CN115272951A - Repeat alarm optimization processing method and device, computer equipment and storage medium - Google Patents

Repeat alarm optimization processing method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN115272951A
CN115272951A CN202210698421.0A CN202210698421A CN115272951A CN 115272951 A CN115272951 A CN 115272951A CN 202210698421 A CN202210698421 A CN 202210698421A CN 115272951 A CN115272951 A CN 115272951A
Authority
CN
China
Prior art keywords
target
alarm
parking
person
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210698421.0A
Other languages
Chinese (zh)
Inventor
陆晓栋
魏东东
周永哲
吴忠人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Dahua Technology Co Ltd
Original Assignee
Zhejiang Dahua Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Dahua Technology Co Ltd filed Critical Zhejiang Dahua Technology Co Ltd
Priority to CN202210698421.0A priority Critical patent/CN115272951A/en
Publication of CN115272951A publication Critical patent/CN115272951A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30236—Traffic on road, railway or crossing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Emergency Alarm Devices (AREA)

Abstract

The application relates to a repeated alarm optimization processing method, a repeated alarm optimization processing device, computer equipment and a storage medium, wherein under the condition that an unalarged target person with a history track of which the duration time meets a first preset condition appears in a current video frame acquired by a camera, whether a parking target with a space-time association relation with the unalarged target person exists is detected; if so, taking the parking target which has a space-time association relation with the target personnel without alarming as the designated parking target; determining a first history person which has an appearance time earlier than that of an unalarmed target person and is subjected to alarm processing among history persons having a space-time association relationship with a specified parking target; if the characteristic information of the target person which does not give an alarm is matched with the characteristic information of the first historical person, the fact that the ID of the target person which does not give an alarm jumps is determined, alarm processing of the target person which does not give an alarm is forbidden, and the problem that the same pedestrian is repeatedly given an alarm due to the fact that the ID of the pedestrian jumps is effectively avoided.

Description

Repeated alarm optimization processing method and device, computer equipment and storage medium
Technical Field
The application relates to the technical field of intelligent traffic, in particular to a repeated alarm optimization processing method, a repeated alarm optimization processing device, computer equipment and a storage medium.
Background
The urban expressway or the expressway is a road section where pedestrians are prohibited, if the urban expressway or the expressway has the pedestrians, generally, due to the fact that an accident or a fault occurs in a motor vehicle, people on the motor vehicle get off to perform vehicle condition inspection or accident confirmation and the like, and road supervision people need to perform a series of confirmation work on the pedestrians appearing on the urban expressway or the expressway.
In the prior art, a camera is installed on a road such as an urban expressway or an expressway which generally does not allow pedestrians to walk, the pedestrian is tracked and monitored by the camera, and once a new pedestrian appears, the new pedestrian can be alarmed and notified to a road supervisor as long as the new pedestrian meets an alarm condition (such as lasting for a set time). However, new pedestrians can appear, and the problem that the same pedestrian is repeatedly alarmed due to the pedestrian ID jump in the prior art is caused by the pedestrian ID jump probably caused by motor vehicle shielding or pedestrian posture change and the like.
Disclosure of Invention
Based on this, it is necessary to provide a method, an apparatus, a computer device and a storage medium for optimizing a repeat alarm to solve the problem of repeat alarm to the same pedestrian caused by ID jump in the related art.
In a first aspect, an embodiment of the present application provides a repetitive alarm optimization processing method, including the following steps:
under the condition that the duration of the historical track appearing in the current video frame collected by the camera meets the target person which is not alarmed under the first preset condition, detecting whether a parking target which has a space-time association relationship with the target person which is not alarmed exists in the recorded parking targets; the historical track and the recorded parking target are identified from historical video frames;
if so, taking the parking target which has a space-time association relationship with the target personnel without alarming as a designated parking target;
determining a first history person which has been subjected to alarm processing and has an appearance time earlier than the target person without alarm, among history persons having a spatiotemporal association relationship with the designated parking target; the historical people are people identified from the historical video frames;
and if the characteristic information of the target person which does not give an alarm is matched with the characteristic information of the first historical person, determining that the ID of the target person which does not give an alarm jumps, and forbidding the target person which does not give an alarm to carry out alarm processing.
In some embodiments, the detecting whether there is a parking target in a spatiotemporal association with the target person without alarm in the recorded parking targets comprises the following steps:
detecting whether parking targets with parking information meeting a preset second condition exist in all recorded parking targets, and if so, determining the parking targets meeting the preset condition as parking targets which are in space-time association with target persons not giving an alarm; wherein the parking information is identified from the historical video frames;
the preset second condition includes:
temporal and spatial.
In some embodiments, the detecting whether the parking information has the parking target meeting the preset second condition includes the following steps:
acquiring endpoint coordinate information of a detection frame of the parking target in a parking time period from the historical video frame;
detecting whether the distance between the historical track of the target person without alarm and the detection frame of the parking target is within a preset range in the parking time period of the parking target.
In some of these embodiments, the method further comprises:
detecting a motor vehicle target appearing in a video frame, and judging whether the motor vehicle target is in a parking state or not;
and if the current motor vehicle target is in a parking state, taking the current motor vehicle target as a parking target, and recording the duration time, the parking starting time and the parking ending time of the parking state of the current parking target.
In some of these embodiments, the method further comprises:
and storing the space-time association relation between the target personnel without alarm and the designated parking target.
In some of these embodiments, the method further comprises:
if the feature information of the target person which does not give an alarm is not matched with the feature information of the first historical person or if the parking target which has a space-time association relationship with the target person which does not give an alarm does not exist, sending the target person which does not give an alarm to an alarm process.
In some embodiments, the step of sending the target person without alarm to the alarm process comprises the following steps:
and judging whether the target personnel without alarm is a living body target or not, and carrying out alarm processing on the target personnel without alarm under the condition that the target personnel without alarm is a living body target.
In some embodiments, the determining whether the target person is a living target comprises:
judging whether the target personnel without alarm is a living target or not based on the space-time change relation and the motion characteristics of the target personnel without alarm; the temporal-spatial variation relation and the motion characteristics of the target personnel without alarm are obtained from the historical video frames.
In a second aspect, an embodiment of the present application provides a repeated alarm optimization processing apparatus, where the apparatus includes: the device comprises a detection module, a designation module, a determination module and a matching module;
the detection module is used for detecting whether a parking target which has a space-time association relation with an unalarmed target person exists in recorded parking targets under the condition that the duration of the occurrence of the historical track in the current video frame acquired by the camera meets a first preset condition is determined; the historical track and the recorded parking target are identified from historical video frames;
the designated module is used for taking the parking target which has a space-time association relationship with the target personnel who do not give an alarm as a designated parking target if the designated module is used for taking the parking target as the designated parking target;
the determining module is used for determining a first historical person which has the appearance time earlier than the target person which is not alarmed and has been subjected to alarm processing in historical persons which have space-time association relationship with the specified parking target; the historical people are people identified from the historical video frames;
and the matching module is used for determining that the ID of the target person who does not give an alarm jumps and forbidding the alarm processing of the target person who does not give an alarm if the characteristic information of the target person who does not give an alarm is matched with the characteristic information of the first historical person.
In a third aspect, there is provided in this embodiment a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the computer program.
In a fourth aspect, in the present embodiment, a storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method according to the first aspect as described above.
According to the repeated alarm optimization processing method, the repeated alarm optimization processing device, the computer equipment and the storage medium, under the condition that the target person which does not alarm and has the duration time of the historical track in the current video frame collected by the camera meeting the first preset condition is determined, whether a parking target which has a space-time association relation with the target person which does not alarm exists or not exists is detected in the recorded parking targets; the historical track and the recorded parking target are identified from the historical video frame; if so, taking the parking target with space-time association relation with the target personnel without alarming as the designated parking target; determining a first historical person which has earlier appearance time than the target person which does not give an alarm and has been subjected to alarm processing among the historical persons which have space-time association relationship with the designated parking target; historical people are people identified from historical video frames; and if the characteristic information of the target person which does not give the alarm is matched with the characteristic information of the first historical person, determining that the ID of the target person which does not give the alarm jumps, and forbidding the alarm processing of the target person which does not give the alarm. According to the method and the device, personnel matching is carried out by utilizing the space-time association relation between the target personnel without alarming and the parking target, whether the target personnel without alarming at present is the alarming target with the ID jumping or not is judged, if the target personnel without alarming at present is determined to be the alarming target with the ID jumping, the target personnel without alarming at present is not sent into an alarming flow, and the problem that the same pedestrian is repeatedly alarmed due to the ID jumping of the pedestrian is effectively avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a diagram of an application scenario of a repetitive alarm optimization processing method provided in an embodiment of the present application;
FIG. 2 is a flow chart of a repetitive alarm optimization processing method provided according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a repeated alarm optimization processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a computer device provided according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that such a development effort might be complex and tedious, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, given the benefit of this disclosure, without departing from the scope of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of describing the invention (including a single reference) are to be construed in a non-limiting sense as indicating either the singular or the plural. The use of the terms "including," "comprising," "having," and any variations thereof herein, is meant to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
Fig. 1 is an application scenario diagram of a repetitive alarm optimization processing method according to an embodiment of the present application. As shown in fig. 1, data transmission may be performed between a server 101 and a terminal 102 via a network. The system comprises a terminal 102, a server 101, a parking target and a monitoring server, wherein the terminal 102 is used for monitoring road conditions on roads, such as urban expressways or expressways, which are not allowed to walk by pedestrians generally and collecting monitoring data, the server 101 is used for analyzing video frames collected by the terminal 102, and under the condition that target persons which are not alarmed have historical tracks with duration time meeting a first preset condition in the video frames collected by the terminal 102, whether the parking target exists in a space-time association relationship with the target persons which are not alarmed is detected in the recorded parking targets; the historical track and the recorded parking target are identified from the historical video frame; if so, taking the parking target with space-time association relation with the target personnel without alarming as the designated parking target; determining a first history person which has a space-time association relation with a specified parking target and is subjected to alarm processing among history persons; historical people are people identified from video frames prior to the current video frame; and if the characteristic information of the target personnel is matched with the characteristic information of the first historical personnel, determining that the ID of the target personnel which is not alarmed jumps, and forbidding the alarm processing of the target personnel which is not alarmed. The server 101 may be implemented by an independent server or a server cluster composed of a plurality of servers, and the terminal 102 may be implemented by an independent or a plurality of arbitrary video capture devices.
The embodiment provides a repeated alarm optimization processing method, as shown in fig. 2, the method includes the following steps:
step S210, under the condition that the duration of the historical track in the current video frame collected by the camera meets the target personnel without alarming of a first preset condition, detecting whether a parking target with a space-time association relation with the target personnel without alarming exists in the recorded parking targets; the historical track and the recorded parking target are identified from the historical video frame;
in particular, due to the defects of the existing target detection algorithm, the personnel target may be detected as a non-motor vehicle target sometimes, so all the unalarmed target personnel in the embodiment of the present application may refer to an unalarmed human target and an unalarmed non-motor vehicle target. The target person who is not alarmed may be the target person who appears for the first time and does not alarm at present, or the target person who has ID jump (the target person is not alarmed after the ID jump). In the embodiment of the application, the historical track can be obtained by tracking and detecting the historical video frames. The duration time of the historical track needs to meet a first preset condition, because the duration time of the historical track is not too long or too short, if the duration time is too long, the current target person is not ready to be processed, and the target person disappears in the visual field of the camera; if the time is too short, the historical track is not enough, and the space-time association relationship between the target personnel and the parking target cannot be accurately acquired, so that the first preset condition met by the duration time of the historical track in the application can be adjusted according to actual requirements. In addition, the parking target in the embodiment of the application is a motor vehicle target in a parking state, and whether a parking target having a space-time association relationship with an unalarmed target person exists or not is judged, that is, whether the space-time association relationship exists between the motor vehicle target and the unalarmed target person within a parking time period or not is judged.
And step S220, if so, taking the parking target which has space-time association relation with the target personnel without alarming as the designated parking target.
Specifically, assuming that the parking target a has a space-time association relationship with the target person m who is not alarming, the parking target a is taken as a specified parking target of the target person m.
Step S230, determining a first historical person which has the appearance time earlier than the target person without alarm and has been subjected to alarm processing from historical persons having space-time association relationship with the specified parking target; historical people are people identified from historical video frames.
Specifically, on roads such as urban expressways or expressways which are not allowed to walk by pedestrians, the personnel object generally carries out work such as fault confirmation from the upper part and the lower part of a motor vehicle, and then the ID may jump due to squatting or vehicle body shielding, and the ID before and after jumping generally has a space-time association relation with the same motor vehicle. Taking the above example as an example, assuming that the designated parking target of the target person m who does not give an alarm is a, it means that the target person m who does not give an alarm is most likely to be a person who has undergone ID hopping by a historical person who has a time-space association with the designated parking target a. If the target person m is indeed the person who has passed the ID jump, the person before the ID jump must appear earlier than the target person m, otherwise there is no chance of passing the ID jump to become the target person m. Furthermore, before going through ID hopping, there may be two cases, first: if the ID before jumping is normally alarmed, the target person m which is not alarmed does not need to be alarmed again; secondly, the method comprises the following steps: if the ID before jumping is missed, the target person m which is not alarmed needs to be alarmed at the moment. Therefore, in this embodiment, it is necessary to determine the first history person who has been subjected to the alarm processing and whose current time is earlier than that of the target person m who has not yet alarmed, from among the history persons who have a temporal-spatial relationship with the designated parking target, and if it is determined that the target person m who has not yet alarmed is a person who has undergone ID hopping of the first history person, it is not necessary to alarm the target person m who has not yet alarmed again. Assuming that historical persons having a time-space association relationship with the designated parking target A have a, b, c, d, f, g and h, wherein only a, b, c and d appear earlier than the unalarmed target person m and have been subjected to alarm processing, the a, b, c and d are determined as first historical persons.
And step S240, if the characteristic information of the target person without alarm matches with the characteristic information of the first historical person, determining that the ID of the target person without alarm jumps, and forbidding the target person without alarm to be alarmed.
Taking the above as an example, assuming that the designated parking target of the target person m without alarm is a, and there are a, b, c and d in the first history person which has been subjected to alarm processing and has a space-time association relationship with a and appears earlier than the target person m without alarm, the feature information of the target person m without alarm is matched with the feature information of the first history person a, b, c and d, so as to determine whether the target person m without alarm is the alarm person after ID jump. Specifically, the features of the first historical persons a, b, c and d and the features of the target person m who is not alarming may be extracted by using a feature extraction algorithm to obtain the feature information of the target person m who is not alarming and the feature information of the first historical persons a, b, c and d. In addition, the similarity between the feature information of the target person m without alarm and the feature information of the first history persons a, b, c and d can be compared by using the existing cosine similarity calculation. In addition, as the distance, the posture, the size of the snapshot and the like of the personnel target in the video frame all influence the currently extracted feature information, the video frames in the same state as the current target personnel m which is not alarmed can be selected from the historical video frames of the first historical personnel a, b, c and d for feature extraction according to the distance, the posture, the size of the snapshot and the like of the target personnel m which is not alarmed in the video frame, so that the accuracy of the comparison result is improved.
If the feature information of the target person m without alarm matches with the feature information of the first historical person a, it is indicated that the target person m without alarm is the target person generated after the first historical person a undergoes ID hopping, and since a is the person who has performed alarm processing, the target person m without alarm does not need to be alarmed again, so that the alarm processing of the target person m without alarm is prohibited, and a series of operations generated after repeated alarm is avoided.
In the prior art, a camera is installed on a road such as an urban expressway or an expressway which generally does not allow pedestrians to walk, the pedestrian is tracked and monitored by the camera, and once a new pedestrian appears, the new pedestrian can be alarmed and notified to a road supervisor as long as the new pedestrian meets an alarm condition (such as lasting for a set time). However, new pedestrians can appear, and the problem that the same pedestrian is repeatedly alarmed due to the pedestrian ID jump in the prior art is caused by the pedestrian ID jump probably caused by motor vehicle shielding or pedestrian posture change and the like.
In order to solve the problems, the application provides a repeated alarm optimization processing method, which includes the steps that under the condition that an unalarged target person with a historical track duration meeting a first preset condition appears in a current video frame collected by a camera, whether a parking target with a space-time association relation with the unalarged target person exists or not is detected in recorded parking targets; the historical track and the recorded parking target are identified from the historical video frame; if so, taking the parking target with space-time association relation with the target personnel without alarming as the designated parking target; determining a first historical person which has earlier appearance time than the target person which does not give an alarm and has been subjected to alarm processing among the historical persons which have space-time association relationship with the designated parking target; historical people are people identified from historical video frames; and if the characteristic information of the target person which does not give an alarm is matched with the characteristic information of the first historical person, determining that the ID of the target person which does not give an alarm jumps, and forbidding the target person which does not give an alarm to carry out alarm processing. According to the method and the system, personnel matching is carried out by utilizing the space-time association relation between the target personnel without alarming and the parking target, whether the target personnel without alarming at present is the alarming target with the ID jumping or not is judged, if the target personnel without alarming at present is identified as the alarming target with the ID jumping, the target personnel without alarming at present is not sent into an alarming flow, and the problem of repeated alarming on the same pedestrian caused by the ID jumping of the pedestrian is effectively avoided.
As one embodiment, the step S210 of detecting whether there is a parking target having a spatiotemporal association relationship with an unalarmed target person among the recorded parking targets includes the following steps:
step S211, detecting whether parking targets with parking information meeting a preset second condition exist in all the recorded parking targets, and if so, determining the parking targets meeting the preset condition as parking targets which are associated with target personnel without alarm in time and space; wherein the parking information is identified from historical video frames;
presetting the second condition includes: temporal and spatial.
In the present embodiment, the parking information refers to the parking time and parking place of the vehicle target, which can be recognized from the historical video frames. The track of the parking target and the track of the target person without alarming are verified in time and space, so that whether the parking target is in space-time association with the target person without alarming is effectively judged. Specifically, assuming that the parking time period of the parking target B is 10 to 10, and the parking place of the parking target is S point, it is determined whether the trajectory of the unalarged human target at 10. Similarly, traversing all recorded parking targets, and detecting whether a parking target with parking information meeting a preset second condition exists, namely detecting whether a parking target with space-time intersection exists between the track in the parking time period and the track of the target person without alarm.
Further, in one embodiment, the step S211 of detecting whether there is a parking target whose parking information satisfies the preset second condition includes the following steps:
acquiring endpoint coordinate information of a detection frame of a parking target in a parking time period from a historical video frame;
and detecting whether the distance between the historical track of the target person without alarm and the detection frame of the parking target is within a preset range in the parking time period of the parking target.
Specifically, in the existing intelligent monitoring field, if the existence of a motor vehicle target is detected in a video frame, a detection frame is displayed around the motor vehicle target, and the detection frame of the motor vehicle target is generally rectangular and surrounds the motor vehicle target. In the embodiment, the endpoint coordinate information of the detection frame of the parking target in the parking time period is acquired from the historical video frame, the endpoint coordinate information of the detection frame reflects the position information of the parking target in the video frame, and whether the distance between the historical track of the target person without alarm and the detection frame of the parking target is within a preset range in the parking time period of the parking target is detected, so that whether the parking target with parking information meeting a preset second condition exists is effectively detected.
In one embodiment, the repeated alarm optimization processing method further comprises the following steps:
and step S250, detecting the motor vehicle target appearing in the video frame, and judging whether the motor vehicle target is in a parking state.
Specifically, the existing target detection algorithm may be used to detect the vehicle target appearing in the video frame, and determine whether the vehicle target is in a parking state, for example, a public algorithm such as SSD (Single Shot multi box Detector) or YOLO (You Only Look Once).
And step S260, if the current motor vehicle target is in a parking state, taking the current motor vehicle target as a parking target, and recording the duration time, the parking starting time and the parking ending time of the parking state of the current parking target.
If the current motor vehicle target is detected to be in the parking state, the current motor vehicle target can be used as the parking target, the duration time of the parking state, the parking starting time and the parking ending time of the current parking target are recorded, and the time-space association relationship is built for subsequent target personnel to be ready for work.
As one implementation mode, the space-time association relation between the target personnel without alarming and the designated parking target can be stored, the subsequent personnel matching efficiency is improved, and the working efficiency of repeated alarming optimization processing of the application is further improved.
In one embodiment, the repeated alarm optimization processing method further comprises the following steps:
and step S270, if the feature information of the target person which does not give an alarm is not matched with the feature information of the first historical person or if no parking target which has a space-time association relationship with the target person which does not give an alarm exists, sending the target person which does not give an alarm to an alarm process.
Specifically, if the feature information of the target person without alarm is not matched with the feature information of the first historical person or if a parking target with a space-time association relation with the target person without alarm does not exist, it is proved that the target person without alarm is not subjected to alarm processing, the target person without alarm is sent to an alarm process, the target person without alarm is prevented from being missed to report, and further the influence on road supervision work is effectively avoided.
Further, in one embodiment, the step S270 of sending the target person without alarm to the alarm process includes the following steps:
and step S271, judging whether the target personnel without alarm is a living body target, and carrying out alarm processing on the target personnel without alarm under the condition that the target personnel without alarm is the living body target.
Specifically, since the human-shaped poster on the motor vehicle and the human-shaped vertical plate, the pot plant, the columnar object and the like arranged on the road are likely to be detected as the human target, thereby causing the situations of false detection and false alarm of the human target, whether the target person without alarm is the living body target needs to be judged, and the target person without alarm is subjected to alarm processing under the situation that the target person without alarm is the living body target, thereby further effectively reducing the false alarm rate of the target person without alarm.
As one embodiment, whether an unalarged target person is a living target or not may be determined based on the temporal-spatial variation relationship and the motion characteristics of the unalarged target person; the temporal-spatial variation relation and the motion characteristics of the target personnel without alarm are obtained from historical video frames. And judging whether the target personnel without alarm is a living body target or not based on the space-time change relation and the motion characteristics of the target personnel without alarm, namely judging whether the continuous existence time and the motion track distance of the target personnel without alarm accord with the motion rule of the living body target or not and judging whether the motion characteristics of the target personnel without alarm accord with the motion characteristics of the living body target or not so as to judge whether the target personnel without alarm is the living body target or not.
Fig. 3 is a schematic diagram of a repeat alarm optimization processing apparatus according to an embodiment of the present invention, and as shown in fig. 3, there is provided a repeat alarm optimization processing apparatus 30, including: a detection module 31, a designation module 32, a determination module 33, and a matching module 34;
the detection module 31 is configured to, in a case where it is determined that an unalarmed target person whose duration of a historical trajectory in a current video frame acquired by a camera satisfies a first preset condition occurs, detect whether a parking target having a temporal-spatial association relationship with the unalarmed target person exists among recorded parking targets; the historical track and the recorded parking target are identified from the historical video frame;
the specifying module 32 is used for taking the parking target which has the space-time association relation with the target personnel without alarming as the specified parking target if the parking target exists;
a determination module 33, configured to determine, among historical persons having a space-time association relationship with a specified parking target, a first historical person who has been subjected to alarm processing and has an appearance time earlier than that of an unalarged target person; historical people are people identified from historical video frames;
and the matching module 34 is configured to determine that the ID of the target person who does not alarm jumps if the feature information of the target person matches the feature information of the first historical person, and prohibit the target person who does not alarm from being alarmed.
The above repeated alarm optimization processing apparatus 30 detects whether there is a parking target having a space-time association relationship with an object person not alarming in the recorded parking targets by determining that the duration of the historical trajectory occurring in the current video frame acquired by the camera satisfies a first preset condition; the historical track and the recorded parking target are identified from the historical video frame; if so, taking the parking target which has a space-time association relation with the target personnel without alarming as the designated parking target; determining a first historical person which has earlier appearance time than the target person which does not give an alarm and has been subjected to alarm processing among the historical persons which have space-time association relationship with the designated parking target; historical people are people identified from historical video frames; and if the characteristic information of the target person which does not give an alarm is matched with the characteristic information of the first historical person, determining that the ID of the target person which does not give an alarm jumps, and forbidding the target person which does not give an alarm to carry out alarm processing. According to the method and the device, personnel matching is carried out by utilizing the space-time association relation between the target personnel without alarming and the parking target, whether the target personnel without alarming at present is the alarming target with the ID jumping or not is judged, if the target personnel without alarming at present is determined to be the alarming target with the ID jumping, the target personnel without alarming at present is not sent into an alarming flow, and the problem that the same pedestrian is repeatedly alarmed due to the ID jumping of the pedestrian is effectively avoided.
In one embodiment, the detection module 31 is further configured to detect whether there is a parking target whose parking information satisfies a preset second condition in all the recorded parking targets, and if so, determine the parking target satisfying the preset condition as a parking target associated with the presence of the target person without alarm in space-time; wherein the parking information is identified from historical video frames;
the preset second condition includes:
temporal and spatial.
In one embodiment, the detection module 31 is further configured to obtain, from the historical video frames, endpoint coordinate information of a detection frame of the parking target in the parking time period;
and detecting whether the distance between the historical track of the target person without alarm and the detection frame of the parking target is within a preset range in the parking time period of the parking target.
In one embodiment, the repeated alarm optimization processing apparatus 30 further includes a recording module, configured to detect a motor vehicle target appearing in the video frame, and determine whether the motor vehicle target is in a parking state; and if the current motor vehicle target is in the parking state, taking the current motor vehicle target as the parking target, and recording the duration time, the parking starting time and the parking ending time of the parking state of the current parking target.
In one embodiment, the repeat alert optimization process 30 further includes a saving module for saving a spatiotemporal association between unalarmed target persons and designated parking targets.
In one embodiment, the repeated alarm optimization processing device 30 further includes an alarm module, configured to send the target person without alarm to the alarm process if the feature information of the target person without alarm does not match the feature information of the first historical person or if there is no parking target having a space-time association relationship with the target person without alarm.
In one embodiment, the alarm module is further configured to determine whether an unalarged target person is a living body target, and perform alarm processing on the unalarged target person when the unalarged target person is the living body target.
In one embodiment, the alarm module is further configured to determine whether an unalarged target person is a living target based on a temporal-spatial variation relationship and a motion characteristic of the unalarged target person; the temporal-spatial variation relationship and the motion characteristics of the target personnel without alarm are obtained from historical video frames.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operating system and the running of computer programs in the non-volatile storage medium. The database of the computer device is used for storing a preset configuration information set. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement the above-described repeat alarm optimization processing method.
In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The memory provides an environment for the operating system and the computer programs to run in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a repeat alarm optimization method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the configuration shown in fig. 4 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation on the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a storage medium is provided, on which a computer program is stored, which computer program, when executed by a processor, performs the steps of:
under the condition that the target person which does not give an alarm and has a historical track with the duration time meeting a first preset condition appears in the current video frame collected by the camera, detecting whether a parking target which has a space-time association relation with the target person which does not give an alarm exists in the recorded parking targets; the historical track and the recorded parking target are identified from the historical video frame;
if so, taking the parking target which has a space-time association relation with the target personnel without alarming as the designated parking target;
determining a first history person which has an appearance time earlier than that of an unalarmed target person and is subjected to alarm processing among history persons having a space-time association relationship with a specified parking target; historical people are people identified from historical video frames;
and if the characteristic information of the target personnel is matched with the characteristic information of the first historical personnel, determining that the ID of the target personnel which is not alarmed jumps, and forbidding the alarm processing of the target personnel which is not alarmed.
In one embodiment, the processor when executing the computer program further performs the steps of:
detecting whether parking targets with parking information meeting a preset second condition exist in all recorded parking targets, and if so, determining the parking targets meeting the preset condition as parking targets which are in space-time association with target personnel not giving an alarm; wherein the parking information is identified from historical video frames;
presetting the second condition includes:
temporal and spatial.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring endpoint coordinate information of a detection frame of a parking target in a parking time period from a historical video frame;
and detecting whether the distance between the historical track of the target person without alarm and the detection frame of the parking target is within a preset range in the parking time period of the parking target.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
detecting the motor vehicle target appearing in the video frame, and judging whether the motor vehicle target is in a parking state;
and if the current motor vehicle target is in a parking state, taking the current motor vehicle target as a parking target, and recording the duration time, the parking starting time and the parking ending time of the parking state of the current parking target.
In one embodiment, the processor when executing the computer program further performs the steps of:
and storing the space-time association relation between the target personnel without alarm and the designated parking target.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and if the feature information of the target person which does not give an alarm is not matched with the feature information of the first historical person or if no parking target which has a space-time association relationship with the target person which does not give an alarm exists, sending the target person which does not give an alarm to an alarm flow.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and judging whether the target personnel without alarm is a living body target or not, and carrying out alarm processing on the target personnel without alarm under the condition that the target personnel without alarm is the living body target.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
judging whether the target personnel without alarming is a living target or not based on the space-time change relation and the motion characteristics of the target personnel without alarming; the temporal-spatial variation relationship and the motion characteristics of the target personnel without alarm are obtained from historical video frames.
The storage medium detects whether a parking target having a space-time association relation with an unalarmed target person exists in recorded parking targets under the condition that the duration of the occurrence of the historical track in the current video frame collected by the camera meets a first preset condition is determined; the historical track and the recorded parking target are identified from the historical video frame; if so, taking the parking target which has a space-time association relation with the target personnel without alarming as the designated parking target; determining a first historical person which has earlier appearance time than the target person which does not give an alarm and has been subjected to alarm processing among the historical persons which have space-time association relationship with the designated parking target; historical people are people identified from historical video frames; and if the characteristic information of the target person which does not give an alarm is matched with the characteristic information of the first historical person, determining that the ID of the target person which does not give an alarm jumps, and forbidding the target person which does not give an alarm to carry out alarm processing. According to the method and the system, personnel matching is carried out by utilizing the space-time association relation between the target personnel without alarming and the parking target, whether the target personnel without alarming at present is the alarming target with the ID jumping or not is judged, if the target personnel without alarming at present is identified as the alarming target with the ID jumping, the target personnel without alarming at present is not sent into an alarming flow, and the problem of repeated alarming on the same pedestrian caused by the ID jumping of the pedestrian is effectively avoided.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.
It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the patent protection. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (11)

1. A repeated alarm optimization processing method is characterized by comprising the following steps:
under the condition that the duration of the occurrence of the historical track in the current video frame acquired by the camera meets the condition of target persons which are not alarmed under a first preset condition, detecting whether parking targets which have a space-time association relationship with the target persons which are not alarmed exist in the recorded parking targets; the historical track and the recorded parking target are identified from historical video frames;
if so, taking the parking target with space-time association relation with the target personnel without alarm as a designated parking target;
determining a first history person which has been subjected to alarm processing and has an appearance time earlier than the target person without alarm, among history persons having a spatiotemporal association relationship with the designated parking target; the historical people are people identified from the historical video frames;
and if the characteristic information of the target person which does not give the alarm is matched with the characteristic information of the first historical person, determining that the ID of the target person which does not give the alarm jumps, and forbidding the alarm processing of the target person which does not give the alarm.
2. The repetitive alert optimization process of claim 1, wherein the detecting of the presence of a parking target having a spatiotemporal relationship with the target person not being alerted among the recorded parking targets comprises the steps of:
detecting whether parking targets with parking information meeting a preset second condition exist in all recorded parking targets, and if so, determining the parking targets meeting the preset condition as parking targets which are in space-time association with target persons not giving an alarm; wherein the parking information is identified from the historical video frames;
the preset second condition includes:
temporal and spatial.
3. The repeated alarm optimization processing method according to claim 2, wherein the step of detecting whether the parking information has the parking target meeting a preset second condition comprises the following steps:
acquiring endpoint coordinate information of a detection frame of the parking target in a parking time period from the historical video frame;
detecting whether the distance between the historical track of the target person without alarm and the detection frame of the parking target is within a preset range in the parking time period of the parking target.
4. The repetitive alert optimization process of claim 1, further comprising:
detecting a motor vehicle target appearing in a video frame, and judging whether the motor vehicle target is in a parking state;
and if the current motor vehicle target is in a parking state, taking the current motor vehicle target as a parking target, and recording the duration time, the parking starting time and the parking ending time of the parking state of the current parking target.
5. The repetitive alert optimization process of claim 1, further comprising:
and storing the space-time association relationship between the target personnel without alarm and the designated parking target.
6. The repetitive alarm optimization process of claim 1, further comprising:
if the feature information of the target person which does not give an alarm is not matched with the feature information of the first historical person or if the parking target which has a space-time association relationship with the target person which does not give an alarm does not exist, sending the target person which does not give an alarm to an alarm process.
7. The repetitive alarm optimization method of claim 6, wherein the step of sending the target person who is not alarmed to an alarm process comprises the steps of:
and judging whether the target personnel without alarm is a living target or not, and carrying out alarm processing on the target personnel without alarm under the condition that the target personnel without alarm is the living target.
8. The repetitive alarm optimization processing method of claim 7, wherein the judging whether the target person who is not alarmed is a living object comprises the steps of:
judging whether the target personnel without alarm is a living target or not based on the space-time change relation and the motion characteristics of the target personnel without alarm; and the temporal-spatial variation relation and the motion characteristics of the target personnel without alarm are obtained from the historical video frames.
9. A repeat alarm optimization device, comprising: the device comprises a detection module, a designation module, a determination module and a matching module;
the detection module is used for detecting whether a parking target which has a space-time association relation with an unalarmed target person exists in recorded parking targets under the condition that the duration of the occurrence of the historical track in the current video frame acquired by the camera meets a first preset condition is determined; the historical track and the recorded parking target are identified from historical video frames;
the designated module is used for taking the parking target which has a space-time association relationship with the target personnel who do not give an alarm as a designated parking target if the designated module is used for taking the parking target as the designated parking target;
the determining module is used for determining a first historical person which has an appearance time earlier than that of the target person without the alarm and is subjected to alarm processing in historical persons having space-time association relation with the specified parking target; the historical people are people identified from the historical video frames;
and the matching module is used for determining that the ID of the target person who does not give an alarm jumps and forbidding the alarm processing of the target person who does not give an alarm if the characteristic information of the target person who does not give an alarm is matched with the characteristic information of the first historical person.
10. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 8 when executing the computer program.
11. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, performing the steps of the method of any one of claims 1 to 8.
CN202210698421.0A 2022-06-20 2022-06-20 Repeat alarm optimization processing method and device, computer equipment and storage medium Pending CN115272951A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210698421.0A CN115272951A (en) 2022-06-20 2022-06-20 Repeat alarm optimization processing method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210698421.0A CN115272951A (en) 2022-06-20 2022-06-20 Repeat alarm optimization processing method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115272951A true CN115272951A (en) 2022-11-01

Family

ID=83760609

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210698421.0A Pending CN115272951A (en) 2022-06-20 2022-06-20 Repeat alarm optimization processing method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115272951A (en)

Similar Documents

Publication Publication Date Title
US10930151B2 (en) Roadside parking management method, device, and system based on multiple cameras
US8189049B2 (en) Intrusion alarm video-processing device
JP6954420B2 (en) Information processing equipment, information processing methods, and programs
CN109345829B (en) Unmanned vehicle monitoring method, device, equipment and storage medium
CN111738240A (en) Region monitoring method, device, equipment and storage medium
US10997422B2 (en) Information processing apparatus, information processing method, and program
WO2018179202A1 (en) Information processing device, control method, and program
KR20190046351A (en) Method and Apparatus for Detecting Intruder
CN111339901B (en) Image-based intrusion detection method and device, electronic equipment and storage medium
KR101454644B1 (en) Loitering Detection Using a Pedestrian Tracker
CN111524350B (en) Method, system, terminal device and medium for detecting abnormal driving condition of vehicle and road cooperation
CN111126153A (en) Safety monitoring method, system, server and storage medium based on deep learning
CN111666821A (en) Personnel gathering detection method, device and equipment
CN110751809A (en) Construction safety monitoring method and related product
CN109446926A (en) A kind of traffic monitoring method and device, electronic equipment and storage medium
KR102494953B1 (en) On-device real-time traffic signal control system based on deep learning
CN117495896A (en) Method and system for detecting abnormal track of pedestrian in traffic environment
CN115272951A (en) Repeat alarm optimization processing method and device, computer equipment and storage medium
JP2005284652A (en) Video monitoring method and apparatus using moving vector
CN112560658B (en) Early warning method, early warning device, electronic equipment and computer readable storage medium
CN113469080A (en) Individual, group and scene interactive collaborative perception method, system and equipment
JP7347481B2 (en) Information processing device, information processing method, and program
CN117474983B (en) Early warning method based on light-vision linkage and related device
KR102347338B1 (en) Method, apparatus and computer-readable recording medium for obtaining movement path information of a dangerous object
JPH06301782A (en) Monitor device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination