CN113011290A

CN113011290A - Event detection method and device, electronic equipment and storage medium

Info

Publication number: CN113011290A
Application number: CN202110236981.XA
Authority: CN
Inventors: 徐孟莹; 曾星宇; 于志鹏; 梁鼎
Original assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Current assignee: Shanghai Sensetime Intelligent Technology Co Ltd
Priority date: 2021-03-03
Filing date: 2021-03-03
Publication date: 2021-06-22
Also published as: WO2022183661A1; KR20220125716A

Abstract

The present disclosure relates to an event detection method and apparatus, an electronic device, and a storage medium, wherein the method includes: acquiring a video stream of the escalator; carrying out human body detection on the video stream, and determining a first area where a target object in the video stream is located; performing gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, wherein the gesture recognition result comprises a confidence coefficient that the gesture of the target object is an abnormal gesture; and determining an event detection result of the target object according to the gesture recognition result of the target object. The embodiment of the disclosure can improve the accuracy of event detection.

Description

Event 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 an event detection method and apparatus, an electronic device, and a storage medium.

Background

With the development of economy and the continuous improvement of infrastructure construction, the application of the escalator in markets, office buildings, public transportation and other scenes is more and more extensive. While the escalator brings convenience, people pay more attention to possible accidents caused by abnormal actions of pedestrians on the escalator, such as falling, retrograde motion, squatting and the like. If abnormal actions on the escalator cannot be detected in time and the escalator is alarmed to stop running in time, great loss can be caused to the life and property safety of pedestrians on the escalator.

Disclosure of Invention

The present disclosure provides an event detection technical solution.

According to an aspect of the present disclosure, there is provided an event detection method including: acquiring a video stream of the escalator; carrying out human body detection on the video stream, and determining a first area where a target object in the video stream is located; performing gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, wherein the gesture recognition result comprises a confidence coefficient that the gesture of the target object is an abnormal gesture; and determining an event detection result of the target object according to the gesture recognition result of the target object.

In one possible implementation manner, the determining an event detection result of the target object according to the gesture recognition result of the target object includes: and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold, determining that the event detection result of the target object is an abnormal event.

In one possible implementation manner, the determining an event detection result of the target object according to the gesture recognition result of the target object includes: and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold value, and the first duration of the confidence greater than or equal to the confidence threshold value is greater than or equal to the activation time, determining that the event detection result of the target object is an abnormal event.

In one possible implementation, the method further includes: and sending first alarm information under the condition that the event detection result of the target object is the occurrence of an abnormal event.

In one possible implementation, the method further includes: changing the detection state of the target object to a detected state when the event detection result of the target object is the occurrence of an abnormal event, wherein the determining the event detection result of the target object according to the gesture recognition result of the target object comprises: determining that the event detection result of the target object is abnormal event duration under the condition that the detection state of the target object is a detected state, the confidence coefficient of the target object at the current moment is greater than or equal to a confidence coefficient threshold value, and the second duration of the confidence coefficient greater than or equal to the confidence coefficient threshold value is greater than cooling time; and sending second alarm information under the condition that the event detection result of the target object is that the abnormal event lasts.

In one possible implementation manner, the determining an event detection result of the target object according to the gesture recognition result of the target object includes: and determining that the event detection result of the target object is an abnormal event end when the detection state of the target object is a detected state, the confidence of the target object at the current moment is smaller than a confidence threshold, and the third duration of the confidence smaller than the confidence threshold is longer than the deactivation time.

In one possible implementation, the method further includes: expanding the first area according to a preset expansion coefficient to obtain an expanded second area; and cutting out the image of the second area from the video frame of the video stream to obtain the first area image.

In a possible implementation manner, the method performs gesture recognition on a first area image corresponding to the first area through a gesture recognition network to obtain a gesture recognition result of the target object, where the method further includes: training the posture recognition network according to a preset training set, wherein the object postures marked by the sample images in the training set comprise abnormal postures, normal postures and other postures, and the other postures comprise the normal postures and postures except the abnormal postures.

In one possible implementation, the abnormal posture includes a squat posture, and the abnormal event includes a squat event.

According to an aspect of the present disclosure, there is provided an event detection apparatus including: the video stream acquisition module is used for acquiring the video stream of the escalator; the region determining module is used for carrying out human body detection on the video stream and determining a first region where a target object in the video stream is located; the gesture recognition module is used for carrying out gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, wherein the gesture recognition result comprises a confidence coefficient that the gesture of the target object is an abnormal gesture; and the event detection module is used for determining the event detection result of the target object according to the gesture recognition result of the target object.

In one possible implementation, the event detection module is configured to: and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold, determining that the event detection result of the target object is an abnormal event.

In one possible implementation, the event detection module is configured to: and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold value, and the first duration of the confidence greater than or equal to the confidence threshold value is greater than or equal to the activation time, determining that the event detection result of the target object is an abnormal event.

In one possible implementation, the apparatus further includes: and the first alarm module is used for sending first alarm information under the condition that the event detection result of the target object is the abnormal event.

In one possible implementation, the apparatus further includes: a state changing module, configured to change a detection state of the target object to a detected state when an event detection result of the target object is an occurrence of an abnormal event, where the event detecting module is configured to: determining that the event detection result of the target object is abnormal event duration under the condition that the detection state of the target object is a detected state, the confidence coefficient of the target object at the current moment is greater than or equal to a confidence coefficient threshold value, and the second duration of the confidence coefficient greater than or equal to the confidence coefficient threshold value is greater than cooling time; and sending second alarm information under the condition that the event detection result of the target object is that the abnormal event lasts.

In one possible implementation, the event detection module is configured to: and determining that the event detection result of the target object is an abnormal event end when the detection state of the target object is a detected state, the confidence of the target object at the current moment is smaller than a confidence threshold, and the third duration of the confidence smaller than the confidence threshold is longer than the deactivation time.

In one possible implementation, the apparatus further includes: the expansion module is used for expanding the first area according to a preset expansion coefficient to obtain an expanded second area; and the cutting module is used for cutting the image of the second area from the video frame of the video stream to obtain the image of the first area.

In a possible implementation manner, the apparatus performs gesture recognition on a first area image corresponding to the first area through a gesture recognition network to obtain a gesture recognition result of the target object, where the apparatus further includes: the training module is used for training the posture recognition network according to a preset training set, the object postures marked by the sample images in the training set comprise abnormal postures, normal postures and other postures, and the other postures comprise the normal postures and postures except the abnormal postures.

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 invoke the memory-stored instructions to perform the above-described method.

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-described method.

According to the embodiment of the disclosure, the area where the object is located in the video stream can be detected; recognizing the image of the area to determine the pose of the object; the event detection result is determined according to the posture of the object, and the accuracy of event detection can be improved, so that the probability of accidents is reduced, and the cost of manpower detection is reduced.

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 an event detection method according to an embodiment of the present disclosure.

Fig. 2 illustrates a schematic diagram of a detected state change of a target object according to an embodiment of the present disclosure.

Fig. 3 shows a block diagram of an event detection device according to an embodiment of the present disclosure.

Fig. 4 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure.

Fig. 5 shows a block diagram of an electronic device in accordance with 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.

The event detection method can be applied to scenes such as shopping malls, office buildings, public transportation and the like, and based on a deep learning method, video streams of the area where the escalator is located in the scene are processed and analyzed, abnormal events (such as falling, retrograde motion, squatting and the like) of an object (such as a pedestrian) can be detected in real time, the area where the abnormal events occur on the escalator is located, and an alarm is given in time so as to stop the operation of the escalator, so that the risk of safety accidents is reduced.

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

in step S11, a video stream of the escalator is acquired;

in step S12, performing human body detection on the video stream, and determining a first area where a target object in the video stream is located;

in step S13, performing gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, where the gesture recognition result includes a confidence that the gesture of the target object is an abnormal gesture;

in step S14, an event detection result of the target object is determined according to the gesture recognition result of the target object.

In one possible implementation, the event detection method may be performed by an electronic device such as a terminal device or a server, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like, and the method may be implemented by a processor calling a computer-readable instruction stored in a memory. Alternatively, the method may be performed by a server.

For example, at least one image capturing device, such as at least one camera facing the escalator, may be disposed at the position of the escalator to be detected, so as to capture the video stream of the escalator and detect an object (e.g., a pedestrian) riding on the escalator in the video stream. The installation position of the image acquisition device, the acquisition mode of the video stream and the specific area corresponding to the video stream are not limited in the disclosure.

In one possible implementation, in step S11, a video stream of the escalator may be acquired, for example, a video stream uploaded by the image capture device is received; and decodes the acquired video stream to obtain a decoded video stream (also referred to as a picture stream).

In one possible implementation manner, in step S12, human body detection may be performed on the decoded video stream, and a human body frame in each video frame of the video stream is determined; and tracking the human body frames in the video frames to determine the human body frames of pedestrians (which can be called target objects) belonging to the same identity, namely, determining a first area where the target object is located in the video stream.

The human body detection mode can be, for example, human body key point identification, human body contour detection and the like; the human body tracking mode may be, for example, determining objects belonging to the same identity according to the intersection ratio of human body frames in adjacent video frames. It will be appreciated by those skilled in the art that human detection and tracking can be accomplished in any manner known in the relevant art, and the present disclosure is not limited thereto.

In one possible implementation, human detection and tracking may be performed on each video frame of the video stream; or sampling the video stream at a certain time interval, and carrying out human body detection and tracking on the sampled video frames; and key frames in the video stream can be acquired, and human body detection and tracking can be performed on the key frames. The present disclosure is not so limited.

In one possible implementation, the first Region may be represented as the upper left corner (x) of a human body box (which may also be referred to as a Region of Interest (ROI))₁，y₁) And the coordinates of the vertex of the lower right corner (x)₂，y₂) And the tracking ID of the target object, the present disclosure does not limit the manner in which the first region is represented.

In one possible implementation manner, a first region image corresponding to the first region may be cut out from each video frame, and in step S13, the first region image is subjected to pose recognition through a trained pose recognition network, so as to obtain a pose recognition result of the target object. The gesture recognition network can be, for example, a convolutional neural network, and the disclosure does not limit the specific network structure and training mode of the gesture recognition network.

In one possible implementation, the gesture recognition result includes a confidence that the gesture of the target object is an abnormal gesture, so as to determine whether an abnormal event occurs in subsequent processing. The gesture recognition result may further include a confidence that the gesture of the target object is a normal gesture, a confidence that the gesture is other gestures besides the normal gesture and the abnormal gesture, and the like.

In one possible implementation, the abnormal posture may be, for example, a squat posture, a fall posture, or the like; the normal posture may be, for example, a standing posture; other postures may include lying, lying on the stomach, etc., or situations where no posture can be recognized. The present disclosure is not limited to a particular category of gestures.

In one possible implementation manner, in step S14, an event detection result of the target object may be determined according to a gesture recognition result of the target object. The event detection result may include occurrence or non-occurrence of an abnormal event, for example, when the confidence of the abnormal posture exceeds a threshold value, or the confidence exceeds the threshold value and lasts for a certain time, the event detection result is determined as the occurrence of the abnormal event. Wherein, the abnormal event can be determined according to the category of the abnormal posture, such as a squatting event, a falling event, etc., which is not limited by the present disclosure.

In one possible implementation, if the event detection result is that an abnormal event occurs, warning information may be generated and sent. The alarm information may include a reminder of the abnormal event and may also include an area where the target object in which the abnormal event occurs is located, so that the relevant person can perform positioning. The present disclosure is not so limited.

In one possible implementation, an alarm message can be sent, for example, to the control device of the escalator, so that the control device stops the operation of the escalator; the warning information can also be sent to the related personnel in charge of the escalator operation, so that the related personnel stop the escalator operation and go to the escalator for rescue and the like. The present disclosure does not limit the content of the warning information.

The following provides an explanation of the event detection method of the embodiments of the present disclosure.

As described above, the video stream of the area where the escalator is located may be collected by the camera, and the collected video stream may be transmitted to the local electronic device such as the front server or the cloud server. The electronic device may decode the received video stream to obtain a decoded video stream.

In step S12, the human body detection and tracking may be performed on the decoded video stream through the detection and tracking network, so as to detect the human body frame in each video frame of the video stream, and track the human body frames of pedestrians belonging to the same identity, thereby obtaining the first region where the target object in the video stream is located. The detection tracking network may be a convolutional neural network, and the network structure of the detection tracking network is not limited by the present disclosure.

After the first region is obtained, a first region image corresponding to the first region may be acquired. The image of the first area can be directly cut out from the video frame of the video stream, and the first area can also be subjected to expansion processing.

In a possible implementation manner, the event detection method according to the embodiment of the present disclosure may further include:

expanding the first area according to a preset expansion coefficient to obtain an expanded second area;

and cutting out the image of the second area from the video frame of the video stream to obtain the first area image.

As previously described, the first region may be represented as the top left corner (x1, y1) and bottom right corner vertex coordinates (x2, y2) of the body frame, and the tracking ID of the target object. The expansion coefficient may be set in advance, and the first region may be expanded based on the expansion coefficient. Let the vertex coordinates of the upper left corner and the lower right corner of the expanded second region be (x'₁，y′₁)(x′₂，y′₂) Then, there are:

x′₁＝max(0,x₁-e(x₂-x₁))

y′₁＝max(0,y₂-e(y₂-y₁))

x′₂＝min(W-1,x₂+e(x₂-x₁))

y′₂＝min(H-1,y₂+e(y₂-y₁) Equation (1)

In the formula (1), W and H represent the image width and height of the video frame, respectively, and e represents the expansion coefficient. The expansion coefficient e is, for example, 0.1, and the specific value of the expansion coefficient e is not limited in the present disclosure.

According to the formula (1), the expansion of the first area in the image range of the video frame can be realized, and the expanded second area is obtained. Furthermore, the image of the second area can be cut out from the corresponding video frame to obtain the image of the first area for subsequent processing.

By the mode, the performance of the classifier of the gesture recognition network can be improved, and the accuracy of subsequent gesture recognition is improved.

In one possible implementation manner, the first area image may be subjected to gesture recognition through a gesture recognition network in step S13, so as to obtain a gesture recognition result of the target object. The gesture recognition network may include multiple classifiers to recognize the gesture of the target object as an abnormal gesture, a normal gesture, or other gestures. The gesture recognition network may be trained prior to deployment of the gesture recognition network.

training the posture recognition network according to a preset training set, wherein the object postures marked by the sample images in the training set comprise abnormal postures, normal postures and other postures, and the other postures comprise the normal postures and postures except the abnormal postures.

For example, to improve the robustness of the classifier of the gesture recognition network, an open set training mode can be adopted. That is, the object pose of the sample image annotation includes other poses in addition to the abnormal pose and the normal pose. For example, in the case where the abnormal posture and the normal posture are a squatting posture and a standing posture, respectively, the other postures may include a lying posture, and the like; situations that the posture cannot be judged can also be included, such as the lower half body is completely shielded, is excessively fuzzy and the like; the method can also comprise the situations that the detection frame covers a plurality of people and can not judge who is the main person, and the like. The disclosure is not limited to the gesture types and the specific case of no gesture included in other gestures.

In the training process, the sample images in the training set can be respectively input into the gesture recognition network for processing to obtain a sample recognition result; determining the network loss of the gesture recognition network according to the difference between the sample recognition result and the sample image; reversely adjusting the parameters of the attitude identification network according to the network loss; and obtaining the trained posture recognition network under the condition of network convergence through multiple iterations.

By the mode, the robustness of gesture recognition can be improved, and the accuracy of gesture recognition can be improved.

In one possible implementation, the gesture recognition result may include a confidence s that the gesture of the target object is an abnormal gesture. In step S14, event detection may be performed according to the gesture recognition result of the target object, and the event detection result of the target object may be determined.

In one possible implementation, a state machine may be maintained for each tracking ID (i.e., target object), and the state of the state machine is updated based on the pose recognition result for each video frame to implement event detection.

Fig. 2 illustrates a schematic diagram of a detected state change of a target object according to an embodiment of the present disclosure. As shown in fig. 2, the detection states of the target object may include an IDLE state (IDLE)21, a DETECTING state (DETECTING)22, and a DETECTED state (DETECTED) 23. In the detection process, the detection state can be changed according to each condition in fig. 2, and if a certain condition is satisfied, the corresponding event detection result is output.

In fig. 2, the activation time ac (activation seconds), the cooling time cd (cooldown seconds), the deactivation time da (deactivation seconds), and the confidence threshold T are all preset parameters; the detection time DT (detected time), the undetected time UT (undetected time), and the trigger time TT (trigger time) are timestamps and are used for judging whether the activation time, the deactivation time and the cooling time are reached, and the timestamps are dynamically updated in the processing process; now denotes the timestamp of the current video frame (i.e. the current time instant); SET denotes update of the time stamp, and OUT denotes an output result of the event.

The activation time AC and the deactivation time DA take values of 0 to 3s, the cooling time takes values of 1 to 10s, and the confidence threshold T takes a value of 0.5, which is not limited in the present disclosure.

In one possible implementation, step S14 may include: and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold, determining that the event detection result of the target object is an abnormal event.

For example, if there is No ROI (i.e. the first region) in the video frame at the current time, or the confidence level s that the target object is in an abnormal posture is smaller than the confidence level threshold T, i.e. the condition 211 is satisfied (No ROI or s < T), the detection state of the target object is in the idle state 21.

In one possible implementation, in the case that the target object is in the idle state 21 and the activation time AC is not set or is set to 0, if the confidence of the target object at the current time is greater than or equal to the confidence threshold T, that is, the condition 212 is satisfied (s > -T and AC ═ 0), the output result is START, that is, the event detection result of the target object is determined to be the occurrence of an abnormal event.

In this case, the detection state of the target object may be changed to the detected state 23, and state update may be realized; and updating the trigger time TT and the undetected time UT to the current time now, and starting to calculate the trigger time TT and the undetected time UT for subsequent judgment.

By the method, the abnormal event can be directly determined to occur when the target object is in the abnormal posture, and the real-time performance of event detection is improved, so that the alarm can be given in time, and the risk of the occurrence of safety accidents is reduced.

In one possible implementation, step S14 may include:

and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold value, and the first duration of the confidence greater than or equal to the confidence threshold value is greater than or equal to the activation time, determining that the event detection result of the target object is an abnormal event.

As shown in fig. 2, in the case where the target object is in the idle state 21 and the activation time AC is greater than 0, if the confidence of the target object at the current time is greater than or equal to the confidence threshold T, that is, the condition 213 is satisfied (s > -T and AC >0), the result is not output, that is, the event detection result is that no abnormal event has occurred. In this case, the detection state of the target object may be changed to the detection state 22, and the detection time DT may be updated to the current time now.

In one possible implementation, in the case that the target object is in the detecting state 22, if the confidence of the target object at the current time is less than the confidence threshold T, or there is No ROI in the video frame at the current time, that is, the condition 221 is satisfied (No ROI or s < T), the result is not output, that is, the event detection result is that No abnormal event occurs. In this case, the detection state is changed to the idle state 21.

In one possible implementation, in the case where the target object is in the in-detection state 22, if the confidence of the target object at the current time is greater than or equal to the confidence threshold T and the first duration (now-DT) for which the confidence is greater than or equal to the confidence threshold T is less than the activation time AC, that is, the condition 222 is satisfied (s > -T and now-DT < AC), no result is output, that is, the event detection result is that no abnormal event has occurred. In this case, the detection state is kept as the detection state 22.

In one possible implementation, in the case that the detection state of the target object is the in-detection state 22, if the confidence of the target object at the current time is greater than or equal to the confidence threshold T and the first duration (now-DT) of the confidence greater than or equal to the confidence threshold T is greater than or equal to the activation time AC, that is, the condition 223(s > -T and now-DT > -AC) is satisfied, the result is output as START, that is, the event detection result of the target object is determined to be the occurrence of an abnormal event.

In this case, the detection state of the target object may be changed to the detected state 23, and state update may be realized; and updating the trigger time TT and the undetected time UT to the current time now for subsequent judgment.

By the method, the target object can be determined to be an abnormal event when the target object is in an abnormal posture and continues for a certain time, so that false detection possibly occurring in single-frame detection is avoided, and the accuracy of event detection is improved.

In one possible implementation manner, the event detection method according to the embodiment of the present disclosure further includes: and sending first alarm information under the condition that the event detection result of the target object is the occurrence of an abnormal event.

That is, if the output result is START, that is, the event detection result of the target object is the occurrence of an abnormal event, corresponding alarm information (referred to as first alarm information) may be transmitted. The first warning information may include a reminder of an abnormal event, and may further include an area where a target object of the abnormal event is located, so that relevant people can locate the target object. The present disclosure is not so limited.

In one possible implementation, the first warning message can be sent, for example, to the control device of the escalator, so that the control device stops the operation of the escalator; the first warning information can also be sent to the related personnel in charge of the escalator operation, so that the related personnel stop the escalator operation, go to the escalator for rescue and the like. The present disclosure does not limit the content of the first warning information.

By the mode, the abnormal event can be timely alarmed, and the risk of safety accidents is reduced.

In one possible implementation manner, the event detection method according to the embodiment of the present disclosure further includes:

and changing the detection state of the target object into the detected state when the event detection result of the target object is that an abnormal event occurs.

As described above, if the condition 223 is satisfied (s > -T and now-DT > -AC), the output result is START, that is, it is determined that the event detection result of the target object is the occurrence of an abnormal event. In this case, the detection state of the target object is changed to the detected state 23 so that the detection is continued in the subsequent processing.

In one possible implementation, step S14 may include:

determining that the event detection result of the target object is abnormal event duration under the condition that the detection state of the target object is a detected state, the confidence coefficient of the target object at the current moment is greater than or equal to a confidence coefficient threshold value, and the second duration of the confidence coefficient greater than or equal to the confidence coefficient threshold value is greater than cooling time;

and sending second alarm information under the condition that the event detection result of the target object is that the abnormal event lasts.

For example, in the case where the detection state of the target object is the detected state 23, if the confidence of the target object at the current time is greater than or equal to the confidence threshold T and the first duration (now-TT) for which the confidence is greater than or equal to the confidence threshold T is less than or equal to the cooling time CD, it may be considered that the result is not output within the cooling time after the previous output.

In one possible implementation, If the confidence of the target object at the current time is greater than or equal to the confidence threshold T and the second duration (now-TT) with the confidence greater than or equal to the confidence threshold T is greater than the cooling time CD, that is, the condition 231(s > -T; If now-TT > CD) is satisfied, the result is output as ONGING, that is, the event detection result of the target object is determined to be abnormal event duration.

In one possible implementation, if the confidence of the target object at the current time is greater than or equal to the confidence threshold T, the undetected time UT may be updated to the current time now, i.e., the timestamp of the undetected time UT is reset, so as to restart the calculation of the undetected time. If the confidence of the target object at the current time is greater than or equal to the confidence threshold T and the second duration (now-TT) for which the confidence is greater than or equal to the confidence threshold T is greater than the cooling time CD, the cooling time CD may be updated to the current time now, i.e., the timestamp of the cooling time CD is reset, so as to restart the calculation of the cooling time.

In a possible implementation manner, in a case that the event detection result of the target object is that the abnormal event persists, corresponding alarm information (referred to as second alarm information) may be generated and sent. The second warning information may include a reminder that the abnormal event persists, and may further include an area where the target object where the abnormal event persists, so that the related person may perform positioning. The present disclosure is not so limited.

Through the mode, when the target object is in the abnormal posture and reaches the cooling time, the abnormal event is determined to be continuous, so that the monitoring equipment for repeatedly reminding the escalator or the related personnel in charge of the escalator to run is repeatedly alarmed by taking the cooling time as an interval, the condition of alarming information which is not observed by the related personnel is avoided, and the risk of safety accidents is further reduced.

In one possible implementation, step S14 may include:

and determining that the event detection result of the target object is an abnormal event end when the detection state of the target object is a detected state, the confidence of the target object at the current moment is smaller than a confidence threshold, and the third duration of the confidence smaller than the confidence threshold is longer than the deactivation time.

For example, in the case that the detection state of the target object is the detected state 23, if the confidence of the target object at the current time is less than the confidence threshold T or No ROI, and the third duration (now-UT) with the confidence less than the confidence threshold is less than or equal to the deactivation time DA, that is, the condition 232 is satisfied (No ROI or < T) and now-UT < ═ DA), it may be considered that the result is within the deactivation time DA after the previous output, and the result is not output.

In a possible implementation manner, in the case that the detection state of the target object is the detected state 23, if the confidence of the target object at the current time is less than the confidence threshold T or No ROI, and the third duration (now-UT) that the confidence is less than the confidence threshold is greater than the deactivation time DA, that is, the condition 233 is satisfied ((No ROI or s < T) and now-UT > DA), the output result is END, that is, the event detection result of the target object is determined to be the abnormal event END.

In a possible implementation manner, when the event detection result is that the abnormal event is ended, the event ending information can be generated and sent so as to remind monitoring equipment for escalator operation or related personnel in charge of escalator operation; event end information may not be generated. The present disclosure is not so limited.

In a possible implementation manner, when the event detection result of the target object is the end of the abnormal event, the detection state of the target object may be changed to the idle state 21, so as to implement state update; the timestamp of the undetected time UT is updated to nil (none) for subsequent re-determination.

In one possible implementation, if the detected state of the target object is in the idle state 21 and there is no ROI for the target object for a period of time, the state machine of the target object may be released or applied to other target objects. The present disclosure is not so limited.

In this way, when the target object is not in an abnormal posture and the deactivation time is reached, it is determined that the abnormal event is ended, and thus the whole processing flow of event detection is completed.

According to the event detection method disclosed by the embodiment of the disclosure, the video stream of the region where the escalator is located can be detected and tracked, and the human body region of the same object is determined; performing pose recognition on the image of the region to determine a pose of the object; event detection is carried out according to the posture of the object, and whether a squatting event occurs or not is judged; and finally, returning the area judged as the squatting event and the corresponding human body frame for alarming, so that the accuracy of event detection can be improved, and the risk of safety accidents is reduced.

According to the event detection method disclosed by the embodiment of the disclosure, event detection can be realized only by using the monocular camera without other sensors (such as an infrared sensor and the like), and the efficiency of event detection is improved.

The event detection method can be applied to the field of security monitoring and applied to escalator pedestrian dangerous behavior detection and alarm related products, for example, the method is deployed in an escalator self-service monitoring system in application scenes such as superstores, supermarkets, subway stations and office buildings, and automatic detection and alarm of dangerous behaviors such as elevator squatting events are achieved, so that elevator deceleration or elevator stopping measures are taken, and the cost of manual monitoring is reduced.

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. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.

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

Fig. 3 shows a block diagram of an event detection apparatus according to an embodiment of the present disclosure, which, as shown in fig. 3, includes:

the video stream acquiring module 31 is used for acquiring a video stream of the escalator;

the region determining module 32 is configured to perform human body detection on the video stream, and determine a first region where a target object in the video stream is located;

the gesture recognition module 33 is configured to perform gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, where the gesture recognition result includes a confidence that the gesture of the target object is an abnormal gesture;

and the event detection module 34 is configured to determine an event detection result of the target object according to the gesture recognition result of the target object.

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 specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

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 to invoke the memory-stored instructions to perform the above-described method.

The embodiments of the present disclosure also provide a computer program product, which includes computer readable code, and when the computer readable code runs on a device, a processor in the device executes instructions for implementing the event detection method provided in any one of the above embodiments.

The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed cause a computer to perform the operations of the event detection method provided in any of the above embodiments.

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

Fig. 4 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. 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. 4, 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 Complementary Metal Oxide Semiconductor (CMOS) or Charge Coupled Device (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 a wireless network (WiFi), a second generation mobile communication technology (2G) or a third generation mobile communication technology (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. 5 illustrates a block diagram of an electronic device 1900 in accordance with an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. Referring to fig. 5, 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 further include a power component 1926 configured to perform power management of the electronic device 1900, and a wired or wireless network interface 1950 configured to connect the electronic device 1900 toTo a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as the Microsoft Server operating system (Windows Server), stored in the memory 1932^TM) Apple Inc. of the present application based on the graphic user interface operating System (Mac OS X)^TM) Multi-user, multi-process computer operating system (Unix)^TM) Free and open native code Unix-like operating System (Linux)^TM) Open native code Unix-like operating System (FreeBSD)^TM) 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 is 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.

The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

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. An event detection method, comprising:

acquiring a video stream of the escalator;

carrying out human body detection on the video stream, and determining a first area where a target object in the video stream is located;

performing gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, wherein the gesture recognition result comprises a confidence coefficient that the gesture of the target object is an abnormal gesture;

and determining an event detection result of the target object according to the gesture recognition result of the target object.

2. The method of claim 1, wherein determining the event detection result of the target object according to the gesture recognition result of the target object comprises:

and under the condition that the confidence of the target object at the current moment is greater than or equal to a confidence threshold, determining that the event detection result of the target object is an abnormal event.

3. The method of claim 1, wherein determining the event detection result of the target object according to the gesture recognition result of the target object comprises:

4. The method according to any one of claims 1-3, further comprising:

and sending first alarm information under the condition that the event detection result of the target object is the occurrence of an abnormal event.

5. The method according to any one of claims 1-4, further comprising:

changing the detection state of the target object to a detected state when the event detection result of the target object is the occurrence of an abnormal event,

wherein the determining an event detection result of the target object according to the gesture recognition result of the target object includes:

6. The method of claim 5, wherein determining the event detection result of the target object according to the gesture recognition result of the target object comprises:

7. The method according to any one of claims 1-6, further comprising:

8. The method according to any one of claims 1 to 7, wherein the method performs gesture recognition on a first region image corresponding to the first region through a gesture recognition network to obtain a gesture recognition result of the target object,

wherein the method further comprises: training the posture recognition network according to a preset training set, wherein the object postures marked by the sample images in the training set comprise abnormal postures, normal postures and other postures, and the other postures comprise the normal postures and postures except the abnormal postures.

9. The method of any one of claims 2-8, wherein the abnormal posture comprises a squat posture and the abnormal event comprises a squat event.

10. An event detection device, comprising:

the video stream acquisition module is used for acquiring the video stream of the escalator;

the region determining module is used for carrying out human body detection on the video stream and determining a first region where a target object in the video stream is located;

the gesture recognition module is used for carrying out gesture recognition on a first region image corresponding to the first region to obtain a gesture recognition result of the target object, wherein the gesture recognition result comprises a confidence coefficient that the gesture of the target object is an abnormal gesture;

and the event detection module is used for determining the event detection result of the target object according to the gesture recognition result of the target object.

11. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 9.

12. 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 9.