector to adjust, so that the target image collector is rotated to a position where the field of view faces the target, and the magnification that can clearly view the target is enlarged, thereby improving the target detection efficiency and the detection success rate.

[0130] Embodiment 5

[0131] Fig.12 This is a schematic diagram of the structure of a target detection device provided in Embodiment 5 of the present application. The device can execute the target detection method provided in any embodiment of the present application and has the corresponding functional modules and beneficial effects of the execution method. Fig.12 As shown, the device comprises:

[0132] The detection module 510 is used to detect the target through the detection device and determine the detection information of the target;

[0133] A target detection module 520 is used to determine a target image collector corresponding to the target, detect the target through the target image collector, and determine a target detection result;

[0134] The visible range detection module 530 is used to determine the visible range detection result of the target image collector according to the detection information of the target and the target detection result, so as to determine a new target image collector corresponding to a new target according to the visible range detection result and detect the new target.

[0135] In the embodiment of the present application, the visual range detection module 530 includes:

[0136] A visual range determination unit, configured to determine a critical line segment according to detection information of the target if the target detection result is that the target is detected, and determine a visual range of the target image collector according to the critical line segment;

[0137] The invisible range determining unit is used to determine a critical line segment according to the detection information of the target if the target detection result is that the target is not detected, and determine the invisible range of the target image collector according to the critical line segment.

[0138] In an embodiment of the present application, the detection information includes location information and type information of the target;

[0139] The visual range detection module 530 includes:

[0140] A size information determining unit, configured to determine the size information of the target according to the type information of the target;

[0141] A critical line segment determination unit is used to determine a critical line segment with the position of the target as the center and the length of the target perpendicular to the center line as the line segment length based on the position information and the size information; wherein the center line is the line connecting the target and the target image collector.

[0142] In the embodiment of the present application, the visual range determination unit is specifically used to:

[0143] The closed area formed by the critical line segment, the first straight line and the second straight line is used as the visible range;

[0144] The invisible range determination unit is specifically used for:

[0145] The closed area formed by the critical line segment, the first straight line, the second straight line and the edge line of the field of view of the target image collector is used as the invisible range;

[0146] The first straight line is a straight line where the target image collector and one endpoint of the critical line segment are located, and the second straight line is a straight line where the target image collector and the other endpoint of the critical line segment are located.

[0147] In the embodiment of the present application, if there are at least two critical line segments, the device further includes:

[0148] A scanning module, used for emitting a scanning ray from a target image collector to scan the critical line segments, and determining whether there are at least two intersection points between the scanning ray and at least two critical line segments;

[0149] a quantity determination module, for determining the number of intersections of the same scanning ray with at least two critical line segments, if any;

[0150] A first intersection point determination module, configured to take the intersection point as the first intersection point if the number is one;

[0151] A second intersection determination module, configured to, if the number is at least two and at least two critical line segments are determined based on the detected target, use the intersection farthest from the target image collector as the second intersection; if the number is at least two and at least two critical line segments are determined based on the undetected target, use the intersection closest to the target image collector as the second intersection;

[0152] A new critical line segment determination module is used to take the line segment formed by the first intersection points and the line segment formed by the second intersection points as new critical line segments.

[0153] In the embodiment of the present application, the target detection module 520 includes:

[0154] A candidate image collector group determination unit, configured to select a preset number of candidate image collectors according to the position information in the detection information and the position information of the image collectors to obtain a candidate image collector group;

[0155] a screening unit, configured to remove the candidate image collector from the group of candidate image collectors if it is determined according to the position information of the target that the target is located within the invisible range of the candidate image collector;

[0156] A selection unit is used to determine the predicted position of the target according to the moving direction of the target, and select a target image collector from the candidate image collector group according to the positional relationship between the predicted position and the invisible range of the candidate image collectors in the candidate image collector group.

[0157] In the embodiment of the present application, the selection unit includes:

[0158] A first candidate group determination subunit is configured to sort the candidate image collectors according to the position information of the candidate image collectors and the position information of the target to obtain a first candidate group if the target does not enter the invisible range during the process of moving from the current position to the predicted position;

[0159] A second candidate group determination subunit is used for otherwise, for each candidate image collector, determining the time when the target enters the invisible range of the candidate image collector during the process of moving from the current position to the predicted position, and sorting the candidate image collectors according to the time to obtain a second candidate group;

[0160] The target image collector determining subunit is used to select a target image collector from the first candidate group and the second candidate group according to the ranking.

[0161] In the embodiment of the present application, the device further includes:

[0162] A selection module is used to select a new target image collector from the first candidate group and the second candidate group according to the sorting if the target detection result is that the target is not detected, and execute the process of detecting the target through the new target image collector and determining the visible range detection result.

[0163] In the embodiment of the present application, the device further includes:

[0164] An adjustment angle determination module, used to determine the adjustment angle of the target image collector according to the relative position between the target and the target image collector;

[0165] A local field of view angle determination module is used to magnify the target by a preset multiple according to the size information of the target, obtain an enlarged target area, and determine the local field of view angle required for the target image collector to capture the enlarged target area;

[0166] A magnification determination module, used to determine the magnification of the target image collector according to the global field of view of the target image collector and the preset proportion of the enlarged target area in the image collected by the target image collector;

[0167] The sending module is used to send the adjustment angle and the magnification to the target image collector, so that the target image collector detects the target after adjusting parameters based on the adjustment angle and the magnification.

[0168] In the embodiment of the present application, the device further includes:

[0169] An updating module, for determining a new adjustment angle and a new magnification of the target collector if a new target is detected by the detection device and the target image collector corresponding to the new target is the same as the target image collector corresponding to the previous target;

[0170] A first comparison module is used to send the new adjustment angle to the target image collector if the change angle of the new adjustment angle relative to the previous adjustment angle is greater than a preset angle threshold, so that the target image collector performs parameter adjustment based on the new adjustment angle;

[0171] The second comparison module is used to send the new magnification to the target image collector if the change magnification of the new magnification relative to the previous magnification is greater than a preset magnification threshold, so that the target image collector adjusts parameters based on the new magnification.

[0172] A target detection device provided in an embodiment of the present application can execute a target detection method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0173] Embodiment 6

[0174] Fig.13 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, 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 processing, cellular phones, smart phones, 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 examples and are not intended to limit the implementation of the present application described and / or required herein.

[0175] like Fig.13 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0176] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0177] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a target detection method.

[0178] In some embodiments, the target detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the target detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the target detection method in any other appropriate manner (e.g., by means of firmware).

[0179] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0180] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable target detection device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0181] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0182] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0183] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0184] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0185] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the information expected by the technical solution of this application can be achieved, and this document is not limited here.

[0186] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art 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 in the protection scope of this application.

Claims

1. A target detection method, characterized in that: The method comprises: Detecting the target through the detection device and determining the detection information of the target; Determine a target image collector corresponding to the target, detect the target through the target image collector, and determine a target detection result; According to the detection information of the target and the target detection result, the visual range detection result of the target image collector is determined, so as to determine a new target image collector corresponding to a new target according to the visual range detection result, and detect the new target.

2. The method according to claim 1, characterized in that Determining the visual range detection result of the target image collector according to the detection information of the target and the target detection result, including: If the target detection result is that the target is detected, determining a critical line segment according to the detection information of the target, and determining a visible range of the target image collector according to the critical line segment; If the target detection result is that the target is not detected, a critical line segment is determined according to the detection information of the target, and an invisible range of the target image collector is determined according to the critical line segment.

3. The method according to claim 2, characterized in that The detection information includes location information and type information of the target; Determining a critical line segment according to the detection information of the target includes: Determine the size information of the target according to the type information of the target; According to the position information and the size information, a critical line segment is determined with the position of the target as the center and the length of the target perpendicular to the center line as the line segment length; wherein the center line is the line connecting the target and the target image collector.

4. The method according to claim 2 or 3, characterized in that: Determining the visible range of the target image collector according to the critical line segment includes: The closed area formed by the critical line segment, the first straight line and the second straight line is used as the visible range; Determining the invisible range of the target image collector according to the critical line segment includes: The closed area formed by the critical line segment, the first straight line, the second straight line and the edge line of the field of view of the target image collector is used as the invisible range; The first straight line is a straight line where the target image collector and one endpoint of the critical line segment are located, and the second straight line is a straight line where the target image collector and the other endpoint of the critical line segment are located.

5. The method according to claim 1, characterized in that If there are at least two critical line segments, the method further includes: Sending a scanning ray from the target image collector to scan the critical line segments, and determining whether there are at least two intersection points between the scanning ray and at least two critical line segments; If so, determine the number of intersections of the same scan ray with at least two critical line segments; If the number is one, then the intersection point is taken as the first intersection point; If the number is at least two, and at least two critical line segments are determined based on the detected target, the intersection point farthest from the target image collector is used as the second intersection point; If the number is at least two, and at least two critical line segments are determined based on undetected targets, the intersection point closest to the target image collector is used as the second intersection point; The line segment formed by the first intersection points and the line segment formed by the second intersection points are used as new critical line segments.

6. The method according to claim 1, characterized in that Determining a target image collector corresponding to the target includes: According to the position information in the detection information and the position information of the image collector, a preset number of candidate image collectors are selected to obtain a candidate image collector group; If it is determined according to the position information of the target that the target is located within the invisible range of the candidate image collector, then removing the candidate image collector from the candidate image collector group; The predicted position of the target is determined according to the moving direction of the target, and the target image collector is selected from the candidate image collector group according to the positional relationship between the predicted position and the invisible range of the candidate image collectors in the candidate image collector group.

7. The method according to claim 6, characterized in that According to the positional relationship between the predicted position and the invisible range of the candidate image collectors in the candidate image collector group, selecting a target image collector from the candidate image collector group includes: If the target does not enter the invisible range during the process of moving from the current position to the predicted position, the candidate image collectors are sorted according to the position information of the candidate image collectors and the position information of the target to obtain a first candidate group; Otherwise, for each candidate image collector, determine the time when the target enters the invisible range of the candidate image collector during the process of moving from the current position to the predicted position, and sort the candidate image collectors according to the time to obtain a second candidate group; A target image collector is selected from the first candidate group and the second candidate group according to the ranking.

8. The method according to claim 7, characterized in that After determining the target detection result, the method further includes: If the target detection result is that the target is not detected, a new target image collector is selected from the first candidate group and the second candidate group according to the sorting, and the process of detecting the target through the new target image collector and determining the visible range detection result is executed.

9. The method according to claim 1, characterized in that: After determining the target image collector corresponding to the target, the method further includes: Determining an adjustment angle of the target image collector according to a relative position between the target and the target image collector; According to the size information of the target, the target is magnified by a preset multiple to obtain an enlarged target area, and the local field of view angle required for the target image collector to capture the enlarged target area is determined; Determine the magnification of the target image collector according to the global field of view of the target image collector and the preset proportion of the enlarged target area in the image collected by the target image collector; The adjustment angle and the magnification are sent to a target image collector, so that the target image collector detects the target after performing parameter adjustment based on the adjustment angle and the magnification.

10. The method according to claim 9, characterized in that The method further comprises: If a new target is detected by the detection device, and the target image collector corresponding to the new target is the same as the target image collector corresponding to the previous target, then a new adjustment angle and a new magnification of the target collector are determined; If the change angle of the new adjustment angle relative to the previous adjustment angle is greater than the preset angle threshold, the new adjustment angle is sent to the target image collector, so that the target image collector performs parameter adjustment based on the new adjustment angle; If the change ratio of the new magnification relative to the previous magnification is greater than the preset magnification threshold, the new magnification is sent to the target image collector so that the target image collector performs parameter adjustment based on the new magnification.

11. A target detection device, characterized in that: The device comprises: A detection module, used to detect a target through a detection device and determine the detection information of the target; A target detection module is used to determine a target image collector corresponding to the target, detect the target through the target image collector, and determine a target detection result; The visual range detection module is used to determine the visual range detection result of the target image collector according to the detection information of the target and the target detection result, so as to determine a new target image collector corresponding to a new target according to the visual range detection result and detect the new target.

12. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the target detection method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the target detection method according to any one of claims 1 to 10 when executed.

Citation Information

Cited By

  • Target tracking method and device, equipment and storage medium

    CN119728927A