CN112837454A

CN112837454A - Passage detection method and device, electronic equipment and storage medium

Info

Publication number: CN112837454A
Application number: CN202110118334.9A
Authority: CN
Inventors: 胡琨; 王宇杰; 吴一超; 高梦雅; 梁鼎
Original assignee: Shenzhen Sensetime Technology Co Ltd
Current assignee: Shenzhen Sensetime Technology Co Ltd
Priority date: 2021-01-28
Filing date: 2021-01-28
Publication date: 2021-05-25
Also published as: KR20220110743A; WO2022160616A1; JP2023514762A

Abstract

The disclosure relates to a traffic detection method and device, an electronic device and a storage medium, wherein the method comprises the following steps: detecting a video frame of a detected video to obtain first position information of an object to be passed in the video frame and second position information of a target object; according to the first position information and the second position information, matching an object to be passed with the target object to determine a target object with the target object; and generating a detection result at least according to the target position information of the target object, and sending the detection result to the access control system. According to the traffic detection method disclosed by the embodiment of the disclosure, when the object to be traffic is detected to carry the target article, a detection result can be generated. The detection result can be used for indicating that the object passing through the access control system carries the target object, and the access control system can be closed after the target object and the target object pass through, so that the conditions of passing failure or accidental injury of the object carrying the target object and the like can be reduced.

Description

Passage detection method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer vision technologies, and in particular, to a passage detection method and apparatus, an electronic device, and a storage medium.

Background

The access control system generally comprises equipment such as a gate machine and the like which is released after identity verification, and is widely applied to various subway, airport, government organization and other scenes which need to pass after identity verification. When the access control system is used, a passer usually stands at a gate entrance to check, a single person passes through the gate quickly after the gate is opened, and a plurality of sensors in a channel can judge the passing state and legality and decide whether to close the gate and alarm.

Disclosure of Invention

The disclosure provides a traffic detection method and device, electronic equipment and a storage medium.

According to an aspect of the present disclosure, there is provided a traffic detection method including: detecting a video frame of a detected video to obtain first position information of an object to be passed in the video frame and second position information of a target object, wherein the detected video is a video shot at a passage channel; according to the first position information and the second position information, matching the object to be passed with the target object to determine the target object with the target object; and generating a detection result at least according to the target position information of the target object, and sending the detection result to the access control system of the passage channel.

According to the traffic detection method of the embodiment of the disclosure, the detection result can be generated under the condition that the object to be traffic is detected to carry the target article. The detection result can be used for indicating that the object passing through the access control system carries the target object, and the access control system can wait for the target object and the target object carried by the target object to pass through the passage and then close the access control system, so that the conditions that the object carrying the target object fails to pass or is accidentally injured and the like can be reduced. In addition, the system acquires the detection video of the passage channel through the image acquisition assembly, processes the detection video to generate a detection result, does not depend on the sensor of the access control system, can reduce the number of the sensors of the access control system, reduces the space occupied by the sensor, and can improve the accuracy of judging the passage state of the object to be passed.

In this possible implementation, the method further includes: receiving verification information of the access control system under the condition that the target position information indicates that the target object is located at a preset position; wherein generating a detection result at least according to the target position information of the target object comprises: and generating the detection result under the condition that the verification information is verified.

In this possible implementation manner, the first position information includes position information of a first selection box for framing a head and a shoulder of the object, where the performing detection processing on a video frame of the detection video to obtain first position information of the object to be passed in the video frame includes: and carrying out detection processing on the video frame of the detected video to obtain the position information of the first selection frame of the head and shoulder part of the frame selection object.

By the mode, whether the object reaches the preset position or not can be accurately judged through the position information of the first selection frame for framing the head and shoulder parts of the object, and verification is received, so that the accuracy of position determination can be improved. And can generate the testing result after the target object passes the verification to indicate that the access control system is closed after the target object and the target object pass, thereby reducing the possibility of passing failure.

In this possible implementation manner, the receiving the verification information of the access control system when the target location information indicates that the target object is located at the preset location includes: determining position information of a first selection frame of a plurality of objects in a video frame; and receiving verification information of the access control system under the condition that the first selection frame of the target object is located in the preset area or the intersection ratio of the first selection frame and the preset area is greater than or equal to a first threshold value.

In this possible implementation, the method further includes: under the condition that the first position information indicates that the object is located at a preset position, performing action recognition processing on the object, and determining whether the object performs a preset action or not; and under the condition that the object performs a predetermined action, saving a video clip recording the predetermined action in the detection video.

By the method, the violation can be detected when the object breaks through the access control system, and the video record of the violation is stored, so that the violation can be conveniently investigated, and a basis is provided for access control management.

In this possible implementation manner, the determining the target object with the target object by matching the object to be passed with the target object according to the first position information and the second position information includes: and determining the first object as a target object matched with the target item when the intersection ratio of the second selection frame and the third selection frame of the first object is greater than or equal to a second threshold value, wherein the first object is any object.

In this possible implementation, the method further includes: generating a pass record in the event that the object passes through the pass lane.

In this possible implementation, in a case where the object passes through the passage channel, generating a pass record includes: and generating a passing record when the target object and the target object matched with the target object pass through the passing channel.

According to an aspect of the present disclosure, a traffic detection system is provided, which includes an image acquisition component and a processing component, where the image acquisition component is configured to acquire a detection video of a traffic channel; the processing component is to: detecting a video frame of a detected video to obtain first position information of an object to be passed in the video frame and second position information of a target object; according to the first position information and the second position information, matching the object to be passed with the target object to determine the target object with the target object; and generating a detection result at least according to the target position information of the target object, and sending the detection result to the access control system of the passage channel.

In one possible implementation, the processing component is further configured to: receiving verification information of the access control system under the condition that the target position information indicates that the target object is located at a preset position; wherein generating a detection result at least according to the target position information of the target object comprises: and generating the detection result under the condition that the verification information is verified.

In a possible implementation manner, the first position information includes position information of a first selection box for framing a head and a shoulder of an object, where the detecting a video frame of a detection video to obtain first position information of an object to be passed in the video frame includes: and carrying out detection processing on the video frame of the detected video to obtain the position information of the first selection frame of the head and shoulder part of the frame selection object.

In a possible implementation manner, the preset position comprises a preset area outside an access control system of the passage,

in a possible implementation manner, receiving the verification information of the access control system when the target location information indicates that the target object is located at a preset location includes: determining position information of a first selection frame of a plurality of objects in a video frame; and receiving verification information of the access control system under the condition that the first selection frame of the target object is located in the preset area or the intersection ratio of the first selection frame and the preset area is greater than or equal to a first threshold value.

In one possible implementation, the system further includes a storage component, and the processing component is further configured to: under the condition that the first position information indicates that the object is located at a preset position, performing action recognition processing on the object, and determining whether the object performs a preset action or not; and under the condition that the object performs a predetermined action, saving a video clip recording the predetermined action in the detection video to the storage component.

In a possible implementation manner, the determining the target object with the target object by matching the object to be passed with the target object according to the first position information and the second position information includes: and determining the first object as a target object matched with the target item when the intersection ratio of the second selection frame and the third selection frame of the first object is greater than or equal to a second threshold value, wherein the first object is any object.

In one possible implementation, the device processing component is further configured to: generating a pass record in the event that the object passes through the pass lane.

In one possible implementation, in a case where the object passes through the passage channel, generating a pass record includes: and generating a passing record when the target object and the target object matched with the target object pass through the passing channel.

According to an aspect of the present disclosure, there is provided an electronic device including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to: the above described traffic detection method is performed.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-mentioned traffic detection method.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

FIG. 1 shows a flow diagram of a traffic detection method according to an embodiment of the present disclosure;

FIG. 2 shows a schematic diagram of an object detection network according to an embodiment of the present disclosure;

FIG. 3 shows a schematic diagram of a motion recognition network according to an embodiment of the present disclosure;

FIG. 4 shows a schematic diagram of an application of a traffic detection method according to an embodiment of the present disclosure;

FIG. 5 shows a block diagram of a traffic detection system according to an embodiment of the present disclosure;

FIG. 6 shows a block diagram of an electronic device according to an embodiment of the disclosure;

fig. 7 shows a block diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

Fig. 1 shows a flow chart of a traffic detection method according to an embodiment of the present disclosure, as shown in fig. 1, the method includes:

step S11, detecting a video frame of a detection video to obtain first position information of an object to be passed in the video frame and second position information of a target article, wherein the detection video is a video shot at a passage channel;

step S12, according to the first position information and the second position information, in the objects to be passed, determining a target object matched with the target object;

and step S13, generating a detection result at least according to the target position information of the target object, and sending the detection result to the access control system of the passage.

In one possible implementation, some or all of the objects to be traveled may carry or ride certain items, e.g., some objects may carry strollers, luggage, etc., or some objects may ride wheelchairs, etc. Because these articles are bulky, the door control system is prone to make a judgment error, for example, the door control system (such as a gate, etc.) is closed faster, resulting in a failure in passing objects. For example, the gate is closed when the object passes but the item has not yet passed, resulting in the item not passing, or the item passing but the object not yet passing.

In one possible implementation, to address the above issues, the access control system may be prompted when a person carrying an article such as a stroller or a trunk passes, for example, the access control system may be notified that there are two objects passing through (i.e., two objects, a person and an article), and then closed after both objects pass.

In one possible implementation manner, the detection video may be captured by an image capturing component such as a camera, and the detection video is a video captured at the traffic lane. In an example, the camera may be disposed above the access control system, and may capture the detection video from a top view, in which one or more objects to be passed may be captured, or if some objects carry target objects of a trunk or a stroller, the target objects may be captured in the detection video. The passage detection method may be executed by a processing component, for example, the processing component may be connected with an image acquisition component such as a camera (for example, connected through a USB interface, WIFI, and the like, and the connection manner is not limited in this disclosure). The processing assembly can receive the detection video, detect the video frame and process, still can determine the target object who carries the target object through the matching, and when the target object passes through access control system, generate the testing result and send access control system to make access control system close again after target object and target object all pass through.

The processing component can determine first position information of an object to be passed in the video frame and second position information of the target object, and can determine the target object matched with the target object, namely, the object carrying the target object is determined in the objects, and then a detection result can be generated and sent to the access control system when the target object carrying the target object passes through the passing channel, so that the access control system can be closed after the target object and the target object pass through, and the occurrence probability of the conditions of passing failure and accidental injury is reduced.

In one possible implementation, the processing component may perform frame-by-frame detection or frame-decimation detection on the detected video. In an example, in order to save processing resources, a way of frame extraction detection may be selected, for example, a detection video may be extracted and detected once every 2 seconds, and the time interval of frame extraction is not limited by the present disclosure.

In an example, the video frame may be detected through a neural network, for example, a single-stage target detection network (e.g., RetinaNet) may be used to detect the object and the target object in the video frame, for example, the object and the target object of a specific class may be identified in the video frame, and the first location information where the object is located and the second location information of the target object may be determined. The present disclosure is not limited as to the type of target detection network.

Fig. 2 is a schematic diagram of an object detection network according to an embodiment of the present disclosure, and as shown in fig. 2, in a case that RetinaNet is used, the object detection network may include a feature extraction network, and feature extraction may be performed on a video frame through a multi-level feature extraction network, for example, the feature extraction network may be a mobilenenet v2 feature extraction network, the feature extraction network is a lightweight multi-level feature extraction network, and the feature extraction network may also be of other types, and the present disclosure does not limit the type of the feature extraction network.

Further, the features extracted from each level of the feature extraction network may be respectively input into each level of the feature pyramid, in an example, the feature pyramid may include 4 levels, each level may include 3 feature anchors, and the disclosure does not limit the number of levels and the number of anchors. In an example, each level of the feature pyramid may include two sub-networks, one sub-network being a category sub-network for identifying a category of each object in the video frame, e.g., each object in the video frame and a specific category of target item may be identified; another subnetwork is a location subnetwork that can determine the location of objects and target items and can generate selection boxes for framing the objects and target items. The position information of the selection frame of the frame selection object is the first position information, and the position information of the selection frame of the frame selection target object is the second position information. The present disclosure does not limit the structure and parameter settings of the target detection network.

In an example, the first position information may include position information of a first selection box for framing a head-shoulder portion of the subject and position information of a second selection box for framing a body portion of the subject, where the position information of the first selection box may be used for tracking a motion trajectory of each subject, and step S11 may include: and carrying out detection processing on the video frame of the detected video to obtain the position information of the first selection frame of the head and shoulder part of the frame selection object. For example, the position information of the object may be represented by the position information of the first selection box. And the position of each object may be tracked using the position information of the first selection box.

In an example, the position information of the second selection box may be used to match with the second position information of the target item to determine a target object matching the target item, i.e., to select an object carrying the target item from a plurality of objects.

In one possible implementation, one or more objects may be detected in a certain video frame, where there may be some or all of the objects carrying the target item. The target object carrying the target item may be determined to generate a detection result when the target object is ready to pass through an access control system of the passage way, the detection result being indicative that the object is the target object carrying the target item (e.g., a trunk, a baby carriage, etc.), and the access control system may receive the detection result and close the access control system after both the target object and the target item pass through the access control system, so as to reduce the occurrence probability of the passage failure.

In one possible implementation, as described above, the position information of the second selection box that may frame the body part of the subject may be matched with the second position information of the target item. The second location information may include location information of a third selection box for framing the target item, and the step S12 may include: and determining the first object as a target object matched with the target item when the intersection ratio of the second selection frame and the third selection frame of the first object is greater than or equal to a second threshold value, wherein the first object is any object.

In an example, a target object that matches the target item may be determined by solving an intersection ratio of the third selection box and objects in the video frame. For example, an object may carry large items such as luggage, a stroller, etc., which may be placed on the ground and in close proximity to the body of the carrier, i.e., at the side of the body. Thus, there may be an overlap in the video frame of the second selection box of the body part of the frame carrier and the third selection box of the frame target item. Also, since the target item is generally placed near the carrier and relatively distant from the other person, the third selection frame for framing the target item and the second selection frame for framing the body part of the other person generally do not overlap or overlap less. Thus, the target object matching the target item may be determined by the overlap between the second and third selection boxes of the carrier.

In an example, the size of the overlap portion may be represented by an intersection ratio between the second selection box and the third selection box. That is, when the intersection ratio of the second selection frame and the third selection frame is large, the overlapping portion is large, when the intersection ratio of the second selection frame and the third selection frame is small, the overlapping portion is small, and when the intersection ratio of the second selection frame and the third selection frame is 0, the second selection frame and the third selection frame do not have the overlapping portion. A second threshold of the intersection ratio can be set, and a second selection frame with the intersection ratio to the third selection frame being greater than or equal to the second threshold can be determined in a second selection frame of one or more objects in the video frame, and the second selection frame is determined as a second selection frame of the target object, that is, the body part framed by the second selection frame is the body part of the target object, and the target object is the object matched with the target object. Through the method, the target object matched with each target object detected in the video frame is determined.

By the method, the target object matched with the target object can be determined through the intersection and combination ratio between the second selection frame for framing the body part and the third selection frame for framing the target object, namely, the carrier of the target object is accurately determined, so that a detection result is generated when the carrier passes through the access control system, and the probability of passing failure is reduced.

In a possible implementation manner, after a target object and an object are detected and a target object (i.e., a carrier) matched with the target object is determined, trajectory tracking can be performed on each object (including the target object), that is, position information of the same object and/or the target object is determined in a plurality of video frames, the object not carrying the target object passes through an access control system and is normally verified and passed through, and the object carrying the target object passes through the access control system and is verified and generates a detection result so as to prompt the access control system to close after the target object and the target object pass through.

In an example, in a trajectory tracking process, a plurality of objects and a plurality of target items may be included in a detection video, and motion trajectories of the plurality of objects and the target items may be tracked respectively. In an example, a multi-target tracking method of bipartite graph matching and Kalman filtering may be employed to simultaneously track the locations of multiple objects and target items. For example, the position information of the object and/or the target object, that is, the selection frame, may be determined in the adjacent video frames processed by the processing component (if the processing component processes the detection video frame by frame, the processed adjacent video frames are the adjacent video frames of the detection video; if the processing component performs frame extraction processing on the detection video, the processed adjacent video frames are the extracted adjacent video frames), and the matching of the object and/or the target object may be performed, that is, it is determined that the same object and/or the target object is selected by the selection frame in the adjacent video frames.

In an example, it may be determined that the selection boxes in the adjacent video frames are selected to be the same object and/or target item by means of an intersection ratio, for example, in a certain video frame, the selection box for selecting the target item is located in an area a, in an adjacent video frame, the selection box for selecting the certain target item is located in an area B, and if the intersection ratio between the area a and the area B reaches a preset threshold value, it may be determined that the selection boxes in the two adjacent video frames are the same target item.

Further, the position of each target item and/or object in the following video frame may be predicted after determining the position of the target item in the two adjacent video frames, for example, the position of each target item and/or object in the following video frame may be predicted through a kalman filtering algorithm, the predicted position may also be matched with the actual position of the target item and/or object detected in the following video frame, for example, if the intersection ratio of the predicted position and the actual position is greater than or equal to the prediction threshold, it may be determined that the same object and/or target item is framed in the two adjacent video frames, and if the intersection ratio does not reach the prediction threshold, it may be framed that the same object and/or target item is not the same, which may be caused by a queue in which some object leaves the queue. One or more target items and/or objects in the detected video may be tracked in the manner described above.

In a possible implementation manner, the position and the motion trajectory of each object may be determined in the above manner, and the authentication information of the access control system is received when an object reaches a preset position (for example, before the access control system). In an example, whether the object carries the target object or not, the object needs to be verified when passing through the access control system, for example, the verification can be performed by means of card swiping, code swiping, face recognition, fingerprint recognition, iris recognition and the like, the access control system can open the gate to allow the object to pass through if the verification passes, and if the verification does not pass, the gate is not opened, and the object which does not pass through the verification is prevented from passing through.

Further, the method further comprises: receiving verification information of the access control system under the condition that the target position information indicates that the target object is located at a preset position; wherein generating a detection result at least according to the target position information of the target object comprises: and generating the detection result under the condition that the verification information is verified. That is, if it is determined that the target object reaches the preset position, the access control system also authenticates the target object, and if the authentication is passed, the target object can be released. In this case, the detection result may be generated to prompt the access control system to close after the target object and the target item both pass.

In an example, when determining whether the object reaches the preset position, it may be determined by first position information of the object. The first position information includes position information of a first selection frame for framing the head and shoulder portions of the object, that is, if the position of the first selection frame is within a preset position (e.g., a preset area in front of an access control system) or has a relatively large overlapping area with the preset position, it may be determined that the object reaches the preset area.

Similarly, the target location information is first location information of the target object, and includes location information of a first selection box for framing a head and a shoulder of the target object, where the preset location includes a preset area outside the access control system of the passage way, and when the target location information indicates that the target object is located at the preset location, the receiving of the verification information of the access control system includes: determining position information of a first selection frame of a plurality of objects in a video frame; and receiving verification information of the access control system under the condition that the first selection frame is located in the preset area or the intersection ratio of the first selection frame and the preset area is greater than or equal to a first threshold value. That is, the location information of a plurality of objects, which may be target objects carrying target objects, may be tracked simultaneously, and the authentication information of the access control system may be received when it is determined that the objects reach the target locations. The position information of the first selection frame for framing the head and shoulder part of the target object can be used, the target object can be determined to reach the preset position when the first selection frame is in the preset area outside the access control system or is more overlapped with the preset area (the intersection ratio is larger than or equal to the first threshold), and the verification of the access control system can be received. If the verification passes, a detection result may be generated.

In one possible implementation, the method further includes: generating a pass record in the event that the object passes through the pass lane. In an example, if the access control system passes the verification of the object to be passed, the access control system (e.g., a gate) may be opened for release, and after the object passes, the processing component may generate a pass record, e.g., may number the feature information of the passed object (e.g., generate a code corresponding to the head and shoulder feature information of the object one-to-one), and save the feature information and the code into a database for query.

In another example, the passing record may also be generated based on the characteristic information of the target object and the passing time, and stored in the database, and the present disclosure does not limit the content contained in the passing record. In an example, the processing component may be coupled to a storage component, and the database may be disposed in the storage component for maintaining the pass record.

In one possible implementation, if the object passing through the access control system is the target object carrying the target object, the access control system may be closed after both the target object and the target object pass through, and may generate a pass record after both the target object and the target object pass through. Generating a pass record in the event that the object passes through the pass lane, comprising: and generating a passing record when the target object and the target object matched with the target object pass through the passing channel. That is, the processing component may further determine that both the target object and the target item pass through the access control system of the passage, i.e., the passage record is regenerated after there is no passage failure.

In a possible implementation manner, the case that the verification is passed is described above, but there may be a case that the verification is not passed, and if an object passes through the access control system after the verification is not passed, or passes through the access control system without verification, both the cases can be regarded as violations. In addition to the above-described violations, other predetermined behaviors may be identified and recorded by the processing component. For example, if it is recognized that a certain object carries a dangerous object, the behavior can be considered as belonging to a predetermined behavior, and the behavior is recorded. The system further comprises a storage component for storing a video clip of the detected video, the method further comprising: under the condition that the first position information indicates that the object is located at a preset position, performing action recognition processing on the object, and determining whether the object performs a preset action or not; and under the condition that the object performs a predetermined action, saving a video clip recording the predetermined action in the detection video.

In an example, after the object reaches the preset location, the access control system may authenticate the object, and if the object is not authenticated and breaks through the access control system or does not authenticate and still breaks through the access control system, the processing component may determine the behavior as a predetermined behavior (violation behavior).

In an example, the predetermined behavior may be determined by an action recognition network, for example, in case the verification fails, if a behavior of an object running through an access control system is detected, the behavior is determined as the predetermined behavior. For example, the predetermined behavior may include flipping through a gate of an access control system or drilling through a gate of an access control system, etc., and the present disclosure does not limit the category of the predetermined behavior.

FIG. 3 shows a schematic diagram of a motion recognition network according to an embodiment of the present disclosure. The motion recognition network can recognize the detection video frame by frame, and also can recognize the sampled video frame after extracting the frame of the detection video. In an example, to improve processing efficiency and reduce consumption of computational resources, frame extraction processing may be performed on a detected video, for example, frame extraction may be performed on a video between a time when it is determined that the object verification fails and a time when the object rushes through the access control system, for example, 8 video frames may be extracted, or one video frame may be extracted every 2 seconds, and the frame extraction manner is not limited in the present disclosure.

In an example, the motion recognition network may perform motion recognition processing on the extracted video frames, for example, may perform feature extraction processing on the extracted video frames, for example, feature extraction processing may be performed by a MobileNetV2 feature extraction network, so as to obtain a feature map of each video frame. Further, the feature maps of each video frame may be spatio-temporally modeled by the motion recognition network to determine the motion type of the object in the video frame. If the action type is determined to be an violation, it may be determined that the object is performing the violation (e.g., a violation of a gate).

In an example, in such a case, the processing component can save a video clip in which the predetermined behavior occurred. For example, it may be stored in the storage component described above. In an example, a video frame extracted during the action recognition processing may be saved, or a video clip between the time when the object fails to pass the verification and the time when the object passes the access control system may be saved, and if the object does not pass the access control system after the verification, the video clip between the time when the predetermined action of the object is detected and the time when the object passes the access control system may be saved.

Fig. 4 is a schematic application diagram of the traffic detection method according to the embodiment of the disclosure, and as shown in fig. 4, a plurality of objects are in line waiting for passing through the traffic passage before the access control system of the traffic passage, wherein some objects carry target objects such as a trunk.

In one possible implementation, the camera may capture a video of the detection at the passage, i.e., may capture a plurality of objects that are queuing through the access control system. The video frame of the detection video can be detected, and the target object of the video frame can be determined. Further, a target object matching the target object, that is, a target object carrying the target object, may be selected from the plurality of objects by a cross-over ratio between the selection frame of the framed target object and the selection frame of the body part of the subject.

In one possible implementation, the processing component may analyze a plurality of video frames of the detected video and track a motion trajectory of each object. And when the selection frame of the head and shoulder part of the selected object reaches a preset position in front of the access control system, determining that the object is to be verified. And after the access control system verifies the object, if the object passes the verification, the access control system can open and release the object, and can store the passing record of the object. If the passing object is the target object carrying the target object, a detection result can be generated to prompt the access control system to close after the target object and the target object pass, and a passing record of the passing of the target object is stored.

In one possible implementation, if the object fails to verify but passes through the access control system, or if the object does not pass through the access control system yet, the processing component may detect the violation of the object, and may store the video segment during the violation.

According to the passage detection system of the embodiment of the disclosure, the detection result can be generated under the condition that the object to be passed is detected to carry the target article. The detection result can be used for indicating the access control system to wait for the object and the carried target object to pass through the passage and then close the access control system, so that the conditions that the object carrying the target object fails to pass or is accidentally injured can be reduced, the predetermined behavior can be detected when the object runs through the access control system, and the video record of the predetermined behavior is stored, so that the predetermined behavior can be conveniently investigated, and a basis is provided for access control management. In addition, the method obtains the detection video of the passage channel through the image obtaining assembly, processes the detection video to generate the detection result, does not depend on the sensor of the access control system, can reduce the number of the sensors of the access control system, reduces the space occupied by the sensor, and can improve the accuracy of judging the passage state of the object to be passed.

In a possible implementation manner, the passage detection method can be used in an access control system, for example, a subway, an airport, a government agency and other scenes needing to pass after identity verification, and when an object passing through the access control carries an article such as luggage, the access control can be closed after the object and the article pass through the access control, so that the probability of occurrence of passing failure and accidental injury events is reduced. And the video clip when the violation behaviors occur, such as the object rushing through the access control system, can be stored for the management of the access control system. The application field of the traffic detection method is not limited by the disclosure.

Fig. 5 shows a block diagram of a traffic detection system according to an embodiment of the present disclosure, as shown in fig. 5, the system includes an image acquisition component 11 and a processing component 12, the image acquisition component 11 is used for acquiring a detection video of a traffic lane; the processing component 12 is configured to: detecting a video frame of a detected video to obtain first position information of an object to be passed in the video frame and second position information of a target object; according to the first position information and the second position information, matching the object to be passed with the target object to determine the target object with the target object; and generating a detection result at least according to the target position information of the target object, and sending the detection result to the access control system of the passage channel.

It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted.

In addition, the present disclosure also provides a passage detection device, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any passage detection method provided by the present disclosure, and the corresponding technical solutions and descriptions and corresponding descriptions in the methods section are not repeated.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and for specific implementation, reference may be made to the description of the above method embodiments, and for brevity, details are not described here again

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured as the above method.

The electronic device may be provided as a terminal, server, or other form of device.

Fig. 6 is a block diagram illustrating an electronic device 800 in accordance with an example embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.

Referring to fig. 6, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.

Fig. 7 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, the electronic device 1900 may be provided as a server. Referring to fig. 7, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A traffic detection method, comprising:

detecting a video frame of a detected video to obtain first position information of an object to be passed in the video frame and second position information of a target object, wherein the detected video is a video shot at a passage channel;

according to the first position information and the second position information, matching the object to be passed with the target object to determine the target object with the target object;

and generating a detection result at least according to the target position information of the target object, and sending the detection result to the access control system of the passage channel.

2. The method of claim 1, further comprising:

receiving verification information of the access control system under the condition that the target position information indicates that the target object is located at a preset position;

wherein generating a detection result at least according to the target position information of the target object comprises:

and generating the detection result under the condition that the verification information is verified.

3. The method of claim 1, wherein the first position information includes position information of a first selection box that boxes a head and shoulder portion of the subject,

the detecting process of the video frame of the detection video to obtain the first position information of the object to be passed in the video frame includes:

and carrying out detection processing on the video frame of the detected video to obtain the position information of the first selection frame of the head and shoulder part of the frame selection object.

4. The method of claim 3, wherein the predetermined location comprises a predetermined area outside of an access control system of the transit passage,

receiving verification information of the access control system under the condition that the target position information indicates that the target object is located at a preset position, wherein the verification information comprises:

determining position information of a first selection frame of a plurality of objects in a video frame;

and receiving verification information of the access control system under the condition that the first selection frame of the target object is located in the preset area or the intersection ratio of the first selection frame and the preset area is greater than or equal to a first threshold value.

5. The method of claim 1, further comprising:

under the condition that the first position information indicates that the object is located at a preset position, performing action recognition processing on the object, and determining whether the object performs a preset action or not;

and under the condition that the object performs a predetermined action, saving a video clip recording the predetermined action in the detection video.

6. The method of claim 1, wherein the first location information comprises location information of a second checkbox for checking a body part of the subject, the second location information comprises location information of a third checkbox for checking a target item,

according to the first position information and the second position information, matching the object to be passed with the target object, and determining the target object with the target object, wherein the method comprises the following steps:

and determining the first object as a target object matched with the target item when the intersection ratio of the second selection frame and the third selection frame of the first object is greater than or equal to a second threshold value, wherein the first object is any object.

7. The method of claim 1, further comprising:

generating a pass record in the event that the object passes through the pass lane.

8. The method of claim 7, wherein generating a pass record if the object passes through the pass lane comprises:

and generating a passing record when the target object and the target object matched with the target object pass through the passing channel.

9. A traffic detection device, comprising: an image acquisition component and a processing component,

the image acquisition component is used for acquiring a detection video of the passage;

the processing component is to:

detecting a video frame of a detected video to obtain first position information of an object to be passed in the video frame and second position information of a target object;

10. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to: performing the method of any one of claims 1 to 8.

11. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 8.