CN118042270A - Behavior image sensing system - Google Patents
Behavior image sensing system Download PDFInfo
- Publication number
- CN118042270A CN118042270A CN202211412660.1A CN202211412660A CN118042270A CN 118042270 A CN118042270 A CN 118042270A CN 202211412660 A CN202211412660 A CN 202211412660A CN 118042270 A CN118042270 A CN 118042270A
- Authority
- CN
- China
- Prior art keywords
- control unit
- moving object
- image
- unit
- warning
- 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
Links
- 230000033001 locomotion Effects 0.000 claims abstract description 53
- 230000006399 behavior Effects 0.000 claims description 68
- 238000012544 monitoring process Methods 0.000 claims description 21
- 230000003542 behavioural effect Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000002604 ultrasonography Methods 0.000 claims 1
- 230000003068 static effect Effects 0.000 abstract description 19
- 238000012545 processing Methods 0.000 abstract description 10
- 241001465754 Metazoa Species 0.000 description 86
- 230000000694 effects Effects 0.000 description 14
- 238000001514 detection method Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 7
- 210000003128 head Anatomy 0.000 description 7
- 210000001508 eye Anatomy 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 4
- 241000282421 Canidae Species 0.000 description 3
- 241000282335 Procyon Species 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 210000005252 bulbus oculi Anatomy 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000004886 head movement Effects 0.000 description 3
- 241000271566 Aves Species 0.000 description 2
- 241000282472 Canis lupus familiaris Species 0.000 description 2
- 241000288673 Chiroptera Species 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 2
- 241000282346 Meles meles Species 0.000 description 2
- 241000699670 Mus sp. Species 0.000 description 2
- 241000428199 Mustelinae Species 0.000 description 2
- 241000283984 Rodentia Species 0.000 description 2
- 241000282887 Suidae Species 0.000 description 2
- 241000282458 Ursus sp. Species 0.000 description 2
- 208000008784 apnea Diseases 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241000282994 Cervidae Species 0.000 description 1
- 241000282326 Felis catus Species 0.000 description 1
- 241000282339 Mustela Species 0.000 description 1
- 241000283973 Oryctolagus cuniculus Species 0.000 description 1
- 241000282320 Panthera leo Species 0.000 description 1
- 241000282373 Panthera pardus Species 0.000 description 1
- 241000282376 Panthera tigris Species 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 244000038280 herbivores Species 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000020912 omnivore Nutrition 0.000 description 1
- 244000054334 omnivore Species 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000009531 respiratory rate measurement Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention provides a behavior image sensing system, which comprises a first image capturing unit and a control unit. The first image capturing unit is used for capturing dynamic images. The control unit is electrically connected with the first image capturing unit, receives the dynamic image, and calculates the motion trail of the moving object in the dynamic image so as to judge whether the motion trail of the moving object accords with a specific dangerous behavior mode. Therefore, the behavior image sensing system of the invention does not need to capture the static image of the static object at all, does not need to judge the behavior mode of the static object, reduces the data processing amount greatly, and is suitable for any environment.
Description
Technical Field
The present invention relates to the field of influence sensing technologies, and in particular, to a behavioral image sensing system.
Background
The current remote monitoring system uses a camera to photograph a specific area, and a user can see the following events from a monitoring screen: firstly, someone or wild animals invade a specific area; secondly, the wild animal is a dangerous animal; thirdly, a person swings a punch, kicks a step or handplay; fourth, someone does not have access to a specific area. Upon the occurrence of the event, the user may immediately take strain measures.
However, the video cameras of the remote monitoring system of the prior art are all capable of capturing images continuously for a long time, and the amount of video data is quite large.
Furthermore, the eyes of the user must keep staring at the monitoring picture all the time, so that the user can be ensured not to miss any event, and the physical and psychological burden of the user is increased. The user is unaware of the trouble or needs to leave the post temporarily due to reasons, and the factors can cause the user to not notice the events and miss the opportunity to take strain measures, so that the probability of accidents is increased.
Furthermore, no device is currently available on the market for monitoring whether a driver is doing dangerous movements. Once the driver makes a dangerous action such as dozing, sliding a mobile phone or lowering, a car accident can happen, and the danger is quite high.
Disclosure of Invention
The present invention is directed to a behavioral image sensing system, which can effectively reduce data processing capacity and is suitable for any environment.
Another objective of the present invention is to provide a behavioral image sensing system capable of reducing the probability of accidents.
In order to achieve the above-mentioned objective, the present invention provides a behavioral image sensing system, which includes a first image capturing unit and a control unit. The first image capturing unit is used for capturing a dynamic image. The control unit is electrically connected with the first image capturing unit, receives the dynamic image, and calculates a motion track of a moving object in the dynamic image so as to determine whether the motion track of the moving object accords with a specific dangerous behavior mode.
In some embodiments, the behavior image sensing system further includes a warning unit, and the control unit is electrically connected to the warning unit; when the control unit determines that the motion track of the moving object accords with a specific dangerous behavior mode, the control unit controls the warning unit to send out a warning signal.
In some embodiments, the behavioral image sensing system further includes a second image capturing unit, and the control unit is electrically connected to the second image capturing unit; when the control unit determines that the motion track of the moving object accords with the specific dangerous behavior mode, the control unit starts the second image capturing unit, the second image capturing unit is used for capturing a general image, the control unit receives the general image, calculates an appearance of the moving object in the general image, and determines whether the appearance of the moving object accords with a specific category.
In some embodiments, the control unit further comprises an image database and a comparison program, the control unit compares the image database and calculates the appearance of the moving object in the general image by the comparison program to determine whether the appearance of the moving object meets the specific category.
In some embodiments, the comparison process further includes a deep learning algorithm, wherein the appearance of the moving object is calculated by the deep learning algorithm to determine whether the appearance of the moving object meets the specific category.
In some embodiments, the behavior image sensing system further includes a warning unit, and the control unit is electrically connected to the warning unit; when the control unit determines that the appearance of the moving object accords with the specific category, the control unit controls the warning unit to send out a warning signal.
In some embodiments, the behavioral image sensing system further includes a distance sensing unit, and the control unit is electrically connected to the distance sensing unit; when the control unit determines that the motion track of the moving object accords with the specific dangerous behavior mode, or when the control unit determines that the appearance of the moving object accords with the specific category, the control unit starts the distance sensing unit, the distance sensing unit is used for sensing a distance of the moving object, and the control unit receives the distance of the moving object and determines whether the distance of the moving object is smaller than a preset value.
In some embodiments, the behavior image sensing system further includes a warning unit, and the control unit is electrically connected to the warning unit; when the control unit determines that the distance of the moving object is smaller than the preset value, the control unit controls the warning unit to send out a warning signal.
In some embodiments, the warning signal at least includes sound, ultrasonic wave, strong light, voice, vibration or text, and is used to drive away the moving object or inform the user.
In some embodiments, the warning unit comprises at least one of an outdoor alarm, a voice player, a vibrator and a notification program, wherein the outdoor alarm is disposed outdoors, the warning signal generated by the outdoor alarm at least comprises one of sound, ultrasonic wave and strong light, the voice player is mounted on a vehicle, the warning signal generated by the voice player is a voice, the vibrator is mounted on a steering wheel, the warning signal generated by the vibrator is a vibration, the notification program is mounted in one of a vehicle computer, a remote monitoring system and a portable electronic device, and the warning signal generated by the notification program at least comprises one of text and voice and pushes the warning signal through one of the vehicle computer, the remote monitoring system and the portable electronic device.
The invention has the advantages that the behavior image sensing system can judge the behavior mode of the moving object through the dynamic image, does not need to capture the static image of the static object at all, does not need to judge the behavior mode of the static object, reduces the data processing amount greatly, and is suitable for any environment.
Furthermore, the behavior image sensing system of the invention further judges the type of the moving object through the general image after determining the behavior mode of the moving object, thus completely eliminating the need of capturing the static image of the static object and judging the type of the static object, and reducing the data processing amount greatly.
In addition, the behavior image sensing system further calculates the distance of the moving object after determining the behavior mode or the class of the moving object, judges whether the distance of the moving object is smaller than a preset value, does not need to calculate the distance of the static object at all, does not need to judge whether the distance of the static object is smaller than the preset value, and reduces the data processing amount greatly.
In addition, the control unit can control the warning unit to send out warning signals according to the situation so as to drive away the moving object or inform a user, and the accident occurrence probability is reduced.
Drawings
FIG. 1 is a schematic diagram of a behavior image sensing system according to the present invention.
FIG. 2 is a flowchart of a behavior image sensing system according to a first embodiment of the present invention.
FIG. 3 is a flowchart of a behavior image sensing system according to a second embodiment of the present invention.
FIG. 4 is a flowchart of a behavior image sensing system according to a third embodiment of the present invention.
FIG. 5 is a flowchart of a behavior image sensing system according to a fourth embodiment of the present invention.
Reference numerals illustrate:
10, a first image capturing unit; 20, a second image capturing unit; a distance sensing unit; 40, a warning unit; 50, a control unit; 51, an image database; 52, comparing the program; S100-S130, namely, a step; S200-S260, namely, the steps; S300-S380, namely, steps; S400-S480.
Detailed Description
The following embodiments of the invention are described in sufficient detail to enable those skilled in the art to practice the invention, and are presented in the context of a study of the specification.
FIG. 1 is a schematic diagram of a behavior image sensing system according to the present invention. As shown in fig. 1, the present invention provides a behavioral image sensing system, which includes a first image capturing unit 10, a second image capturing unit 20, a distance sensing unit 30, a warning unit 40 and a control unit 50. The control unit 50 is electrically connected to the first image capturing unit 10, the second image capturing unit 20, the distance sensing unit 30 and the warning unit 40. The control unit 50 further comprises an image database 51 and a comparison program 52, and the comparison program 52 further comprises a deep learning algorithm.
The first image capturing unit 10 is a dynamic visual sensor (Dynamic Vision Sensor, DVS) that records information in units of events. Specifically, the light intensity in the environment changes during the movement of the object, and the dynamic vision sensor can detect and record the change of the light intensity in the environment. Therefore, the first image capturing unit 10 is substantially configured to detect a change in light intensity when an object in the environment is moving, wherein the moving object can be defined as a moving object, and the change in light intensity in the environment can be defined as a dynamic image.
The second image capturing unit 20 is a general image sensor (e.g. RGB CMOS image sensor) that records images in units of frames, and the image content can be color pixels or black-and-white pixels. Therefore, the second image capturing unit 20 essentially records the images of the moving object and the surrounding environment thereof and recognizes the appearance of the moving object in the images.
The distance sensing unit 30 is an optical radar Sensor (LiDAR Sensor), an indirect time-of-flight Sensor (iToF Sensor), or a direct time-of-flight Sensor (dToF Sensor). Thus, the distance sensing unit 30 of the above type detects the distance of the moving object by optical radar, indirect time of flight, or direct time of flight.
The operation of the behavior image sensing system of the present invention will be described in the following by various embodiments.
FIG. 2 is a flowchart of a behavior image sensing system according to a first embodiment of the present invention. As shown in fig. 1 and 2, the first embodiment includes the steps of: step S100, when a moving object (not shown) enters the image capturing range of the first image capturing unit 10, the first image capturing unit 10 captures a dynamic image; step S110, the control unit 50 receives the dynamic image and calculates a motion trail of the moving object in the dynamic image; step S120, the control unit 50 determines whether the motion trail of the moving object accords with a specific dangerous behavior pattern; step S130, when the control unit 50 determines that the motion track of the moving object accords with the specific dangerous behavior mode, the control unit 50 controls the warning unit 40 to send out a warning signal, wherein the warning signal is used for driving away the moving object or notifying a user; when the control unit 50 determines that the motion profile of the moving object does not conform to the specific dangerous behavior pattern, it returns to step S110.
A case will be listed below as an example of how the first embodiment monitors whether the driver is doing dangerous actions in the vehicle. In this case, the warning unit 40 is a voice player or a notification program, the voice player is installed on the vehicle, the notification program is installed on a portable electronic device such as a car computer, a smart phone, a tablet computer, etc., the vehicle is a specific occasion, and the dangerous action is a specific dangerous behavior mode.
Step S100, when the driver enters the image capturing range of the first image capturing unit 10, the first image capturing unit 10 captures an image (dynamic image) of the eye, hand or head movement; step S110, the control unit 50 receives an image of the eye, hand or head movement and calculates a movement locus of the eye, hand or head (moving object) in the image of the eye, hand or head movement; step S120, the control unit 50 determines whether the motion trail of the eyeball, the hand or the head accords with the specific dangerous behavior mode, such as dozing, sliding the mobile phone or lowering the head; and step S130, when the control unit 50 determines that the motion track of the eyeball, the hand or the head accords with the specific dangerous behavior mode as "dangerous action", the control unit 50 controls the voice player (the warning unit 40) to send out a similar voice (warning signal) such as "you are in dangerous driving state" or controls the notification program (the warning unit 40) to push out a similar voice (warning signal) such as "you are in dangerous driving state" through the vehicle computer or the portable electronic device, so as to achieve the purpose of notifying the driver. After receiving the notification, the driver wakes up, puts down the mobile phone or lifts the head immediately, so as to avoid traffic accidents; when the control unit 50 determines that the movement track of the eyeball, the hand or the head does not conform to the specific dangerous behavior pattern as "dangerous motion", for example, the eye looks ahead, the hand grips the steering wheel or lifts the head, it goes back to step S110.
A case will be listed below as an example of how the first embodiment monitors whether a building is being run by a person. In this case, the warning unit 40 includes at least one buzzer, at least one warning light and a notification program, the buzzer and the warning light are installed outdoors, the notification program is installed in a remote monitoring system or a portable electronic device such as a smart phone, a tablet computer, etc., the building is a specific occasion, and the running of the door is a specific dangerous behavior pattern.
Step S100, when a person enters the image capturing range of the first image capturing unit 10, the first image capturing unit 10 captures an image (dynamic image) of the motion of the person; step 110, the control unit 50 receives the image of the motion of the person and calculates the motion trail of the person (moving object) in the image of the motion of the person; step S120, the control unit 50 determines whether the motion trail of a person accords with a specific dangerous behavior mode, namely "running a door; and step S130, when the control unit 50 determines that the motion trail of the person accords with the specific dangerous behavior mode as "running the door", for example, the person climbs the wall to enter or prizes the door lock, etc., the control unit 50 controls the buzzer (the warning unit 40) to loudly sound (the warning signal) or controls the warning light (the warning unit 40) to continuously flash the strong light (the warning signal), and the person can be frightened by the sudden sound or the strong light, so as to achieve the purpose of driving away the person; meanwhile, the control unit 50 controls the notification program (the warning unit 40) to push similar characters or voices (warning signals) such as 'someone rushing through the air door', so that a homeowner can know the occurrence of events such as 'someone rushing through the air door' from a remote monitoring system or a portable electronic device and can immediately take emergency strain measures; when the control unit 50 determines that the motion trajectory of the person does not conform to the specific dangerous behavior pattern as "running the door" for example, the person passes through the doorway, knocks the door, presses the doorbell, or the like, it returns to step S110.
FIG. 3 is a flowchart of a behavior image sensing system according to a second embodiment of the present invention. As shown in fig. 1 and 3, steps S200 to S220 of the second embodiment are identical to steps S100 to S120 of the first embodiment; the second embodiment further comprises the steps of: step S230, when the control unit 50 determines that the motion trajectory of the moving object accords with the specific dangerous behavior mode, the control unit 50 starts the second image capturing unit 20, and the second image capturing unit 20 captures a general image; when the control unit 50 determines that the motion trajectory of the moving object does not conform to the specific dangerous behavior pattern, it returns to step S210; step S240, the control unit 50 receives the general image, compares the image database 51 through the comparison program 52, and calculates an appearance of the moving object in the general image through the deep learning algorithm; step S250, the control unit 50 determines whether the appearance of the moving object meets a specific category; step S260, when the control unit 50 determines that the appearance of the moving object meets the specific category, the control unit 50 controls the warning unit 40 to send a warning signal for driving away the moving object or notifying the user; when the control unit 50 determines that the appearance of the moving object does not conform to the specific category, it returns to step S240.
A case will be listed below as an example of how the second embodiment monitors whether a wild animal invading a vast, thin building is a dangerous animal. In this case, the warning unit 40 includes at least one buzzer, at least one ultrasonic wave repeller, at least one warning light and a notification program, the buzzer, the ultrasonic wave repeller and the warning light are installed outdoors, the notification program is installed in a remote monitoring system or a portable electronic device such as a smart phone, a tablet computer, etc., the building is a specific occasion, and the intrusion into the building is a specific dangerous behavior pattern.
Step 200, when the wild animal enters the image capturing range of the first image capturing unit 10, the first image capturing unit 10 captures an image (dynamic image) of the motion of the wild animal; step S210, the control unit 50 receives the image of the motion of the wild animal and calculates the motion trajectory of the wild animal (moving object) in the image of the motion of the wild animal; step S220, the control unit 50 determines whether the motion trail of the wild animal accords with the specific dangerous behavior pattern as "intrusion into the building"; step S230, when the control unit 50 determines that the motion trajectory of the wild animal accords with the specific dangerous behavior mode as "invading the building", for example, the wild animal goes to the building, the control unit 50 starts the second image capturing unit 20, and the second image capturing unit 20 captures images (general images) of the wild animal and its surrounding environment; when the control unit 50 determines that the movement track of the wild animal does not conform to the specific dangerous behavior pattern as "intrusion into the building", for example, the wild animal gradually moves away from the building, and returns to step S210; step S240, the control unit 50 receives the images of the wild animal and its surrounding environment, compares the image database 51 through the comparison program 52, and calculates the appearance of the wild animal in the images of the wild animal and its surrounding environment via the deep learning algorithm; in step S250, the control unit 50 determines whether the appearance of the wild animal meets a specific category of "dangerous animals", such as lions, tigers, leopards, bears, wolves, wild dogs, badgers, foxes, minks, raccoons, wild pigs, mice, birds, bats, rodents, and the like; in step S260, when the control unit 50 determines that the appearance of the wild animal accords with the specific category as "dangerous animal", the control unit 50 controls the buzzer (warning unit 40) to loudly sound (warning signal) or controls the ultrasonic wave rejector (warning unit 40) to generate ultrasonic waves (warning signal) or controls the warning lamp (warning unit 40) to continuously flash strong light (warning signal), so that the wild animal is frightened by the sound or strong light of the wild animal or receives the rejected ultrasonic waves, and the wild animal is frightened and run, thereby achieving the purpose of expelling the dangerous animal; meanwhile, the control unit 50 controls the notification program (the warning unit 40) to push similar words or voices (warning signals) such as 'dangerous animal invading building', so that a homeowner can know the occurrence of the event such as 'dangerous animal invading building' from a remote monitoring system or a portable electronic device and can immediately take emergency strain measures; when the control unit 50 determines that the appearance of the wild animal does not conform to the specific category as "dangerous animal", for example, a omnivore or herbivore such as human, sheep, deer, rabbit, etc., it goes back to step S240.
It is worth mentioning that the ultrasonic wave with the frequency of 13.5 kilohertz can repel animals such as mice, dogs, foxes, martens and the like, the ultrasonic wave with the frequency of 19.5-24.5 kilohertz can repel animals such as cats, raccoons, badgers, bears and the like, the ultrasonic wave with the frequency of 24.5-45.5 kilohertz can repel animals such as bats, birds, rodents and the like, and the strong flash of light can repel animals such as raccoons, wild pigs, martens and the like. In practice, ultrasonic waves with a frequency of 13.5-45.5 khz can repel all wild animals listed above, and with a strong flash, all animals can be repelled.
A case will be described below as to how the second embodiment monitors whether someone intrudes into the restricted area. The forbidden zone refers to a special area or region which is not allowed to be accessed by unauthorized persons, such as military forbidden zone, airport forbidden zone, border forbidden zone, battle zone, fishing forbidden zone and staff rest room. In this case, the alarm unit 40 is a notification program installed in the remote monitoring system, the forbidden zone is a specific occasion, and the illegal intrusion is a specific dangerous behavior mode.
Step S200, when a person enters the image capturing range of the first image capturing unit 10, the first image capturing unit 10 captures an image (dynamic image) of the motion of the person; step S210, the control unit 50 receives the image of the motion of the person and calculates the motion trajectory of the person (moving object) in the image of the motion of the person; step S220, the control unit 50 determines whether the motion trail of the person accords with the specific dangerous behavior mode as "intrude; step S230, when the control unit 50 determines that the motion trajectory of the person accords with the specific dangerous behavior mode as "intrude", for example, the person crosses the boundary of the forbidden zone and enters the forbidden zone, the control unit 50 starts the second image capturing unit 20, and the second image capturing unit 20 captures images (general images) of the person and the surrounding environment thereof; when the control unit 50 determines that the motion trajectory of the person does not conform to the specific dangerous behavior pattern, for example, the person walks outside the boundary of the forbidden zone and does not enter the forbidden zone, the step returns to step S210; in step S240, the control unit 50 receives the images of the person and the surrounding environment, compares the images of the person and the surrounding environment with the image database 51 through the comparison program 52, and calculates the appearance of the person in the images of the person and the surrounding environment through the deep learning algorithm; step S250, the control unit 50 determines whether the appearance of a person accords with a specific category of "person without authority"; step S260, when the control unit 50 determines that the appearance of a person accords with the specific category of "person without authority", the control unit 50 controls the notification program (the warning unit 40) to push the words or voices (warning signals) similar to "person intrudes into forbidden areas", so that the guard can learn from the remote monitoring system that events such as "person intrudes into forbidden areas" occur and can immediately take emergency measures; when the control unit 50 determines that the appearance of the certain person does not conform to the specific category of "person without authority", for example, the certain person is a licensed person, it goes back to step S240.
FIG. 4 is a flowchart of a behavior image sensing system according to a third embodiment of the present invention. As shown in fig. 1 and 4, steps S300 to S350 of the third embodiment are identical to steps S200 to S250 of the second embodiment, and the third embodiment further includes the steps of: step S360, when the control unit 50 determines that the appearance of the moving object meets a specific category, the control unit 50 activates the distance sensing unit 30, a transmitter (not shown) of the distance sensing unit 30 emits light, a receiver (not shown) of the distance sensing unit 30 receives the light reflected by the moving object, and the distance sensing unit 30 calculates a distance of the moving object according to a time difference from the light emission to the receiving; when the control unit 50 determines that the appearance of the moving object does not conform to the specific category, it goes back to step S340; step S370, the control unit 50 receives the distance of the moving object and determines whether the distance of the moving object is less than a preset value; step S380, when the control unit 50 determines that the distance between the moving object is smaller than the preset value, the control unit 50 controls the warning unit 40 to send a warning signal for driving away the moving object or notifying the user; when the control unit 50 determines that the distance of the moving object is greater than the preset value, it goes back to step S360.
A case will be listed below as an example of how the third embodiment monitors whether a wild animal that invades a vast, thin building is a dangerous animal.
Steps S300 to S350 of this case can refer to steps S200 to S250 of the second embodiment regarding how to monitor whether or not a wild animal invading a vast or rare building is a dangerous animal. Step S360, when the control unit 50 determines that the appearance of the wild animal accords with the specific category as "dangerous animal", the control unit 50 starts the distance sensing unit 30, and the distance sensing unit 30 calculates the distance of the wild animal; when the control unit 50 determines that the appearance of the wild animal does not conform to the specific category as "dangerous animal", it goes back to step S340; step S370, the control unit 50 receives the distance of the wild animal and determines whether the distance of the wild animal is less than a preset value; step S380, when the control unit 50 determines that the distance between the wild animals is smaller than the preset value, the control unit 50 controls the buzzer (warning unit 40) to loudly sound (warning signal) or controls the ultrasonic wave repeller (warning unit 40) to generate ultrasonic waves (warning signal) or controls the warning lamp (warning unit 40) to continuously flash strong light (warning signal), so that the wild animals are frightened by the sound or strong light of the wild animals or receive the repelled ultrasonic waves, and the wild animals are frightened and run, thereby achieving the purpose of driving the dangerous animals; meanwhile, the control unit 50 controls the notification program (the warning unit 40) to push similar words or voices (warning signals) such as 'dangerous animal invading building', so that a homeowner can know the occurrence of the event such as 'dangerous animal invading building' from a remote monitoring system or a portable electronic device and can immediately take emergency strain measures; when the control unit 50 determines that the distance of the wild animal is greater than the preset value, it goes back to step S360.
A case will be described below as to how the third embodiment monitors whether someone intrudes into the restricted area.
Steps S300 to S350 of this case can refer to steps S200 to 250 of the second embodiment regarding how to monitor whether a person intrudes into the forbidden zone. Step S360, when the control unit 50 determines that the appearance of the person accords with the specific category of "person without authority", the control unit 50 starts the distance sensing unit 30, and the distance sensing unit 30 calculates the distance of the person; step S370, the control unit 50 receives the distance of the person and determines whether the distance of the person is less than a preset value; step S380, when the control unit 50 determines that the distance between the two persons is smaller than the preset value, the control unit 50 controls the notification program (the warning unit 40) to push the words or voices (warning signals) similar to "someone intrudes into the forbidden zone", so that the guard can learn from the remote monitoring system that the event such as "someone intrudes into the forbidden zone" occurs and can immediately take emergency measures; when the control unit 50 determines that the distance of the person is greater than the preset value, it goes back to step S360.
FIG. 5 is a flowchart of a behavior image sensing system according to a fourth embodiment of the present invention. As shown in fig. 1 and 5, steps S400 to S420 of the fourth embodiment are identical to steps S200 to S220 of the second embodiment, and the fourth embodiment further includes the steps of: step S430, when the control unit 50 determines that the motion trajectory of the moving object accords with the specific dangerous behavior mode, the control unit 50 starts the distance sensing unit 30, a transmitter (not shown) of the distance sensing unit 30 emits light, a receiver (not shown) of the distance sensing unit 30 receives the light reflected by the moving object, and the distance sensing unit 30 calculates a distance of the moving object according to a time difference from the light emission to the receiving; when the control unit 50 determines that the motion trajectory of the moving object does not conform to the specific dangerous behavior pattern, it returns to step S410; step S440, the control unit 50 receives the distance of the moving object and determines whether the distance of the moving object is less than a preset value; step S450, when the control unit 50 determines that the distance between the moving object is smaller than the preset value, the control unit 50 starts the second image capturing unit 20, and the second image capturing unit 20 captures a general image; when the control unit 50 determines that the distance of the moving object is greater than the preset value, it returns to step S430; step S460, the control unit 50 receives the general image, compares the image database 51 through the comparison program 52, and calculates an appearance of the moving object in the general image through the deep learning algorithm; step S470, the control unit 50 determines whether the appearance of the moving object meets a specific category; step S480, when the control unit 50 determines that the appearance of the moving object meets the specific category, the control unit 50 controls the warning unit 40 to send a warning signal for driving away the moving object or notifying the user; when the control unit 50 determines that the appearance of the moving object does not conform to the specific category, it returns to step S460.
A case will be listed below as an example of how the fourth embodiment monitors whether a wild animal invading a vast, thin building is a dangerous animal.
Steps S400 to S420 of this case can refer to steps S200 to S220 of the second embodiment regarding how to monitor whether or not a wild animal invading a vast or rare building is a dangerous animal. Step S430, when the control unit 50 determines that the motion trajectory of the wild animal accords with the specific dangerous behavior pattern as "intrusion into a building", for example, the wild animal goes into the building, the control unit 50 starts the distance sensing unit 30, and the distance sensing unit 30 calculates the distance of the wild animal; step S440, the control unit 50 receives the distance of the wild animal and determines whether the distance of the wild animal is less than a preset value; step S450, when the control unit 50 determines that the distance between the wild animal and the image capturing device is smaller than the preset value, the control unit 50 starts the second image capturing unit 20, and the second image capturing unit 20 captures the image (general image) of the wild animal and the surrounding environment thereof; when the control unit 50 determines that the distance of the wild animal is greater than the preset value, it returns to step S430; step S460, the control unit 50 receives the images of the wild animal and its surrounding environment, compares the image database 51 through the comparison program 52, and calculates the appearance of the wild animal in the images of the wild animal and its surrounding environment via the deep learning algorithm; step S470, the control unit 50 determines whether the appearance of the wild animal meets a specific category of "dangerous animal"; in step S480, when the control unit 50 determines that the appearance of the wild animal accords with the specific category as "dangerous animal", the control unit 50 controls the buzzer (warning unit 40) to loudly sound (warning signal) or controls the ultrasonic wave rejector (warning unit 40) to generate ultrasonic waves (warning signal) or controls the warning lamp (warning unit 40) to continuously flash strong light (warning signal), so that the wild animal is frightened by the sound or strong light of the wild animal or receives the rejected ultrasonic waves, and the wild animal is frightened and run, thereby achieving the purpose of expelling the dangerous animal; meanwhile, the control unit 50 controls the notification program (the warning unit 40) to push similar words or voices (warning signals) such as 'dangerous animal invading building', so that a homeowner can know the occurrence of the event such as 'dangerous animal invading building' from a remote monitoring system or a portable electronic device and can immediately take emergency strain measures; when the control unit 50 determines that the appearance of the wild body does not conform to the specific category as "dangerous animal", it returns to step S460.
A case will be described below as to how the fourth embodiment monitors whether someone intrudes into the restricted area.
Steps S400 to S420 of this case can refer to steps S200 to S220 of the second embodiment regarding how to monitor whether a person intrudes into the forbidden zone. Step S430, when the control unit 50 determines that the motion trajectory of the person accords with the specific dangerous behavior mode as "intrude", the control unit 50 starts the distance sensing unit 30, and the distance sensing unit 30 calculates the distance of the person; step S440, the control unit 50 receives the distance of a person and determines whether the distance of the person is less than a preset value; step S450, when the control unit 50 determines that the distance between the person and the image capturing device is smaller than the preset value, the control unit 50 starts the second image capturing unit 20, and the second image capturing unit 20 captures an image (a general image) of the person and the surrounding environment; when the control unit 50 determines that the distance of a person is greater than the preset value, it returns to step S430; in step S460, the control unit 50 receives the images of the person and the surrounding environment, compares the image database 51 through the comparison program 52, and calculates the appearance of the person in the images of the person and the surrounding environment via the deep learning algorithm; step S470, the control unit 50 determines whether the appearance of a person accords with the specific category of "person without authority"; in step S480, when the control unit 50 determines that the appearance of a person accords with the specific category of "person without authority", the control unit 50 controls the notification program (the warning unit 40) to push the similar text or voice (warning signal) such as "person intrudes into the forbidden zone", so that the guard can learn from the remote monitoring system that the event such as "person intrudes into the forbidden zone" occurs, and can immediately take emergency measures; when the control unit 50 determines that the appearance of a person does not conform to the specific category as "person without authority", it returns to step S460.
Respiratory measurement is performed by capturing images of the upper body of a subject (i.e., a moving object), calculating respiratory rate or detecting the presence of respiration based on chest relief. The image capturing range of the first image capturing unit 10 or the second image capturing unit 20 according to the present invention is photographed to generate a sensing image, and the user is reminded of whether the subject has an apnea condition through a communication module (not shown) or other related devices; in detail, in the image capturing range of the first image capturing unit 10 or the second image capturing unit 20 of the present invention, the subject can determine whether the chest of the subject continuously fluctuates through the image capturing function of the first image capturing unit 10 or the second image capturing unit 20 by the control unit 50. If the chest of the subject is found to stop fluctuating during monitoring, the warning unit 40 pushes words or voices (warning signals) such as 'the chest of the subject stops fluctuating', and the like, so that the dangerous situation that the subject is in an apnea state is noticed, the user can know the occurrence of events such as 'the chest of the subject stops' from the remote monitoring system, and can immediately take emergency strain measures.
The object detection technology is a computer technology related to computer vision and image processing for detecting a certain type of image and video, such as human beings, animals, buildings, or vehicles. Research fields of object detection include, for example, face detection and pedestrian detection, and object detection has applications in many fields of computer vision, including image retrieval and video surveillance. The first image capturing unit 10 or the second image capturing unit 20 of the present invention can detect the driver, the pedestrian, the animal in the environment, etc. in the image by using the object detection technology. Object detection methods are generally classified as neural network-based methods or non-neural methods. For non-neural methods, it is necessary to first define features using one of the following methods, and then classify the features using techniques such as support vector machines (support vector machine, SVM). On the other hand, neural technology is capable of object detection without explicitly defining features, and is typically based on convolutional neural networks (Convolutional Neural Network, CNN). Non-neural methods such as: the method is based on the characteristics of Hard digital images, such as a Viola-Jones target detection framework (Viola-Jones object detection framework based on Haar features), scale-invariant feature transform (Scale-INVARIANT FEATURE TRANSFORM, SIFT), a direction gradient histogram (Histogram of oriented gradients (HOG) features) and the like, but is not limited thereto; neural methods such as: R-CNN candidate region (Region Proposals (R-CNN)), single sample multi-frame detector (Single Shot MultiBox Detector, SSD), you need only look once (You Only Look Once, YOLO), single refinement neural network for target detection (Single-Shot Refinement Neural Network for Object Detection (REFINEDET)), retina-Net (Retina-Net), deformed convolutional neural network (Deformable convolutional networks), etc., but not limited thereto.
Behavior recognition, motion recognition or limb motion recognition is a technique for recognizing animal motions by using computer technology related to image acquisition and image processing. Because of its versatility, different fields may refer to behavior recognition as plan recognition, object recognition, intent recognition, location estimation, and the like. The behavior recognition is as follows: sensor-based single-user activity recognition (user activity recognition), sensor-based activity recognition level (Levels of Sensor-based activity recognition), sensor-based multiple-user activity recognition (multi-user activity recognition), and the like; the manner of behavior recognition is for example: activity recognition by logic and reasoning (Activity recognition through logic and reasoning), activity recognition by probabilistic reasoning (Activity recognition through probabilistic reasoning), data mining based activity recognition method (DATA MINING based approach to activity recognition), global positioning system based activity recognition (GPS-based activity recognition), but not limited thereto. The first image capturing unit 10 of the present invention can detect a specific dangerous behavior pattern of a moving object in an image by using a behavior recognition technology, such as dangerous actions of a driver, a person running a blank door or a non-intrusive forbidden zone, a wild animal invading a building, etc.
In summary, the behavior image sensing system of the present invention can determine the behavior pattern of the moving object through the dynamic image, and does not need to capture the static image of the static object, nor determine the behavior pattern of the static object, so that the data processing amount is reduced greatly, and the system is suitable for any environment.
Furthermore, the behavior image sensing system of the invention further judges the type of the moving object through the general image after determining the behavior mode of the moving object, thus completely eliminating the need of capturing the static image of the static object and judging the type of the static object, and reducing the data processing amount greatly.
In addition, the behavior image sensing system further calculates the distance of the moving object after determining the behavior mode or the class of the moving object, judges whether the distance of the moving object is smaller than a preset value, does not need to calculate the distance of the static object at all, does not need to judge whether the distance of the static object is smaller than the preset value, and reduces the data processing amount greatly.
In addition, the control unit 50 can control the alarm unit 40 to send out an alarm signal to drive away the moving object or inform the user according to the situation, so as to reduce the accident probability.
The above description is for the purpose of illustrating the preferred embodiments of the present invention and is not intended to limit the present invention in any way, but is intended to cover any and all modifications or variations of the present invention that fall within the spirit and scope of the invention.
Claims (10)
1. A behavioral image sensing system, comprising:
A first image capturing unit for capturing a dynamic image; and
The control unit is electrically connected with the first image capturing unit, receives the dynamic image, and calculates a motion track of a moving object in the dynamic image so as to judge whether the motion track of the moving object accords with a specific dangerous behavior mode.
2. The behavioral image sensing system of claim 1, further comprising:
the control unit is electrically connected with the warning unit;
when the control unit judges that the motion trail of the moving object accords with a specific dangerous behavior mode, the control unit controls the warning unit to send out a warning signal.
3. The behavioral image sensing system of claim 1, further comprising:
the control unit is electrically connected with the second image capturing unit;
when the control unit determines that the motion trail of the moving object accords with the specific dangerous behavior mode, the control unit starts the second image capturing unit, the second image capturing unit is used for capturing a general image, the control unit receives the general image, calculates an appearance of the moving object in the general image, and determines whether the appearance of the moving object accords with a specific category.
4. The behavioral image sensing system of claim 3, wherein the control unit comprises:
the control unit compares the image database through the comparison program and calculates the appearance of the moving object in the general image so as to judge whether the appearance of the moving object accords with the specific category.
5. The behavioral image sensing system according to claim 4, wherein the comparison procedure comprises: a deep learning algorithm, through which the appearance of the moving object is calculated to determine whether the appearance of the moving object meets the specific category.
6. The behavioral image sensing system of claim 3 further comprising:
the control unit is electrically connected with the warning unit;
When the control unit determines that the appearance of the moving object accords with the specific category, the control unit controls the warning unit to send out a warning signal.
7. The behavioral image sensing system of claim 3 further comprising:
The control unit is electrically connected with the distance sensing unit;
Wherein when the control unit determines that the motion trajectory of the moving object meets the specific dangerous behavior pattern, or when the control unit determines that the appearance of the moving object meets the specific category, the control unit activates the distance sensing unit to sense a distance of the moving object, the control unit receives the distance of the moving object, and determines whether the distance of the moving object is less than a preset value.
8. The behavioral image sensing system of claim 7, further comprising:
the control unit is electrically connected with the warning unit;
when the control unit judges that the distance of the moving object is smaller than the preset value, the control unit controls the warning unit to send out a warning signal.
9. The behavioral image sensing system according to claim 2, 6 or 8, wherein the alert signal comprises at least one of sound, ultrasound, intense light, voice, vibration, or text, and is used to dislodge the moving object or notify the user.
10. The behavioral image sensing system according to claim 9, wherein the alert unit comprises at least one of an outdoor alarm, a voice player, a vibrator and a notification program, wherein the outdoor alarm is disposed outdoors, the alert signal generated by the outdoor alarm comprises at least one of sound, ultrasonic wave and intense light, the voice player is mounted on a vehicle, the alert signal generated by the voice player is a voice, the vibrator is mounted on a steering wheel, the alert signal generated by the vibrator is a vibration, the notification program is mounted in one of a vehicle computer, a remote monitoring system and a portable electronic device, and the alert signal generated by the notification program comprises at least one of text and voice and is pushed by one of the vehicle computer, the remote monitoring system and the portable electronic device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211412660.1A CN118042270A (en) | 2022-11-11 | 2022-11-11 | Behavior image sensing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211412660.1A CN118042270A (en) | 2022-11-11 | 2022-11-11 | Behavior image sensing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118042270A true CN118042270A (en) | 2024-05-14 |
Family
ID=91000958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211412660.1A Pending CN118042270A (en) | 2022-11-11 | 2022-11-11 | Behavior image sensing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118042270A (en) |
-
2022
- 2022-11-11 CN CN202211412660.1A patent/CN118042270A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7639840B2 (en) | Method and apparatus for improved video surveillance through classification of detected objects | |
| EP3410413A1 (en) | Improved generation of alert events based on a detection of objects from camera images | |
| JP4569190B2 (en) | Suspicious person countermeasure system and suspicious person detection device | |
| CN106327759A (en) | Invasion preventive intelligent safety protection system deployed in unattended transformer substation | |
| KR101877294B1 (en) | Smart cctv system for crime prevention capable of setting multi situation and recognizing automatic situation by defining several basic behaviors based on organic relation between object, area and object's events | |
| WO2006083283A2 (en) | Method and apparatus for video surveillance | |
| CN113723369B (en) | Control method, control device, electronic equipment and storage medium | |
| CN113033521B (en) | Perimeter dynamic early warning method and system based on target analysis | |
| US20220343650A1 (en) | Image based aquatic alert system | |
| CN116994389A (en) | Monitoring alarm driving system and method based on artificial intelligence and image recognition | |
| CN115703431A (en) | System and method for vehicle safety monitoring | |
| CN114973573A (en) | Target intrusion determination method and device, storage medium and electronic device | |
| US11616932B1 (en) | Car security camera triggering mechanism | |
| KR102492066B1 (en) | Mobile preventive warning system | |
| Roopashree et al. | Monitoring the movements of wild animals and alert system using deep learning algorithm | |
| CN113055651A (en) | Artificial intelligence type vehicle security system and computer readable storage medium | |
| CN118042270A (en) | Behavior image sensing system | |
| Karishma et al. | Smart office surveillance robot using face recognition | |
| CN109214316B (en) | Perimeter protection method and device | |
| CN114511978B (en) | Intrusion early warning method, device, vehicle and computer readable storage medium | |
| US20240153109A1 (en) | Image based tracking system | |
| TWI827356B (en) | Behavior image sensor system | |
| TW202420244A (en) | Behavior image sensor system | |
| CN114387689A (en) | Method for controlling parking lot barrier gate and related device | |
| CN116740874A (en) | Intrusion detection method and related 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 |