CN116597385B - Abnormal behavior analysis method and system - Google Patents
Abnormal behavior analysis method and system Download PDFInfo
- Publication number
- CN116597385B CN116597385B CN202310650995.5A CN202310650995A CN116597385B CN 116597385 B CN116597385 B CN 116597385B CN 202310650995 A CN202310650995 A CN 202310650995A CN 116597385 B CN116597385 B CN 116597385B
- Authority
- CN
- China
- Prior art keywords
- gesture
- target
- area
- bias
- speed
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 36
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 32
- 230000000694 effects Effects 0.000 claims abstract description 60
- 238000012544 monitoring process Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012806 monitoring device Methods 0.000 claims description 31
- 230000009471 action Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000007306 turnover Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention is applicable to the field of computers, and provides an abnormal behavior analysis method and system, wherein the method comprises the following steps: acquiring target activity information in a set junction region of a main region and a bias region, wherein the bias region is positioned in a bias direction of the main region, and the target activity information is used for representing the activity condition of an active target in the set junction region; when it is determined that an active target in a set junction area enters a first subarea according to the target activity information, a first control instruction is generated, wherein the first control instruction is used for controlling first monitoring equipment acting on a bias area, and the first subarea is a part of the set junction area, which is located in the bias area, and the beneficial effects of the invention are that: the method does not need to cover the large area to be analyzed in a full-disc manner, avoids monitoring limitation limited to the position of the movable outlet, and realizes effective identification of the article circulation.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to an abnormal behavior analysis method and system.
Background
At present, behavior analysis in the area range is an important means for ensuring the safe operation of the assets and machines in the area, and the behavior can be supervised and standardized through the behavior analysis.
For example, through a monitoring system, the images can be checked through a smart phone, and meanwhile, the images are automatically identified, stored and automatically alarmed; the video data is transmitted back to the control host through the 4G/5G/WIFI, and the host can perform operations such as real-time watching, inputting, playback, calling out and storing on the images, so that video monitoring of mobile interconnection is realized.
However, based on the above prior art, it is noted that, when the current video monitoring system circulates an abnormal channel (such as an abnormal exit) of an object passing area, one prior art needs to cover the whole area, and the method has large recognition operand and is easy to miss; in the other prior art, a monitoring system is specially arranged at the abnormal outlet position, but the method can not identify the circulation behavior of the article far away from the abnormal outlet (for example, throwing objects at a position with a certain distance from the abnormal outlet), so as to solve the defects, and provide an abnormal behavior analysis method and system.
Disclosure of Invention
The embodiment of the invention aims to provide an abnormal behavior analysis method and system, and aims to solve the problems in the background technology.
The embodiment of the invention is realized in such a way that, on the one hand, the method for analyzing the abnormal behavior comprises the following steps:
acquiring target activity information in a set junction region of a main region and a bias region, wherein the bias region is positioned in a bias direction of the main region, and the target activity information is used for representing the activity condition of an active target in the set junction region;
when it is determined that an active target in a set junction area enters a first subarea according to the target activity information, generating a first control instruction, wherein the first control instruction is used for controlling first monitoring equipment acting on a bias area, and the first subarea is a part of the set junction area, which is positioned in the bias area;
controlling a first monitoring device to capture a first gesture of a first movable target within a variable local area according to a first control instruction, wherein the variable local area is determined according to a moving speed of the first movable target, and the variable local area at least covers an activity outlet of the bias area;
based on the captured first gesture, judging whether the first gesture accords with a set gesture, wherein the set gesture comprises a picking and placing gesture;
if yes, generating an article circulation prompt, wherein the article circulation prompt is used for prompting the movable outlet to be about to associate the business turn over of an article.
As a further aspect of the present invention, the method further includes:
identifying a first moment when the first gesture meets a set gesture;
extracting a first deflection angle corresponding to a first moment in an action log of first monitoring equipment;
extracting a first relative angle corresponding to a first posture at a first moment, wherein the first relative angle is relative to the deflection angle of the first monitoring equipment according to the first relative angle;
determining a first direction corresponding to the first gesture according to the relative angle and the first deflection angle;
determining a possible drop point of an article according to the first direction;
and generating a second control instruction according to the possible drop points so as to control a second monitoring device acting on the movable outlet to acquire drop point distribution information of an article.
As still further aspects of the present invention, after generating the item flow alert, the method further comprises:
displaying the article circulation prompt on a designated device, wherein the designated device comprises a central control screen of a main area;
and acquiring a first setting operation of the appointed equipment, and displaying the drop point distribution information based on the appointed equipment, wherein the drop point distribution information is sent to the appointed equipment by the second monitoring equipment.
As a still further aspect of the present invention, the method further includes:
judging whether an activity target passes through a first virtual boundary according to the target activity information, wherein the first virtual boundary is a virtual boundary of a main area and a bias area;
if yes, judging whether the residence time of the corresponding movable target in the bias area reaches the set time according to the first distinguishing characteristic of the corresponding movable target;
if yes, determining that the movable target in the set junction area enters the first subarea.
As a further aspect of the present invention, the controlling the first monitoring device to capture the first gesture of the first moving target within the variable local area according to the first control instruction specifically includes:
issuing a first control instruction to first monitoring equipment, wherein the first control instruction carries a second distinguishing feature of a first movable target and a limited subarea determined according to a first position of the first movable target, and the limited subarea is contained in a variable local range;
indicating the first monitoring device to align the monitoring range with the limited subarea so as to identify a third distinguishing feature of the first activity target according to the second distinguishing feature, wherein the third distinguishing feature is a local distinguishing feature;
identifying a first section in the first moving object where the gesture may occur according to the third distinguishing feature;
the first section is positioned, and a first gesture of a first moving target within the first section is captured.
As a further aspect of the present invention, the method further includes:
identifying a first speed of the moving target in a set junction area according to the target moving information;
and identifying the size between the first speed and the set average speed, and determining a variable local area range according to the identification result, wherein when the first speed is greater than the set average speed, the variable local area range is greater than the standard local area range, and the set average speed is matched with the standard local area range.
As a further aspect of the present invention, the determining the variable local area range according to the identification result specifically includes:
and when the identification result shows that the first speed is not greater than the set average speed, taking the standard local area range as a variable local area range of the first movable target.
As a further aspect of the present invention, the specific method further includes:
and when the identification result shows that the first speed is greater than the set average speed, determining a speed section in which the first speed is positioned, inquiring a corresponding speed range conversion coefficient according to the speed section, and calculating a variable local range corresponding to the first speed by taking an active outlet as a base point according to the inquiry result and a standard local range.
As a further aspect of the present invention, in another aspect, an abnormal behavior analysis system includes:
the information acquisition module is used for acquiring target activity information in a set junction area of the main area and the bias area, the bias area is positioned in a bias direction of the main area, and the target activity information is used for representing the activity condition of an activity target in the set junction area;
the condition judging and instruction generating module is used for generating a first control instruction when the movable target in the set junction area enters a first subarea according to the target activity information, wherein the first control instruction is used for controlling first monitoring equipment acting on the offset area, and the first subarea is a part of the set junction area, which is positioned in the offset area;
an instruction control and gesture capturing module for controlling a first monitoring device to capture a first gesture of a first moving target within a variable local range according to a first control instruction, the variable local range being determined according to a moving speed of the first moving target, the variable local range covering at least a moving outlet of the bias area;
the gesture judging module is used for judging whether the first captured gesture accords with a set gesture or not based on the first captured gesture, wherein the set gesture comprises a picking and placing gesture;
and the prejudgment prompting module is used for generating an article circulation prompting when the captured first gesture accords with the set gesture, wherein the article circulation prompting is used for prompting the movement of the exit to be related to the in-out circulation of an article.
Further optionally, the system further comprises a drop point acquisition module, wherein the drop point acquisition module is specifically configured to perform the following steps:
identifying a first moment when the first gesture meets a set gesture;
extracting a first deflection angle corresponding to a first moment in an action log of first monitoring equipment;
extracting a first relative angle corresponding to a first posture at a first moment, wherein the first relative angle is relative to the deflection angle of the first monitoring equipment according to the first relative angle;
determining a first direction corresponding to the first gesture according to the relative angle and the first deflection angle;
determining a possible drop point of an article according to the first direction;
and generating a second control instruction according to the possible drop points so as to control a second monitoring device acting on the movable outlet to acquire drop point distribution information of an article.
According to the method and the system for analyzing the abnormal behavior, provided by the embodiment of the invention, through acquiring the target activity information in the set junction area of the main area and the bias area, when the existence of the activity target in the set junction area is judged to enter the first subarea according to the target activity information, a first control instruction is generated so as to control first monitoring equipment acting on the bias area; controlling a first monitoring device to capture a first gesture of a first movable target within a variable local area according to a first control instruction, wherein the variable local area is determined according to a moving speed of the first movable target, and the variable local area at least covers an activity outlet of the bias area; based on the captured first gesture, when the first gesture is judged to be in accordance with the set gesture, an article circulation prompt is generated, and the article circulation prompt prompts that the movable outlet is about to be associated with the in-out circulation of an article can respectively carry out joint analysis based on the out-of-range, the movable speed and the gesture of the movable target, so that the large area to be analyzed is not required to be covered in a whole disc, the monitoring limitation limited to the position of the movable outlet is avoided, and the effective identification of circulation of the article through the movable outlet in and out of the large area to be analyzed is realized.
Drawings
FIG. 1 is a main flow chart of an abnormal behavior analysis method.
FIG. 2 is a flow chart of collecting drop point distribution information of an item in an abnormal behavior analysis method.
FIG. 3 is a flow chart of a method of abnormal behavior analysis capturing a first gesture of a first moving object within a variable local area.
FIG. 4 is a flow chart of a method of anomaly analysis for identifying a first velocity of an active object at a set interface region.
FIG. 5 is a flow chart of a method for determining a variable local area range based on recognition results in an abnormal behavior analysis method.
Fig. 6 is a main structural diagram of an abnormal behavior analysis system.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Specific implementations of the invention are described in detail below in connection with specific embodiments.
The abnormal behavior analysis method and system provided by the invention solve the technical problems in the background technology.
As shown in fig. 1, a main flow chart of an abnormal behavior analysis method according to an embodiment of the present invention is provided, where the abnormal behavior analysis method includes:
step S10: acquiring target activity information in a set junction region of a main region and a bias region, wherein the bias region is positioned in a bias direction of the main region, and the target activity information is used for representing the activity condition of an active target in the set junction region; the main area and the bias area generally form a large area where abnormal behaviors are to be analyzed, and the main area is generally an area with more artificial activities, such as a main channel; the outlet of the main area is the normal inlet and outlet of the large area to be analyzed;
the bias area is generally an area which is not generally involved in conventional artificial activities, the main area and the bias area are adjacent areas, and the junction area is set as an area formed by taking a part of the main area and the bias area respectively; the target activity information includes image information; the infrared detection technology has the characteristics of long acting distance, strong anti-interference capability, capability of carrying out all-weather monitoring and the like, and is widely applied to the technical fields of security monitoring, target identification and the like;
step S11: when it is determined that an active target in a set junction area enters a first subarea according to the target activity information, generating a first control instruction, wherein the first control instruction is used for controlling first monitoring equipment acting on a bias area, and the first subarea is a part of the set junction area, which is positioned in the bias area; the moving object generally refers to a related person; when a movable target enters the first subarea, the movable target is indicated to have a certain behavior characteristic, and the behavior characteristic may be related to a movable outlet of the offset area, for example, the movable outlet is used for carrying articles in person or matching with illegal operations such as carrying articles, etc., and monitoring analysis may be needed; the event exit generally refers to an exit of a window or other open area (e.g., an exit for normal cargo transportation), etc.;
step S12: controlling a first monitoring device to capture a first gesture of a first movable target within a variable local area according to a first control instruction, wherein the variable local area is determined according to a moving speed of the first movable target, the variable local area at least covers a movable outlet of the bias area, and the first movable target is related to the movable target entering the first subarea; considering that the movable target can be used for carrying articles in person or matching with articles to be carried through the movable outlet and other illegal operations, the first movable target can be the movable target, and can also be a movable target matched with the movable target entering the first subarea, and the first movable target and the movable target can be matched with the movable target entering the first subarea to complete the illegal operations; a so-called variable local area range, i.e. the local area range is an area determined based on the first moving object, and the important determined parameter is the moving speed of the first moving object, the variable local area range being in the range from the set interface area to the moving exit, and the larger the moving speed, the faster the first gesture may be made, and thus may be made within a certain distance from the moving exit, or the larger the moving speed, the larger the absolute speed of the first gesture, and thus the farther from the moving exit, the first gesture may be made;
step S13: based on the captured first gesture, judging whether the first gesture accords with a set gesture, wherein the set gesture comprises a picking and placing gesture; the taking and placing gesture comprises at least one of a parabolic gesture, a taking gesture and the like, and if the parabolic is based on high altitude, the behavior is obviously forbidden; the parabolic material is generally based on a large area to be analyzed, and the difficulty of circulation of the article through the movable outlet inside and outside the large area to be analyzed is considered, so that the circulation of the article is generally completed at a non-high altitude;
step S14: if yes, generating an article circulation prompt, wherein the article circulation prompt is used for prompting the movable outlet to be about to associate the business turn over of an article. I.e., there may be an offending flow of items within the event exit. At this time, corresponding prompts are required to be made by the manager in the large area to be analyzed so as to interfere or check corresponding commodity circulation conditions.
When the method is applied, the target activity information in the set junction area of the main area and the bias area is obtained, and when the existence of the activity target in the set junction area enters the first subarea is judged according to the target activity information, a first control instruction is generated so as to control first monitoring equipment acting on the bias area; controlling a first monitoring device to capture a first gesture of a first movable target within a variable local area according to a first control instruction, wherein the variable local area is determined according to a moving speed of the first movable target, and the variable local area at least covers an activity outlet of the bias area; based on the captured first gesture, when the first gesture is judged to be in accordance with the set gesture, an article circulation prompt is generated, and the article circulation prompt prompts that the movable outlet is about to be associated with the in-out circulation of an article can respectively carry out joint analysis based on the out-of-range, the movable speed and the gesture of the movable target, so that the large area to be analyzed is not required to be covered in a whole disc, the monitoring limitation limited to the position of the movable outlet is avoided, and the effective identification of circulation of the article through the movable outlet in and out of the large area to be analyzed is realized.
As shown in fig. 2, as a preferred embodiment of the present invention, the method further includes:
step S21: identifying a first moment when the first gesture meets a set gesture; the first moment can be extracted from the image information, and the recorded time stamp is correspondingly recorded in the image information;
step S22: extracting a first deflection angle corresponding to a first moment in an action log of first monitoring equipment; in the first monitoring device, rotation information, power information, coverage range and the like of the actions thereof are corresponding to the time of the actions thereof, and are recorded in action logs respectively;
step S23: extracting a first relative angle corresponding to a first posture at a first moment, wherein the first relative angle is relative to the deflection angle of the first monitoring equipment according to the first relative angle; since the first angle of deflection generally refers to an absolute angle, the relative angle is the relative angle of the first pose to the first monitoring device; generally, the angle in the horizontal direction is determined, and when the moving object does not move much, the angle of the first posture is considered not to deviate from the angle of the moving object much, and the angle of the moving object is regarded as a first relative angle; when the action of the movable target is large, the first gesture is considered to have large access between the direction of the movable target and the first gesture, and the first relative angle of the first gesture is recognized directly; for the orientation of the moving object, a plurality of angle reference landmarks (such as a plurality of parallel lines) are generally arranged in the variable local range, and the angle of each angle reference landmark relative to the first monitoring device is known, so that only the relative angle between the moving object and the angle reference landmark needs to be determined, the relative angle is not changed along with the change of the size of the image, the relative angle in the image can be extracted for identification, and in addition, when the moving object acts greatly, the relative angle of the moving object relative to the angle reference landmark at the action part of the moving object can be directly identified;
step S24: determining a first direction corresponding to the first gesture according to the relative angle and the first deflection angle; the first direction corresponding to the first gesture, namely the absolute horizontal deflection angle corresponding to the first gesture, can be determined through the relative angle and the first deflection angle, and the absolute horizontal deflection angle is determined through approximate recognition, so that the corresponding approximate direction is determined. For example, the relative angle is about-20 degrees (in the counterclockwise direction), and the first deflection angle is in the southward direction, so that the first direction corresponding to the first posture is about 20 degrees from the southward direction;
step S25: determining a possible drop point of an article according to the first direction; the possible drop points of the article should follow the direction of extension in the same direction as the first direction, for angles in the vertical direction which are generally not considered here, default to the free fall, which determines the time to land; however, for the second monitoring device, its monitoring range may cover the corresponding positional deviation as long as the direction is determined;
step S26: and generating a second control instruction according to the possible drop points so as to control a second monitoring device acting on the movable outlet to acquire drop point distribution information of an article. The possible drop points are mainly determined based on the first direction, and the possible drop points are generally within the area range where a certain first specific first direction is located; the second control instruction should have control content therein that is directed in the first direction. The second monitoring device is generally arranged at the top of the movable outlet, so that the second monitoring device can monitor the outside and the inside, and a plurality of second monitoring devices can be arranged. In fact, the final reasonable tracing of the object in the first posture can be performed through the final obtaining of the drop point distribution information.
By further, after generating the item flow cues, the method further comprises:
step S31: displaying the article circulation prompt on a designated device, wherein the designated device comprises a central control screen of a main area;
step S32: and acquiring a first setting operation of the appointed equipment, and displaying the drop point distribution information based on the appointed equipment, wherein the drop point distribution information is sent to the appointed equipment by the second monitoring equipment. A first setting operation such as a view click operation or the like;
after the article circulation prompt is displayed, relevant personnel in the main control area are conveniently led to be alert, and after the relevant personnel perform first setting operation on the designated equipment, drop point distribution information can be displayed, so that timely processing based on drop points is facilitated.
As a preferred embodiment of the present invention, the method further comprises:
step S40: judging whether an activity target passes through a first virtual boundary according to the target activity information, wherein the first virtual boundary is a virtual boundary of a main area and a bias area;
step S41: if yes, judging whether the residence time of the corresponding movable target in the bias area reaches the set time according to the first distinguishing characteristic of the corresponding movable target;
step S42: if yes, determining that the movable target in the set junction area enters the first subarea.
It should be understood that the virtual dividing line is between the main area and the offset area, that is, is a demarcation line on the electronic map including the main area and the offset position, and the demarcation line is used as a determination reference for determining whether the moving object passes or not, and by means of the stay time, the situation that a moving object passes by accidentally and is misidentified can be avoided, which is beneficial to reducing the processing amount of invalid data.
As shown in fig. 3, as a preferred embodiment of the present invention, the controlling the first monitoring device to capture the first gesture of the first moving object within the variable local area according to the first control instruction specifically includes:
step S121: issuing a first control instruction to first monitoring equipment, wherein the first control instruction carries a second distinguishing feature of a first movable target and a limited subarea determined according to a first position of the first movable target, and the limited subarea is contained in a variable local range; by defined sub-area is generally meant a virtual sub-area determined from the position of the first movable object, e.g. a circular area surrounding the ground-contacting position where the first object is located; the second distinguishing feature may be at least one of face information and dressing information; the first location may be determined from the second distinguishing characteristic; the second distinguishing feature may be used to identify a location of the first moving object; the second distinguishing feature may be the first distinguishing feature;
step S122: indicating the first monitoring device to align the monitoring range with the limited subarea so as to identify a third distinguishing feature of the first activity target according to the second distinguishing feature, wherein the third distinguishing feature is a local distinguishing feature; in short, the third distinguishing feature may be a part of the second distinguishing feature, or may be another feature located in the same moving object and identified according to the second distinguishing feature, for example, the third distinguishing feature is face information or dressing information in the first region end, or arm feature information (for example, carrying a special tool, such as a glove, etc.); the third distinguishing feature is mainly used for locating a section where the first activity target gesture may occur;
step S123: identifying a first section in the first moving object where the gesture may occur according to the third distinguishing feature; the first section is the position of a certain part of the first movable target;
step S124: the first section is positioned, and a first gesture of a first moving target within the first section is captured. The first gesture in the first section can limit the possible positions of the first gesture through the positioning section, so as to facilitate accurate capture, for example, the first section is more than half of the body so as to facilitate capturing the departure point of the first gesture relative to the first movable target;
when the method is applied, the first monitoring equipment is controlled according to the first control instruction, the first monitoring equipment is gradually moved from large to small layer by layer, the limited subareas and the first sections in the variable local range are respectively identified, and then the first monitoring equipment is moved to the first gesture, so that the first gesture is conveniently identified, and the identification accuracy of the first gesture is improved.
As shown in fig. 4, as a preferred embodiment of the present invention, the method further includes:
step S131: identifying a first speed of the moving target in a set junction area according to the target moving information; the first speed can be determined according to the time spent between at least two recognition points, for example, the first recognition point and the second recognition point are respectively positioned at the positions of the set junction area, the recognition points are provided with landmarks, the distance between the first recognition point and the second recognition point is known, and the corresponding time spent by detecting the time spent by the movable target respectively positioned at the two positions can be obtained, so that the first speed is calculated;
step S132: identifying the size between the first speed and the set average speed, and determining a variable local area range according to the identification result, wherein when the first speed is greater than the set average speed, the variable local area range is greater than the standard local area range, and the set average speed is matched with the standard local area range;
it will be appreciated that for the determination of the first speed it is most likely that it will determine how far or near the distance between the active exit and the active position within the bias zone, since the more the speed the more remote the position of the pick and place action can be from the active exit, the less likely it will be to be found, and thus the present embodiment determines the size of the variable local range based on the first speed and the size of the set mean speed, so that the identified range can reasonably match the first speed.
As shown in fig. 5, as a preferred embodiment of the present invention, the determining the variable local area range according to the identification result specifically includes:
step S1321: when the identification result shows that the first speed is not greater than the set average speed, taking the standard local range as a variable local range of a first movable target;
step S1322: and when the identification result shows that the first speed is greater than the set average speed, determining a speed section in which the first speed is positioned, inquiring a corresponding speed range conversion coefficient according to the speed section, and calculating a variable local range corresponding to the first speed by taking an active outlet as a base point according to the inquiry result and a standard local range. Illustratively, the speed ranges are 0-1m/s, 1-2m/s,2-3m/s,3-4m/s, greater than 4m/s, respectively; wherein 1-2m/s is in the speed range of normal walking of a person, and the speed range is used as a speed interval corresponding to the standard local area range; the speed range conversion coefficients are thus respectively: 1. 1, 1.3, 1.6, 2; wherein the speed range conversion factor is used primarily for stretching the length of the standard local range.
The present embodiment actually provides a method for determining local ranges of different sizes (lengths) based on different speeds, which can be reasonably applied to the first speed, because the larger the first speed is, the more the related behavior is considered to be possibly added with the first speed, so the related behavior can be implemented at a position farther from the activity exit, so different variable local ranges need to be determined for the different first speeds, thereby avoiding missing recognition and excessively expanding the recognition range, and more fitting and intelligentizing the capture of the first gesture.
As another preferred embodiment of the present invention, as shown in fig. 6, in another aspect, an abnormal behavior analysis system, the system includes:
the information acquisition module 100 is configured to acquire target activity information in a set interface region of a main region and a bias region, where the bias region is located in a bias azimuth of the main region, and the target activity information is used to characterize an activity condition of an active target in the set interface region;
the condition judging and instruction generating module 200 is configured to generate a first control instruction when it is judged that an active target in a set junction area enters a first sub-area according to the target activity information, where the first control instruction is used to control a first monitoring device acting on a bias area, and the first sub-area is a portion of the set junction area located in the bias area;
an instruction control and gesture capturing module 300 for controlling the first monitoring device to capture a first gesture of the first movable target within a variable local range according to the first control instruction, the variable local range being determined according to a movement speed of the first movable target, the variable local range covering at least the movable exit of the bias area;
a gesture determining module 400, configured to determine, based on the captured first gesture, whether the captured first gesture corresponds to a set gesture, where the set gesture includes a picking and placing gesture;
the pre-judgment prompting module 500 is configured to generate an item circulation prompt when the captured first gesture accords with the set gesture, where the item circulation prompt is used to prompt the activity exit to be about to transfer an item.
It should be noted that, with reference to the foregoing embodiments, for a description of the implementation of the present system, reference may be made to the foregoing description of the implementation of the method applied by the present system, and the description of the implementation of the present system will not be repeated herein.
As shown in fig. 6, the system further includes a landing point acquisition module 600, specifically configured to perform the following steps:
identifying a first moment when the first gesture meets a set gesture;
extracting a first deflection angle corresponding to a first moment in an action log of first monitoring equipment;
extracting a first relative angle corresponding to a first posture at a first moment, wherein the first relative angle is relative to the deflection angle of the first monitoring equipment according to the first relative angle;
determining a first direction corresponding to the first gesture according to the relative angle and the first deflection angle;
determining a possible drop point of an article according to the first direction;
and generating a second control instruction according to the possible drop points so as to control a second monitoring device acting on the movable outlet to acquire drop point distribution information of an article.
The embodiment of the invention provides an abnormal behavior analysis method, and provides an abnormal behavior analysis system based on the abnormal behavior analysis method, wherein the abnormal behavior analysis system is used for generating a first control instruction to control a first monitoring device acting on a bias area when a target activity information in a set junction area of a main area and the bias area is obtained and the existence of an activity target in the set junction area is judged to enter a first sub-area according to the target activity information; controlling a first monitoring device to capture a first gesture of a first movable target within a variable local area according to a first control instruction, wherein the variable local area is determined according to a moving speed of the first movable target, and the variable local area at least covers an activity outlet of the bias area; based on the captured first gesture, when the first gesture is judged to be in accordance with the set gesture, an article circulation prompt is generated, and the article circulation prompt prompts that the movable outlet is about to be associated with the in-out circulation of an article can respectively carry out joint analysis based on the out-of-range, the movable speed and the gesture of the movable target, so that the large area to be analyzed is not required to be covered in a whole disc, the monitoring limitation limited to the position of the movable outlet is avoided, and the effective identification of circulation of the article through the movable outlet in and out of the large area to be analyzed is realized.
In order to be able to load the method and system described above to function properly, the system may include more or less components than those described above, or may combine some components, or different components, in addition to the various modules described above, for example, may include input and output devices, network access devices, buses, processors, memories, and the like.
The processor may be a central processing unit (CentralProcessingUnit, CPU), other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegratedCircuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the above system, and various interfaces and lines are used to connect the various parts.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (9)
1. A method of abnormal behavior analysis, the method comprising:
acquiring target activity information in a set junction region of a main region and a bias region, wherein the bias region is positioned in a bias direction of the main region, and the target activity information is used for representing the activity condition of an active target in the set junction region;
when it is determined that an active target in a set junction area enters a first subarea according to the target activity information, generating a first control instruction, wherein the first control instruction is used for controlling first monitoring equipment acting on a bias area, and the first subarea is a part of the set junction area, which is positioned in the bias area;
controlling a first monitoring device to capture a first gesture of a first movable target within a variable local area according to a first control instruction, wherein the variable local area is determined according to a moving speed of the first movable target, the variable local area at least covers a movable outlet of the bias area, and the first movable target is related to the movable target entering the first subarea;
based on the captured first gesture, judging whether the first gesture accords with a set gesture, wherein the set gesture comprises a picking and placing gesture;
if yes, generating an article circulation prompt, wherein the article circulation prompt is used for prompting an activity outlet to be about to associate the business turn over of an article;
the controlling the first monitoring device to capture the first gesture of the first moving target within the variable local range according to the first control instruction specifically includes:
issuing a first control instruction to first monitoring equipment, wherein the first control instruction carries a second distinguishing feature of a first movable target and a limited subarea determined according to a first position of the first movable target, and the limited subarea is contained in a variable local range;
indicating the first monitoring device to align the monitoring range with the limited subarea so as to identify a third distinguishing feature of the first activity target according to the second distinguishing feature, wherein the third distinguishing feature is a local distinguishing feature;
identifying a first section in the first moving object where the gesture may occur according to the third distinguishing feature;
the first section is positioned, and a first gesture of a first moving target within the first section is captured.
2. The abnormal behavior analysis method according to claim 1, wherein the method further comprises:
identifying a first moment when the first gesture meets a set gesture;
extracting a first deflection angle corresponding to a first moment in an action log of first monitoring equipment;
extracting a first relative angle corresponding to a first posture at a first moment, wherein the first relative angle is relative to the deflection angle of the first monitoring equipment according to the first relative angle;
determining a first direction corresponding to the first gesture according to the relative angle and the first deflection angle;
determining a possible drop point of an article according to the first direction;
and generating a second control instruction according to the possible drop points so as to control a second monitoring device acting on the movable outlet to acquire drop point distribution information of an article.
3. The abnormal behavior analysis method according to claim 2, wherein after generating the item flow hint, the method further comprises:
displaying the article circulation prompt on a designated device, wherein the designated device comprises a central control screen of a main area;
and acquiring a first setting operation of the appointed equipment, and displaying the drop point distribution information based on the appointed equipment, wherein the drop point distribution information is sent to the appointed equipment by the second monitoring equipment.
4. The abnormal behavior analysis method according to claim 1, wherein the method further comprises:
judging whether an activity target passes through a first virtual boundary according to the target activity information, wherein the first virtual boundary is a virtual boundary of a main area and a bias area;
if yes, judging whether the residence time of the corresponding movable target in the bias area reaches the set time according to the first distinguishing characteristic of the corresponding movable target;
if yes, determining that the movable target in the set junction area enters the first subarea.
5. The abnormal behavior analysis method according to claim 1, wherein the method further comprises:
identifying a first speed of the moving target in a set junction area according to the target moving information;
and identifying the size between the first speed and the set average speed, and determining a variable local area range according to the identification result, wherein when the first speed is greater than the set average speed, the variable local area range is greater than the standard local area range, and the set average speed is matched with the standard local area range.
6. The abnormal behavior analysis method according to claim 5, wherein the determining the variable local area range according to the identification result specifically includes:
and when the identification result shows that the first speed is not greater than the set average speed, taking the standard local area range as a variable local area range of the first movable target.
7. The abnormal behavior analysis method according to claim 5, wherein the specific steps further include:
and when the identification result shows that the first speed is greater than the set average speed, determining a speed section in which the first speed is positioned, inquiring a corresponding speed range conversion coefficient according to the speed section, and calculating a variable local range corresponding to the first speed by taking an active outlet as a base point according to the inquiry result and a standard local range.
8. An abnormal behavior analysis system, the system comprising:
the information acquisition module is used for acquiring target activity information in a set junction area of the main area and the bias area, the bias area is positioned in a bias direction of the main area, and the target activity information is used for representing the activity condition of an activity target in the set junction area;
the condition judging and instruction generating module is used for generating a first control instruction when the movable target in the set junction area enters a first subarea according to the target activity information, wherein the first control instruction is used for controlling first monitoring equipment acting on the offset area, and the first subarea is a part of the set junction area, which is positioned in the offset area;
an instruction control and gesture capturing module for controlling a first monitoring device to capture a first gesture of a first moving target within a variable local range according to a first control instruction, the variable local range being determined according to a moving speed of the first moving target, the variable local range covering at least a moving outlet of the bias area;
the gesture judging module is used for judging whether the first captured gesture accords with a set gesture or not based on the first captured gesture, wherein the set gesture comprises a picking and placing gesture;
the prejudging prompt module is used for generating an article circulation prompt when the captured first gesture accords with the set gesture, wherein the article circulation prompt is used for prompting the movement of an object to be associated to the movement of the article;
the instruction control and gesture capturing module is specifically configured to:
issuing a first control instruction to first monitoring equipment, wherein the first control instruction carries a second distinguishing feature of a first movable target and a limited subarea determined according to a first position of the first movable target, and the limited subarea is contained in a variable local range;
indicating the first monitoring device to align the monitoring range with the limited subarea so as to identify a third distinguishing feature of the first activity target according to the second distinguishing feature, wherein the third distinguishing feature is a local distinguishing feature;
identifying a first section in the first moving object where the gesture may occur according to the third distinguishing feature;
the first section is positioned, and a first gesture of a first moving target within the first section is captured.
9. The abnormal behavior analysis system according to claim 8, further comprising a drop point acquisition module, the drop point acquisition module being specifically configured to perform the steps of:
identifying a first moment when the first gesture meets a set gesture;
extracting a first deflection angle corresponding to a first moment in an action log of first monitoring equipment;
extracting a first relative angle corresponding to a first posture at a first moment, wherein the first relative angle is relative to the deflection angle of the first monitoring equipment according to the first relative angle;
determining a first direction corresponding to the first gesture according to the relative angle and the first deflection angle;
determining a possible drop point of an article according to the first direction;
and generating a second control instruction according to the possible drop points so as to control a second monitoring device acting on the movable outlet to acquire drop point distribution information of an article.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310650995.5A CN116597385B (en) | 2023-06-02 | 2023-06-02 | Abnormal behavior analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310650995.5A CN116597385B (en) | 2023-06-02 | 2023-06-02 | Abnormal behavior analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116597385A CN116597385A (en) | 2023-08-15 |
| CN116597385B true CN116597385B (en) | 2024-01-23 |
Family
ID=87600760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310650995.5A Active CN116597385B (en) | 2023-06-02 | 2023-06-02 | Abnormal behavior analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116597385B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160056107A (en) * | 2014-11-11 | 2016-05-19 | 한국과학기술연구원 | Surveillance System And Method To Object And Area |
| CN110009869A (en) * | 2019-04-01 | 2019-07-12 | 珠海格力电器股份有限公司 | Monitoring method, the device and system of action message |
| JP2019133426A (en) * | 2018-01-31 | 2019-08-08 | 株式会社Uacj | Control device, abnormality detection system, control method for control device, and control program |
| CN112801579A (en) * | 2021-01-21 | 2021-05-14 | 北京顺达同行科技有限公司 | Distribution task abnormity monitoring method and device, computer equipment and storage medium |
| JP2021149313A (en) * | 2020-03-17 | 2021-09-27 | 日本信号株式会社 | Abnormality detection system |
| CN113723355A (en) * | 2021-09-14 | 2021-11-30 | 浙江大华技术股份有限公司 | Target monitoring method and device, storage medium and electronic device |
| WO2022183661A1 (en) * | 2021-03-03 | 2022-09-09 | 上海商汤智能科技有限公司 | Event detection method and apparatus, electronic device, storage medium, and program product |
| CN115690830A (en) * | 2021-07-30 | 2023-02-03 | 海信集团控股股份有限公司 | Abnormal behavior detection method and equipment |
| CN115964645A (en) * | 2023-03-16 | 2023-04-14 | 北京数通魔方科技有限公司 | Information processing method and system based on big data |
| CN116052275A (en) * | 2023-01-28 | 2023-05-02 | 北京安录国际技术有限公司 | Abnormal behavior detection method and system based on big data |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7003612B2 (en) * | 2017-12-08 | 2022-01-20 | 株式会社デンソー | Anomaly detection device and anomaly detection program |
| KR102480424B1 (en) * | 2020-10-21 | 2022-12-23 | 주식회사 올룰로 | Personal mobility having local monitogring function |
-
2023
- 2023-06-02 CN CN202310650995.5A patent/CN116597385B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160056107A (en) * | 2014-11-11 | 2016-05-19 | 한국과학기술연구원 | Surveillance System And Method To Object And Area |
| JP2019133426A (en) * | 2018-01-31 | 2019-08-08 | 株式会社Uacj | Control device, abnormality detection system, control method for control device, and control program |
| CN110009869A (en) * | 2019-04-01 | 2019-07-12 | 珠海格力电器股份有限公司 | Monitoring method, the device and system of action message |
| JP2021149313A (en) * | 2020-03-17 | 2021-09-27 | 日本信号株式会社 | Abnormality detection system |
| CN112801579A (en) * | 2021-01-21 | 2021-05-14 | 北京顺达同行科技有限公司 | Distribution task abnormity monitoring method and device, computer equipment and storage medium |
| WO2022183661A1 (en) * | 2021-03-03 | 2022-09-09 | 上海商汤智能科技有限公司 | Event detection method and apparatus, electronic device, storage medium, and program product |
| KR20220125716A (en) * | 2021-03-03 | 2022-09-14 | 상하이 센스타임 인텔리전트 테크놀로지 컴퍼니 리미티드 | Event detection methods, devices, electronic devices, storage media and program products |
| CN115690830A (en) * | 2021-07-30 | 2023-02-03 | 海信集团控股股份有限公司 | Abnormal behavior detection method and equipment |
| CN113723355A (en) * | 2021-09-14 | 2021-11-30 | 浙江大华技术股份有限公司 | Target monitoring method and device, storage medium and electronic device |
| CN116052275A (en) * | 2023-01-28 | 2023-05-02 | 北京安录国际技术有限公司 | Abnormal behavior detection method and system based on big data |
| CN115964645A (en) * | 2023-03-16 | 2023-04-14 | 北京数通魔方科技有限公司 | Information processing method and system based on big data |
Non-Patent Citations (2)
| Title |
|---|
| 《Abnormal Behavior Detection in Real-time for Advanced Driver Assistance System (ADAS) using YOLO》;May Thu Soe; Aung Zaw Min;《2022 IEEE Symposium on Industrial Electronics & Applications (ISIEA)》;全文 * |
| 《校园围栏场景下的异常行为检测系统》;李瑷嘉；彭新茗;《智能计算机与应用》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116597385A (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232320B (en) | Method and system for detecting danger of workers approaching construction machinery on construction site in real time | |
| Park et al. | Construction worker detection in video frames for initializing vision trackers | |
| US10445887B2 (en) | Tracking processing device and tracking processing system provided with same, and tracking processing method | |
| CN109325456B (en) | Target identification method, target identification device, target identification equipment and storage medium | |
| US20140369566A1 (en) | Perimeter Image Capture and Recognition System | |
| US20060215031A1 (en) | Method and system for camera autocalibration | |
| US9412025B2 (en) | Systems and methods to classify moving airplanes in airports | |
| CN110442120B (en) | Method for controlling robot to move in different scenes, robot and terminal equipment | |
| KR102074669B1 (en) | Disaster Safety Management System for Smart Factory | |
| CN106951889A (en) | Underground high risk zone moving target monitoring and management system | |
| CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
| Kim et al. | Robotic sensing and object recognition from thermal-mapped point clouds | |
| US20230386043A1 (en) | Object detection method and device using multiple area detection | |
| Katsamenis et al. | Man overboard event detection from RGB and thermal imagery: Possibilities and limitations | |
| RU2713876C1 (en) | Method and system for detecting alarm events when interacting with self-service device | |
| CN116434148B (en) | Data processing system and processing method based on Internet of things | |
| US20190096066A1 (en) | System and Method for Segmenting Out Multiple Body Parts | |
| WO2022037281A1 (en) | Real-time substation field operation monitoring and alarm system based on machine vision | |
| CN111753780B (en) | Transformer substation violation detection system and violation detection method | |
| CN117576778A (en) | Factory abnormal behavior monitoring method and system based on video stream and electronic equipment | |
| US20180336694A1 (en) | System and Method for Passive Tracking Based on Color Features | |
| KR101518314B1 (en) | Method and apparatus for video surveillance by using surveillance apparatus of unmanned aerial vehicle | |
| CN116597385B (en) | Abnormal behavior analysis method and system | |
| CN112800918A (en) | Identity recognition method and device for illegal moving target | |
| CN113068000B (en) | Video target monitoring method, device, equipment, system and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |