Target identification method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a target identification method and device, electronic equipment and a medium. The method comprises the following steps: performing target detection on the internal space of the carrying equipment through a main image collector in an image collector association group, and determining a candidate target; wherein the image collector association group comprises a main image collector in the internal space of the carrying equipment and an auxiliary image collector in an area communicated with the carrying equipment; performing tracking detection on the candidate target through the main image collector and / or the auxiliary image collector, and determining motion information of the candidate target; and determining an identification result of the candidate target according to the working state of the carrying equipment and the motion information of the candidate target. According to the scheme, cooperative detection can be carried out through the image collectors in the image collector association group in different working states of the carrying equipment, and the accuracy of target recognition is improved.

Description

Technical Field

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

[0002] Currently, image collectors are widely used in daily life. For example, image collectors are set up in scenes such as roads, communities, and office buildings to monitor the above scenes and detect and identify targets appearing in the above scenes.

[0003] Typically, vehicles are equipped with advertising spaces that display static or dynamic advertising images. These images may contain flat objects, such as faces. The image collector in the vehicle may mistakenly identify these flat objects as real physical objects, affecting the accuracy of security system detection. Summary of the Invention

[0004] The embodiments of the present application provide a target recognition method, device, electronic device, and medium to improve the accuracy of target recognition and accurately distinguish between flat screen targets and real moving targets.

[0005] According to one aspect of the present application, a target recognition method is provided, the method comprising:

[0006] Performing target detection on the interior space of the carrier using a primary image collector in an image collector association group to determine candidate targets; wherein the image collector association group includes the primary image collector in the interior space of the carrier and auxiliary image collectors in an area connected to the carrier;

[0007] Tracking and detecting the candidate target by the main image collector and / or the auxiliary image collector to determine motion information of the candidate target;

[0008] The recognition result of the candidate target is determined according to the working state of the carrier and the motion information of the candidate target.

[0009] According to one aspect of the present application, a target recognition device is provided, the device comprising:

[0010] a candidate target determination module, configured to perform target detection in the interior space of the vehicle using a primary image collector in an associated group of image collectors to determine candidate targets; wherein the associated group of image collectors includes the primary image collector in the interior space of the vehicle and auxiliary image collectors in an area connected to the vehicle;

[0011] a motion information determination module, configured to track and detect the candidate target through the main image collector and / or the auxiliary image collector to determine the motion information of the candidate target;

[0012] The recognition result determination module is used to determine the recognition result of the candidate target according to the working status of the carrier and the motion information of the candidate target.

[0013] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] A memory connected to at least one processor for data processing; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the target recognition method of any embodiment of the present application.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the target recognition method of any embodiment of the present application when executed.

[0018] The technical solution of the embodiment of the present application is to detect targets in the internal space of the carrier equipment through the main image collector in the image collector association group to determine candidate targets; wherein, the image collector association group includes the main image collector in the internal space of the carrier equipment, and the auxiliary image collector in the area connected to the carrier equipment; the candidate targets are tracked and detected by the main image collector and / or the auxiliary image collector to determine the motion information of the candidate targets; and the recognition result of the candidate targets is determined according to the working state of the carrier equipment and the motion information of the candidate targets. The above solution can perform collaborative detection through the image collectors in the image collector association group under different working states of the carrier equipment, accurately distinguish between real moving targets and plane screen targets appearing in the carrier equipment, and improve the accuracy of target recognition.

[0019] 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

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.

[0021] Figure 1 A flowchart of a target recognition method provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of an image collector association group provided in an embodiment of the present application;

[0023] Figure 3 A flowchart of a target recognition method provided in another embodiment of the present application;

[0024] Figure 4 A flowchart of a target recognition method provided in another embodiment of the present application;

[0025] Figure 5 A schematic diagram of the structure of a target recognition device provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0028] 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 variations thereof 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 clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Figure 1 This is a flow chart of a target recognition method provided by an embodiment of the present application. The embodiment of the present application is applicable to the case of identifying targets in a transport device. Typically, the embodiment of the present application is applicable to the case of distinguishing and identifying real moving targets appearing in a transport device and flat screen targets in an advertising space. The method can be executed by a target recognition device, which can be implemented in the form of hardware and / or software, and the target recognition device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110. Perform target detection on the interior space of the carrier through the main image collector in the image collector association group to determine candidate targets; wherein the image collector association group includes the main image collector in the interior space of the carrier and auxiliary image collectors in an area connected to the carrier.

[0031] The image collector association group includes at least two image collectors, at least one of which is located in the carrier as a main image collector and is used to detect targets appearing in the internal space of the carrier. At least one image collector is located in an area connected to the carrier as an auxiliary image collector and is used to detect targets that exit the carrier and enter the area connected to the carrier. The carrier can be a device that can carry targets and has an internal space where advertising spaces can be set up for displaying advertising images, such as an elevator, subway, bus, etc. Candidate targets can be determined based on actual conditions, for example, they can be set as people, and target detection can be the detection of human faces.

[0032] For example, Figure 2 As shown, assuming that the transport device is an elevator and the area connected to the transport device is a corridor, elevator M includes IPC1, elevator N includes IPC2, and the corridor includes IPC3 and IPC4. The corridor is the area connected to elevator M. Targets in elevator M can be detected by IPC1, and targets leaving elevator M can be detected by IPC3 and IPC4. Therefore, IPC1, IPC3, and IPC4 can be used as an image collector association group to collaboratively detect targets inside and outside elevator M. Similarly, IPC2 in elevator N and IPC3 and IPC4 in the corridor can be used as an image collector association group to collaboratively detect targets inside and outside elevator N. Different image collector association groups can include the same image collector. Independent image collectors in two transport devices are not considered as an image collector association group.

[0033] In the embodiments of this application, the vehicle interior typically includes advertising spaces for displaying advertisements, which can cause the image collector within the vehicle to mistakenly identify flat objects within the displayed advertisements as real moving objects. Therefore, the primary image collector within the vehicle first performs object recognition within the vehicle interior, identifying the detected objects as candidate targets.

[0034] S120: Track and detect the candidate target by the main image collector and / or the auxiliary image collector to determine motion information of the candidate target.

[0035] Exemplarily, the candidate target may be a moving target, which may move from the carrier to an area connected to the carrier. In different operating states, different image collectors may be used to detect the candidate target. Therefore, the candidate target may be tracked and detected by the main image collector and / or the auxiliary image collector, and the candidate targets in different positions and different motion states may be tracked and detected more comprehensively to determine the motion information of the candidate target.

[0036] Specifically, when the vehicle's access is closed and the vehicle is out of service, the primary image collector within the vehicle can be used to track and detect candidate targets. When the vehicle is in operation, the primary and auxiliary image collectors can be used to track and detect candidate targets. When the vehicle's access is closed, the auxiliary image collector can be used to track and detect candidate targets that have left the vehicle and entered a connected area. The tracking and detection points can be determined based on actual conditions, for example, representative facial areas such as the center of the target's eyebrows, eyes, and lips.

[0037] S130: Determine the recognition result of the candidate target according to the working state of the carrier and the motion information of the candidate target.

[0038] The operating state can include an inoperative state and an operational state. The motion information of the candidate target within the vehicle varies depending on the vehicle's operating state. For example, when the vehicle is in an inoperative state, the candidate target primarily moves within the vehicle. While the vehicle is in operation, the candidate target may initially move within the vehicle and then leave the vehicle to move to an area connected to the vehicle. Under different vehicle operating states, the candidate target recognition result can be adaptively determined based on the candidate target's motion information, distinguishing whether the candidate target within the vehicle is a flat image target or a real moving target.

[0039] The technical solution of the embodiment of the present application is to detect targets in the internal space of the carrier equipment through the main image collector in the image collector association group to determine candidate targets; wherein, the image collector association group includes the main image collector in the internal space of the carrier equipment, and the auxiliary image collector in the area connected to the carrier equipment; the candidate targets are tracked and detected by the main image collector and / or the auxiliary image collector to determine the motion information of the candidate targets; and the recognition result of the candidate targets is determined according to the working state of the carrier equipment and the motion information of the candidate targets. The above solution can perform collaborative detection through the image collectors in the image collector association group under different working states of the carrier equipment, accurately distinguish between real moving targets and plane screen targets appearing in the carrier equipment, and improve the accuracy of target recognition.

[0040] Figure 3 This is a flow chart of a target recognition method provided by another embodiment of the present application. The present embodiment is optimized based on the above embodiment. For solutions not fully described in the present embodiment, please refer to the above embodiment. Figure 3 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0041] S210. Perform target detection on the interior space of the carrier through a main image collector in an image collector association group to determine candidate targets; wherein the image collector association group includes the main image collector in the interior space of the carrier and auxiliary image collectors in an area connected to the carrier.

[0042] S220: Track and detect the candidate target by the main image collector and / or the auxiliary image collector to determine motion information of the candidate target.

[0043] S230: If the transport equipment is in a stopped state, obtain the position and motion position deviation of the candidate target detected by the main image collector.

[0044] For example, if the transport equipment is in a stopped state, that is, the transport equipment is not moving and is not opening or closing doors, under normal circumstances, there is no real moving target in the transport equipment, and the main image collector cannot detect the candidate target. However, in this case, if the main image collector detects a candidate target, the candidate target may be a flat screen target displayed on an advertising space, or the candidate target is a real moving target, but after entering the transport equipment, it did not trigger the operation switch of the transport equipment. For example, the candidate target forgot to press the button in the elevator while looking at the phone, or a child did not know how to operate the elevator button after entering the elevator, resulting in the elevator not running. In this case, the candidate target is in the internal space of the transport equipment, so the position of the candidate target and the motion position deviation can be detected by the main image collector.

[0045] S240: Determine a recognition result of the candidate target according to the position and motion position deviation of the candidate target.

[0046] For example, if a candidate target is a flat screen object, its position should be within a pre-set advertising spot, with minimal deviation. If a candidate target is a real moving target, its position should move outside the advertising spot, with significant deviation. When the vehicle is stopped, the candidate target's position within the vehicle and its deviation can be used to determine the candidate target's recognition result, distinguishing whether it is a flat screen object or a real moving target.

[0047] In an embodiment of the present application, determining the recognition result of the candidate target according to the position and motion position deviation of the candidate target includes:

[0048] If the number of times that the movement position deviation of the candidate target is continuously detected to exceed the preset deviation exceeds the preset number, and the position of the candidate target is not located in the preset area, then the candidate target is determined to be a real moving target;

[0049] If the number of times that the movement position deviation of the candidate target is continuously detected to exceed the preset deviation does not exceed the preset number, and the position of the candidate target is not located in the preset area, prompting the user to confirm the recognition result of the candidate target;

[0050] If it is continuously detected that the movement position deviation of the candidate target does not exceed the preset deviation for more than a preset number of times, and the position of the candidate target is located in a preset area, then the candidate target is determined to be a plane screen target;

[0051] Otherwise, the candidate target is matched with the plane screen target in the preset area to determine the recognition result of the candidate target.

[0052] The preset deviation and the preset number of detections can be determined based on actual conditions. For example, the preset deviation can be set to 20%, 5%, etc., and the preset number of detections can be set to 60% of the total number of detections within the detection cycle. The deviation between the two positions of the candidate target during its motion is calculated to determine the motion position deviation, for example, the ratio of the difference between the position after the motion and the position before the motion, to the entire field of view of the main image collector. The motion position deviation of the candidate target is determined. If the motion position deviation exceeds the preset deviation, and the candidate target is detected to be in continuous motion, and the motion position deviation exceeds the preset deviation more than a preset number of times, it indicates that the candidate target has a large amplitude of motion. If the motion position deviation of the candidate target meets the above conditions and the candidate target is not located in the preset area, that is, not in the advertising space, the candidate target is determined to be a real moving target. If the candidate target is not located in the preset area, and the number of consecutive detections of the candidate target's motion position deviation does not exceed the preset number, the candidate target cannot be determined to be a real moving target, nor can the candidate target be determined to be a flat screen target. A prompt message is sent to the user, prompting the user to confirm the recognition result of the candidate target. If the motion position deviations of the candidate targets detected continuously do not reach the preset deviation, this is regarded as a result of the existence of a detection error and is not used as a reference for candidate target identification.

[0053] For example, if the candidate target is located in a preset area, that is, in an advertising space, and the candidate target's motion is continuously detected, but the motion position deviation does not exceed the preset deviation more than a preset number of times, it means that the candidate target's motion amplitude is small and has been moving in the preset area. In this case, the candidate target is determined to be a flat screen target and not a real moving target. If the above conditions are not met, the candidate target can be matched with a flat screen target in the preset area. If the match is successful, for example, the similarity reaches a preset similarity, the candidate target is determined to be a flat screen target. Specifically, the advertising screens that can be displayed in the advertising space are generally fixed, displaying only one screen or displaying multiple screens in a loop. Therefore, the flat screen target in the advertising screen is also fixed and can be determined. In addition, in the above scheme, if the candidate target is determined to be a flat screen target, the flat screen target is stored in the database to facilitate subsequent matching. The candidate target detected in the carrier can be matched with the flat screen target to determine whether the candidate target is a flat screen target.

[0054] In the embodiment of the present application, determining that the candidate target is a plane screen target includes:

[0055] Increase the detection frequency of the main image collector to detect the position and motion position deviation of the candidate target;

[0056] If the position and motion position deviation of the candidate target still do not meet the preset conditions, the candidate target is determined to be a plane screen target.

[0057] Exemplarily, in the above implementation, if the candidate target's motion position deviation is continuously detected to be less than a preset deviation for more than a preset number of times, and the candidate target's position is located in a preset area, the candidate target is determined to be a two-dimensional screen target. In an embodiment of the present application, the conditions for determining that a candidate target is a two-dimensional screen target are further limited. Specifically, if the candidate target's motion position deviation is continuously detected to be less than a preset deviation for more than a preset number of times, and the candidate target's position is located in a preset area, the main image collector increases the detection frequency to detect the candidate target's position and motion position deviation, for example, from once every 6 seconds to once every 3 seconds, thereby detecting the candidate target in a more fine-grained manner and improving detection accuracy. If the detected position and motion position deviation of the candidate target still do not meet the preset conditions after increasing the detection frequency, the candidate target is determined to be a two-dimensional screen target. For example, if the candidate target's position is still located in the preset area, and the candidate target's motion position deviation does not exceed the preset deviation for more than a preset number of times, the candidate target is determined to be a two-dimensional screen target. By increasing the detection frequency, detection is further refined, thereby improving the accuracy of candidate target detection and avoiding misidentification.

[0058] In an embodiment of the present application, after determining the recognition result of the candidate target based on the position and motion position deviation of the candidate target, the method further includes:

[0059] If it is determined that the candidate target is a plane screen target, detecting whether there are other candidate targets entering the carrier by the auxiliary image collector;

[0060] If so, and the main image collector detects that the other candidate targets have entered the carrier, matching the other candidate targets detected by the main image collector with the other candidate targets detected by the auxiliary image collector;

[0061] If the match is successful, the other candidate targets are determined to be real moving targets.

[0062] Exemplarily, if it is determined that the candidate target in the carrier is a flat screen target, it can be determined that there is no real moving target in the current carrier. At this time, if it is determined based on the image collector association group detection that there are other candidate targets entering the carrier, it means that the other candidate targets are real moving targets. Specifically, the auxiliary image collector is used to detect whether there are other candidate targets entering the carrier. If so, the main image collector is used to detect whether there are other candidate targets entering the carrier, and the other candidate targets entering the carrier detected by the main image collector and the other candidate targets entering the carrier detected by the auxiliary image collector are matched to determine whether they are the same target. If so, it is determined that the other candidate targets entering the carrier are real moving targets. The beneficial effect of the above scheme is that, when the candidate target is determined to be a flat screen target, the main image collector and the auxiliary image collector can be used to quickly and accurately determine whether the other candidate targets entering the carrier are real moving targets through the collaborative detection, thereby improving the real-time and accuracy of target recognition.

[0063] An embodiment of the present application provides a target recognition method. If the transport device is in an outage state, the position and motion position deviation of the candidate target detected by the main image collector are obtained; and the recognition result of the candidate target is determined based on the position and motion position deviation of the candidate target. The above scheme can accurately judge the motion information of the candidate target based on the position and motion position deviation of the candidate target in the internal space of the transport device, and then accurately distinguish whether the candidate target is a flat screen target or a real moving target, avoiding the misidentification of a flat screen target in an advertising space as a real moving target, thereby improving the accuracy of target recognition.

[0064] Figure 4 This is a flow chart of a target recognition method provided by another embodiment of the present application. The present embodiment is optimized based on the above embodiment. For solutions not fully described in the present embodiment, please refer to the above embodiment. Figure 4 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0065] S310. Perform target detection on the interior space of the carrier through the main image collector in the image collector association group to determine candidate targets; wherein the image collector association group includes the main image collector in the interior space of the carrier and the auxiliary image collectors in the area connected to the carrier.

[0066] S320: Track and detect the candidate target through the main image collector and / or the auxiliary image collector to determine motion information of the candidate target.

[0067] S330: If the transport device is in operation and it is detected that the entrance or exit of the transport device is open, the movement information of the candidate target within the transport device is acquired through the main image collector, and the movement information of the candidate target in the area connected to the transport device is acquired through the auxiliary image collector.

[0068] For example, the operating state can be when the vehicle is in motion or has its doors open. The primary image collector within the vehicle can detect the vehicle's operating state and whether its entrances and exits are open. If the vehicle is in operation and its entrances and exits are detected to be open, the primary image collector acquires information about the candidate target's movement within the vehicle, while the auxiliary image collector acquires information about the candidate target's movement outside the vehicle. This combined information about the candidate target's movement inside and outside the vehicle can then be used to determine the candidate target's overall movement range.

[0069] In an embodiment of the present application, the primary image collector and the auxiliary image collector can continuously detect candidate targets and, after determining that the vehicle is in operation, adaptively acquire the required motion information. Alternatively, the primary image collector can first detect candidate targets within the vehicle. If the primary image collector detects that the vehicle's entrance or exit is open and the candidate target has left the vehicle, it sends a notification message to the auxiliary image collector, notifying the auxiliary image collector that the candidate target has left the vehicle, causing the auxiliary image collector to detect candidate targets that have left the vehicle and entered its field of view.

[0070] S340: If it is determined according to the motion information that the candidate target leaves the vehicle and the candidate target enters an area connected to the vehicle, then the candidate target is determined to be a real moving target.

[0071] For example, if the motion information detected by the main image collector determines that the candidate target leaves the carrier, and the motion information detected by the auxiliary image collector determines that the candidate target enters an area connected to the carrier, that is, outside the carrier, then it is determined that the candidate target has moved from the inside of the carrier to the outside, and the candidate target is not a flat screen target, but a real moving target.

[0072] In the embodiment of the present application, determining that the candidate target is a real moving target includes:

[0073] Matching candidate targets detected by the primary image collector and leaving the vehicle with candidate targets detected by the auxiliary image collector and entering a communication area with the vehicle;

[0074] If the match is successful, it is determined that the candidate targets are the same real moving target.

[0075] Exemplarily, in order to further determine that the candidate target leaving the carrier detected by the main image collector and the candidate target entering the communication area of ​​the carrier detected by the auxiliary image collector are the same target, the two candidate targets can be matched. If the match is successful, it is determined that the candidate target detected by the main image collector and the candidate target detected by the auxiliary image collector are the same candidate target, and it is further determined that the candidate target leaving the carrier is the candidate target entering the communication area of ​​the carrier, and the candidate target is determined to be a real moving target.

[0076] In the embodiment of the present application, determining the recognition result of the candidate target according to the working state of the carrier and the motion information of the candidate target includes:

[0077] If the carrier is in operation and the entrance or exit of the carrier is detected to be open, the auxiliary image collector is used to obtain movement information of the candidate target in the area connected to the carrier;

[0078] If it is determined based on the motion information that the candidate target enters the area connected to the carrier, matching the candidate target detected by the auxiliary image collector with the candidate target detected by the main image collector;

[0079] The successfully matched candidate targets are regarded as the same real moving target.

[0080] Exemplarily, if the main image collector detects that the transport equipment is in operation and the entrance and exit are open, the auxiliary image collector can be notified to perform tracking detection to determine the motion information. If it is determined through the motion information that the candidate target has entered the area connected to the transport equipment, the candidate target detected by the auxiliary image collector is matched with the candidate target detected by the main image collector in the transport equipment to determine which candidate target has entered the area connected to the transport equipment. The successfully matched candidate target is regarded as the same real moving target, and the other candidate targets detected by the main image collector continue to be identified according to the above scheme. It should be noted that the candidate target detected by the main image collector that needs to be matched is the candidate target detected by the main image collector before the entrance and exit of the transport equipment are opened, that is, the candidate target in S310.

[0081] Specifically, when there are at least two candidate targets detected by the main image collector, the candidate target detected by the auxiliary image collector can be matched with the candidate target detected by the main image collector to determine which candidate target the auxiliary image collector is. The candidate target detected by the main image collector that matches the candidate target detected by the auxiliary image collector is determined to be a real moving target, and the other candidate targets are still identified according to the above scheme. For example, the main image collector detects candidate targets P1, P2, and P3, and the auxiliary image collector detects candidate target Q1. Q1 is compared with P1, P2, and P3 respectively. If the similarity between Q1 and P2 reaches a preset similarity, Q1 is determined to be the same candidate target as P2, and the candidate target is determined to be a real moving target. P1 and P3 continue to be identified using the scheme of the above embodiment. In addition, if there are at least two auxiliary image collectors, the candidate targets detected by at least two auxiliary image collectors are matched with the candidate target detected by the main image collector to improve recognition accuracy.

[0082] The present application provides a target recognition method. If a transport device is in operation and the entrance or exit of the transport device is detected to be open, the main image collector is used to obtain the movement information of the candidate target within the transport device, and the auxiliary image collector is used to obtain the movement information of the candidate target in the area connected to the transport device. If the candidate target is determined to have left the transport device based on the movement information and has entered the area connected to the transport device, the candidate target is determined to be a real moving target. The above scheme can more accurately identify the target through the coordinated detection of the main image collector and the auxiliary image collector during the operation of the transport device.

[0083] Figure 5 This is a schematic diagram of the structure of a target recognition device provided in an embodiment of the present application. The device can execute the target recognition method provided in any embodiment of the present application and has the corresponding functional modules and beneficial effects of the execution method. Figure 5 As shown, the device includes:

[0084] A candidate target determination module 410 is configured to perform target detection in the interior space of the vehicle using a primary image collector in an associated group of image collectors to determine candidate targets. The associated group of image collectors includes the primary image collector in the interior space of the vehicle and auxiliary image collectors in an area connected to the vehicle.

[0085] A motion information determination module 420 is configured to track and detect the candidate target through the main image collector and / or the auxiliary image collector to determine the motion information of the candidate target;

[0086] The recognition result determination module 430 is configured to determine the recognition result of the candidate target according to the working status of the carrier and the motion information of the candidate target.

[0087] In the embodiment of the present application, the recognition result determination module 430 is specifically configured to:

[0088] If the carrier is in a stopped state, obtaining the position and motion position deviation of the candidate target detected by the main image collector;

[0089] The recognition result of the candidate target is determined according to the position and motion position deviation of the candidate target.

[0090] In the embodiment of the present application, the recognition result determination module 430 is specifically configured to:

[0091] If the number of times that the movement position deviation of the candidate target is continuously detected to exceed the preset deviation exceeds the preset number, and the position of the candidate target is not located in the preset area, then the candidate target is determined to be a real moving target;

[0092] If the number of times that the movement position deviation of the candidate target is continuously detected to exceed the preset deviation does not exceed the preset number, and the position of the candidate target is not located in the preset area, prompting the user to confirm the recognition result of the candidate target;

[0093] If it is continuously detected that the movement position deviation of the candidate target does not exceed the preset deviation for more than a preset number of times, and the position of the candidate target is located in a preset area, then the candidate target is determined to be a plane screen target;

[0094] Otherwise, the candidate target is matched with the plane screen target in the preset area to determine the recognition result of the candidate target.

[0095] In the embodiment of the present application, the recognition result determination module 430 is specifically configured to:

[0096] Increase the detection frequency of the main image collector to detect the position and motion position deviation of the candidate target;

[0097] If the position and motion position deviation of the candidate target still do not meet the preset conditions, the candidate target is determined to be a plane screen target.

[0098] In an embodiment of the present application, the device further includes:

[0099] an auxiliary detection module, configured to detect, through the auxiliary image collector, whether other candidate targets have entered the carrier if the candidate target is determined to be a plane image target;

[0100] a matching module, configured to, if the primary image collector detects that the other candidate targets have entered the carrier, match the other candidate targets detected by the primary image collector with the other candidate targets detected by the auxiliary image collector;

[0101] The real moving target determination module is used to determine that the other candidate targets are real moving targets if the matching is successful.

[0102] In the embodiment of the present application, the recognition result determination module 430 is specifically configured to:

[0103] If the carrier is in operation and the entrance or exit of the carrier is detected to be open, the main image collector is used to obtain the movement information of the candidate target within the carrier, and the auxiliary image collector is used to obtain the movement information of the candidate target in the area connected to the carrier;

[0104] If it is determined according to the motion information that the candidate target leaves the vehicle and the candidate target enters an area connected to the vehicle, the candidate target is determined to be a real moving target.

[0105] In the embodiment of the present application, the recognition result determination module 430 is specifically configured to:

[0106] Matching candidate targets detected by the primary image collector and leaving the vehicle with candidate targets detected by the auxiliary image collector and entering a communication area with the vehicle;

[0107] If the match is successful, it is determined that the candidate targets are the same real moving target.

[0108] In the embodiment of the present application, the recognition result determination module 430 is specifically configured to:

[0109] If the carrier is in operation and the entrance or exit of the carrier is detected to be open, the auxiliary image collector is used to obtain movement information of the candidate target in the area connected to the carrier;

[0110] If it is determined based on the motion information that the candidate target enters the area connected to the carrier, matching the candidate target detected by the auxiliary image collector with the candidate target detected by the main image collector;

[0111] The successfully matched candidate targets are regarded as the same real moving target.

[0112] A target recognition device provided in an embodiment of the present application can execute a target recognition method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0113] Figure 6 A schematic diagram of the structure 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, 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 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.

[0114] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory connected to the at least one processor 11 for data processing, 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 the 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 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] Multiple 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 magnetic disk, an optical disk, etc.; and a data processing unit 19, such as a network card, a modem, a wireless data processing transceiver, etc. The data processing unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 11 may be any general-purpose and / or specialized processing component 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 specialized 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 executes the various methods and processes described above, such as the target recognition method.

[0117] In some embodiments, the target recognition method can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or data processing unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the target recognition method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the target recognition method in any other suitable manner (e.g., by means of firmware).

[0118] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0119] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable object recognition device, so that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0120] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can 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 can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can 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.

[0121] To provide interaction with a user, the systems 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 can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein can be implemented in a computing system that includes back-end 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 front-end components (e.g., a user computer with a graphical user interface or 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 back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data processing (e.g., a data processing network). Examples of data processing networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] A computing system may include clients and servers. The clients and servers are generally remote from each other and typically interact via a data processing network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0124] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired information of the technical solution of this application can be achieved. This document is not limited here.

[0125] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A target recognition method, characterized in that: The method comprises: Performing target detection on the interior space of the carrier using a primary image collector in an image collector association group to determine candidate targets; wherein the image collector association group includes the primary image collector in the interior space of the carrier and auxiliary image collectors in an area connected to the carrier; Tracking and detecting the candidate target by the main image collector and / or the auxiliary image collector to determine motion information of the candidate target; The recognition result of the candidate target is determined according to the working state of the carrier and the motion information of the candidate target.

2. The method according to claim 1, characterized in that Determining a recognition result of the candidate target according to the working state of the carrier and the motion information of the candidate target includes: If the carrier is in a stopped state, obtaining the position and motion position deviation of the candidate target detected by the main image collector; The recognition result of the candidate target is determined according to the position and motion position deviation of the candidate target.

3. The method according to claim 2, characterized in that Determining a recognition result of the candidate target according to the position and motion position deviation of the candidate target includes: If the number of times that the movement position deviation of the candidate target is continuously detected to exceed the preset deviation exceeds the preset number, and the position of the candidate target is not located in the preset area, then the candidate target is determined to be a real moving target; If the number of times that the movement position deviation of the candidate target is continuously detected to exceed the preset deviation does not exceed the preset number, and the position of the candidate target is not located in the preset area, prompting the user to confirm the recognition result of the candidate target; If it is continuously detected that the movement position deviation of the candidate target does not exceed the preset deviation for more than a preset number of times, and the position of the candidate target is located in a preset area, then the candidate target is determined to be a plane screen target; Otherwise, the candidate target is matched with the plane screen target in the preset area to determine the recognition result of the candidate target.

4. The method according to claim 3, characterized in that Determining that the candidate target is a plane screen target includes: Increase the detection frequency of the main image collector to detect the position and motion position deviation of the candidate target; If the position and motion position deviation of the candidate target still do not meet the preset conditions, the candidate target is determined to be a plane screen target.

5. The method according to claim 2, characterized in that After determining the recognition result of the candidate target according to the position and the motion position deviation of the candidate target, the method further includes: If it is determined that the candidate target is a plane screen target, detecting whether there are other candidate targets entering the carrier by the auxiliary image collector; If so, and the main image collector detects that the other candidate targets have entered the carrier, matching the other candidate targets detected by the main image collector with the other candidate targets detected by the auxiliary image collector; If the match is successful, the other candidate targets are determined to be real moving targets.

6. The method according to claim 1, characterized in that Determining a recognition result of the candidate target according to the working state of the carrier and the motion information of the candidate target includes: If the carrier is in operation and the entrance or exit of the carrier is detected to be open, the main image collector is used to obtain the movement information of the candidate target within the carrier, and the auxiliary image collector is used to obtain the movement information of the candidate target in the area connected to the carrier; If it is determined according to the motion information that the candidate target leaves the vehicle and the candidate target enters an area connected to the vehicle, the candidate target is determined to be a real moving target.

7. The method according to claim 1, characterized in that Determining a recognition result of the candidate target according to the working state of the carrier and the motion information of the candidate target includes: If the carrier is in operation and the entrance or exit of the carrier is detected to be open, the auxiliary image collector is used to obtain movement information of the candidate target in the area connected to the carrier; If it is determined based on the motion information that the candidate target enters the area connected to the carrier, matching the candidate target detected by the auxiliary image collector with the candidate target detected by the main image collector; The successfully matched candidate targets are regarded as the same real moving target.

8. A target recognition device, characterized in that: The device comprises: a candidate target determination module, configured to perform target detection in the interior space of the vehicle using a primary image collector in an associated group of image collectors to determine candidate targets; wherein the associated group of image collectors includes the primary image collector in the interior space of the vehicle and auxiliary image collectors in an area connected to the vehicle; a motion information determination module, configured to track and detect the candidate target through the main image collector and / or the auxiliary image collector to determine the motion information of the candidate target; The recognition result determination module is used to determine the recognition result of the candidate target according to the working status of the carrier and the motion information of the candidate target.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and A memory connected to the at least one processor for data processing; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the target recognition method according to any one of claims 1 to 7.

10. 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 recognition method according to any one of claims 1 to 7 when executed.

Images