WO2015058219A1 - System for identification and tracking of humans - Google Patents
System for identification and tracking of humans Download PDFInfo
- Publication number
- WO2015058219A1 WO2015058219A1 PCT/ZA2014/000052 ZA2014000052W WO2015058219A1 WO 2015058219 A1 WO2015058219 A1 WO 2015058219A1 ZA 2014000052 W ZA2014000052 W ZA 2014000052W WO 2015058219 A1 WO2015058219 A1 WO 2015058219A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- movement
- humans
- monitoring system
- data
- group
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Definitions
- the invention relates to a system of identifying humans, more specifically for differentiating humane from wild animais, especially in conservation areas.
- the inventor is aware of existing thermal, infra-red and similar technologies used in the detection of both humans and wild animais.
- a problem associated with existing technology is that these detection systems cannot differentiate between humans and animais. unless a shape or size is available. These systems often trigger or generate an alarm when detecting irrelevant or unrelated animais. This is particularly the case when monitoring for human activity in areas abundant with wildlife.
- a monitoring system for identifying and tracking humans which includes:
- a sensor for sensing movement of a body
- data capture means for capturing data relating to the movement received from the sensor
- a processor configured to execute an algorithm, which algorithm, based on specific parameters, analyses and compares the captured data to a database of behavioural patterns relating to animais and humans; and a!arm means for generating an alarm signal when a predetermined pattern is identified.
- the sensor may comprise an image capturing device for capturing a series of images of a preselected location over a specific period of time, and a comparing device for comparing the images so as to determine movement in the preselected location.
- the image capturing device may take the form of any one or more of a camera (including all variants such as standard, infrared, thermal, night-vision and any simiiar image or video capture devices), movement sensors (which typically includes infrared and laser trigger devices), deployed animal tracking devices such as radio collars and gps collars, and satellite imagery. It may also include recorded observations from humans.
- a camera including all variants such as standard, infrared, thermal, night-vision and any simiiar image or video capture devices
- movement sensors which typically includes infrared and laser trigger devices
- deployed animal tracking devices such as radio collars and gps collars, and satellite imagery. It may also include recorded observations from humans.
- image capturing devices are used to determine the location of bodies and may also be used to attempt to identify or predict which type of body is being detected. Traditionally such detection is made with varying accuracy, usually accompanied by a statistical variance on the likelihood of an accurate prediction.
- the comparing device may take the form of a processor configured to receive and analyse consecutive images of a preselected location and to generate data which is indicative of movement in the preselected location.
- the data capture means and processor may be incorporated into a computer or workstation capable of performing the necessary capturing and processing functions.
- the system typically as part of the workstation, may include a data storage facility in order to store all data captured.
- the data that is captured and stored may include, but is not limited to:
- the parameters used within the algorithm usually relates to typical values for the related captured data.
- the parameters may also extend further, requiring multiple coinciding detections which form a complete image of the movement of the body.
- the body for example, an animai or human is sensed and logged as moving in a specific direction, and later again sensed by a further sensing operation or sensor in that direction, within an acceptable time-frame, a pattern is identified which increases the likelihood of an accurate prediction on whether the body is a human or animal.
- a pattern associated with wiidiife, which will likely be more random or specifically directed toward a water location can then be differentiated from the pattern of a human which would likely be more goal orientated.
- the algorithm may also compare different sets of data generated by separately captured images in order to establish movement patterns of animals moving across the range of vision of a single camera of other detector.
- the system may therefore still function with a single sensor.
- the analyses of the captured data may be done by means of a processor executing an algorithm, which algorithm, based on specific parameters, analyses and compares they captured data to a database of behavioural patterns relating to animals and humans; and to signal an alarm when a predetermined pattern is identified.
- Figure 1 depicts a schematic representation of a system for identifying and tracking humans, in accordance with the invention.
- FIG. 2 shows a block flow diagram of the data handling present in the system.
- the system 10 is installed to detect and monitor the movement of humans in a conservation area 12 and includes a number of sensors in the form of cameras 14, infrared motion sensors 16 and satellites 18 capable of generating satellite imagery. Ail of these sensors are configured to detect and some, such as the cameras can attempt to identify - although often inaccurately - the specific body detected, such as antelope 20 and humans 22.
- the sensors 14. 16, 18 comprise image capturing devotee for capturing images in a preselected area and a comparing device which processes the images and generate data relating to any movement of an animal 20 or human 22.
- the system 10 includes a computer in the form of a workstation 24, which workstation is provided with data capture and storage means wherein the data is stored digitally. Ail data generated by the sensors 14, 16, 18 is transmitted, captured and stored on the workstation 24.
- the workstation 24 includes a processor configured to execute an algorithm.
- the algorithm analyses the captured and stored data to establish a pattern which fal>s within parameters specific to the usual movement of humans.
- the algorithm differentiates between the movement pattern of humans 22 and other animals such as anteiope 20 based on factors such as the following: information received from camera images
- Position / Location The time that the movement or detection takes place as well as the likelihood of having any animals in a specific area
- the Group or cluster size is the group or cluster size
- This parameter includes the randomness of movement shown.
- Grazing and browsing animals tend to have more random behaviour which can be identified from a time analyses of the animal's position. This can be used to separate species, but even within a species this can be used to identify the activity. Humans that are busy with specific tasks will behave differently to humans that are moving from point A to point ⁇ .
- the position of an object is vital to the identification of that object.
- humans can navigate over most terrains., experts can assist to identify specific terrains where the likelihood of occurrence is higher. An example is that humans may not necessarily move along steep rocky slopes, but would rather prefer to follow water courses and fiat terrain.
- any large group of animals is less iikeiy to be human, and more likely to be one of the gregarious antelope species.
- the movement of antelope 20 typicaily follows an essentially random pattern or coincides with available grazing and water supplies, in contrast the movement of humans 22 is often more goal specific, with unauthorised human movement often taking place at night, when the movement of antelope 20 is usually minimal.
- - Behaviour can also be forced or predicted depending on the subject being tracked, making separation between species or objects easier.
- An example of this can be seen by analysing human and wild animal behaviour at a scent trail. Because humans have a relatively poor sense of smell, they will ignore a scent trail, yet other animals will pick up on the scent and pause, or even foilow it depending on the species and the scent.
- the database contains the same fields mentioned above, with default values or ranges of values for possible targets.
- Possible targets include mammals that are large enough to be detected, as well as man- made structures and objects such as vehicle and building, rocks, and any other object that can be detected with the sensors provided in the system.
- the algorithm can Incorporate and link the data captured from various sensors 14, 18. 18, in order to establish a movement pattern for an anlmai 20 or human 22. or groups of animals and humars. For example, a camera will be set to take a series of images over a specific period of time which will be send to the workstation for comparison and analysis. Once the system 10 identifies a pattern of movement in the images that is associated with the typical movement of humans 22, the processor generates an alarm, which can be acted upon by the necessary authorities.
- the system described above will particularly be useful In combating rhino poaching in national parks such as the Kruger National Park In South Africa
- the positioning of the sensors in the form of cameras such as FUR Ranger HITM and FUR SR - SeriesTM type, which can psck up movement upto 15 kilometres away, on elevated mobile structures on the border of the Kruger National Park w!ll allow early and timeous detection of humans approaching the border.
- the advantage of this system 10 is that false detections of unauthorised human activity made by cameras or other (ess specific sensors 5, 18 can be mitigated.
- the invention will likely reduce the number of false alarms, reducing the loss of resources resulting from such instances.
Abstract
According to the invention there is provided a monitoring system (10) for identifying and tracking humans which includes a sensor (14, 16, 18) for sensing movement of a body, data capture means (24) for capturing data relating to the movement received from the sensor (14, 16, 1 8), a processor configured to execute an algorithm, which algorithm, based on specific parameters, analyses and compares the captured data to a database of behavioural patterns relating to animals and humans, and alarm means for generating an alarm signal when a predetermined pattern is identified.
Description
SYSTEM FOR IDENTIFICATION AND TRACKING OF HUMANS
TECHNICAL FIELD OF THE INVENTION
The invention relates to a system of identifying humans, more specifically for differentiating humane from wild animais, especially in conservation areas.
BACKGROUND TO THE INVENTION
The inventor is aware of existing thermal, infra-red and similar technologies used in the detection of both humans and wild animais.
A problem associated with existing technology is that these detection systems cannot differentiate between humans and animais. unless a shape or size is available. These systems often trigger or generate an alarm when detecting irrelevant or unrelated animais. This is particularly the case when monitoring for human activity in areas abundant with wildlife.
The inventor having considered above now proposes the invention as described hereunder.
SUMMARY OF THE INVENTION
According to the invention there is provided a monitoring system for identifying and tracking humans which includes:
a sensor for sensing movement of a body:
data capture means for capturing data relating to the movement received from the sensor;
a processor configured to execute an algorithm, which algorithm, based on specific parameters, analyses and compares the captured data to a database of behavioural patterns relating to animais and humans; and
a!arm means for generating an alarm signal when a predetermined pattern is identified.
The sensor may comprise an image capturing device for capturing a series of images of a preselected location over a specific period of time, and a comparing device for comparing the images so as to determine movement in the preselected location.
The image capturing device may take the form of any one or more of a camera (including all variants such as standard, infrared, thermal, night-vision and any simiiar image or video capture devices), movement sensors (which typically includes infrared and laser trigger devices), deployed animal tracking devices such as radio collars and gps collars, and satellite imagery. It may also include recorded observations from humans.
These image capturing devices are used to determine the location of bodies and may also be used to attempt to identify or predict which type of body is being detected. Traditionally such detection is made with varying accuracy, usually accompanied by a statistical variance on the likelihood of an accurate prediction.
The comparing device may take the form of a processor configured to receive and analyse consecutive images of a preselected location and to generate data which is indicative of movement in the preselected location.
The data capture means and processor may be incorporated into a computer or workstation capable of performing the necessary capturing and processing functions.
The system, typically as part of the workstation, may include a data storage facility in order to store all data captured. The data that is captured and stored may include, but is not limited to:
the location of the sensor,
the location of the animal or human detected,
time of the detection,
ambient conditions including temperature,
the size of the animal detected,
the proximity to other detected objects and predicted group or cluster size, a prediction on the type of animal detected,
the speed of travel and direction in which animai is moving and
the randomness of the movement
The parameters used within the algorithm usually relates to typical values for the related captured data. The parameters may also extend further, requiring multiple coinciding detections which form a complete image of the movement of the body. As example, if the body, for example, an animai or human is sensed and logged as moving in a specific direction, and later again sensed by a further sensing operation or sensor in that direction, within an acceptable time-frame, a pattern is identified which increases the likelihood of an accurate prediction on whether the body is a human or animal.
A pattern associated with wiidiife, which will likely be more random or specifically directed toward a water location can then be differentiated from the pattern of a human which would likely be more goal orientated.
it is to be appreciated that the algorithm may also compare different sets of data generated by separately captured images in order to establish movement patterns of animals moving across the range of vision of a single camera of other detector. The system may therefore still function with a single sensor.
According to a second aspect of the invention there is provided a method of identifying and tracking humans, which method includes at least the steps of:
sensing movement of a body;
capturing the data relevant to the movement of the body;
comparing the captured data to a database of behavioural patterns of animals and humans; and
generating an alarm signal when a predetermined pattern is identified.
The analyses of the captured data may be done by means of a processor executing an algorithm, which algorithm, based on specific parameters, analyses and compares they captured data to a database of behavioural patterns relating to animals and humans; and to signal an alarm when a predetermined pattern is identified.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention will now be described by way of non-limiting example with reference to the accompanying drawing. in the drawings:
Figure 1 depicts a schematic representation of a system for identifying and tracking humans, in accordance with the invention; and
Figure 2 shows a block flow diagram of the data handling present in the system.
DETAILEO DESCRIPTION OF THE INVENTION
With reference now to the drawing, the system for identifying and tracking humans, in accordance with the invention, is generally indicated by reference numeral 10.
The system 10 is installed to detect and monitor the movement of humans in a conservation area 12 and includes a number of sensors in the form of cameras 14, infrared motion sensors 16 and satellites 18 capable of generating satellite imagery. Ail of these sensors are configured to detect and some, such as the cameras can attempt to identify - although often inaccurately - the specific body detected, such as antelope 20 and humans 22. The sensors 14. 16, 18 comprise image capturing devotee for capturing images in a preselected area and a comparing device which processes the images and generate data relating to any movement of an animal 20 or human 22.
The system 10 includes a computer in the form of a workstation 24, which workstation is provided with data capture and storage means wherein the data is stored digitally. Ail data generated by the sensors 14, 16, 18 is transmitted, captured and stored on the workstation 24.
As more clearly shown in Figure 2, the workstation 24 includes a processor configured to execute an algorithm. The algorithm analyses the captured and stored data to establish a pattern which fal>s within parameters specific to the usual movement of humans. The algorithm differentiates between the movement pattern of humans 22 and other animals such as anteiope 20 based on factors such as the following: information received from camera images
Position / Location
The time that the movement or detection takes place as well as the likelihood of having any animals in a specific area
Temperature
Direction of movement
Speed
The Group or cluster size
Water dependency
Proximity to human settlements
The randomness of the movement, which is the average time spent travelling in one direction and the frequency of direction changes
Behaviour due to external influences
Some of the parameters used to determine patterns are described in more detail below:
- Speed: The speed at which an object moves can help identify It. The fastest human speed recorded is around 45km/h, while several species of antelope and predators can easily exceed this speed. When the topography and habitat is brought into the equation, humans will probably not exceed 10km/h. making distinction between humans and animals even easier.
- Direction: This parameter includes the randomness of movement shown.
Grazing and browsing animals tend to have more random behaviour which can be identified from a time analyses of the animal's position. This can be used to separate species, but even within a species this can be used to identify the activity. Humans that are busy with specific tasks will behave differently to humans that are moving from point A to point Θ.
- Position / Location: The position of an object (source of heat on a thermal image) is vital to the identification of that object. Although humans can navigate over most terrains., experts can assist to identify specific terrains where the likelihood of occurrence is higher. An example is that humans
may not necessarily move along steep rocky slopes, but would rather prefer to follow water courses and fiat terrain.
- Group Size: By looking at objects in a group, the identification can be improved simply by counting the group size, in the anti-poaching context, poachers tend to not move around in large groups, and animals tend to quickly move away from human presence. Therefore, any large group of animals is less iikeiy to be human, and more likely to be one of the gregarious antelope species.
- Randomness of the movement: The movement of antelope 20 typicaily follows an essentially random pattern or coincides with available grazing and water supplies, in contrast the movement of humans 22 is often more goal specific, with unauthorised human movement often taking place at night, when the movement of antelope 20 is usually minimal.
Behaviour due to external influences:
- Behaviour can also be forced or predicted depending on the subject being tracked, making separation between species or objects easier. An example of this can be seen by analysing human and wild animal behaviour at a scent trail. Because humans have a relatively poor sense of smell, they will ignore a scent trail, yet other animals will pick up on the scent and pause, or even foilow it depending on the species and the scent.
• Similarly, human behaviour can be induced using objects mat will be ignored by animals, such as text, images, and aids for crossing obstacles.
This analysed pattern is compared to the existing database for identification purposes. The database contains the same fields mentioned above, with default values or ranges of values for possible targets. Possible targets include mammals that are large enough to be detected, as well as man- made structures and objects such as vehicle and building, rocks, and any other object that can be detected with the sensors provided in the system.
Importantly, the algorithm can Incorporate and link the data captured from various sensors 14, 18. 18, in order to establish a movement pattern for an anlmai 20 or human 22. or groups of animals and humars. For example, a camera will be set to take a series of images over a specific period of time which will be send to the workstation for comparison and analysis. Once the system 10 identifies a pattern of movement in the images that is associated with the typical movement of humans 22, the processor generates an alarm, which can be acted upon by the necessary authorities.
The system described above will particularly be useful In combating rhino poaching in national parks such as the Kruger National Park In South Africa The positioning of the sensors in the form of cameras such as FUR Ranger HI™ and FUR SR - Series™ type, which can psck up movement upto 15 kilometres away, on elevated mobile structures on the border of the Kruger National Park w!ll allow early and timeous detection of humans approaching the border.
The advantage of this system 10 is that false detections of unauthorised human activity made by cameras or other (ess specific sensors 5, 18 can be mitigated. The invention will likely reduce the number of false alarms, reducing the loss of resources resulting from such instances.
The example is provided in order to assist a person skilled In th¾ art In understanding the invention and should not be construed to limit the scope of the invention.
Claims
1. A monitoring system for identifying and tracking humans which includes: a sensor for sensing movement of a body;
data capture means for capturing data relating to the movement received from the sensor;
a processor configured to execute an algorithm, which algorithm, based on specific parameters, analyses and compares the captured data to a database of behavioural patterns relating to animals and humans; and alarm means for generating an alarm signai when a predetermined pattern is identified.
2. A monitoring system as claimed in claim 1 wherein the sensor includes: an image capturing device for capturing a series of images of a preselected location over a period of time; and
a comparing device for comparing the images in order to determine movement in the preselected location.
3. A monitoring system as claimed in claim 2 wherein the image capturing device is selected from any one or more of the group consisting of a camera, video capturing device, movement sensor and deployed animal tracking device.
4. A monitoring system as claimed in claim 3 wherein the deployed animal tracking device is selected from any one or more of the group consisting of a radio collar, gps collar and satellite imagery.
5. A monitoring system as claimed in claim 3 wherein the camera is selected from any one of more of the group consisting of infrared cameras, thermal cameras and night - vision cameras.
6. A monitoring system as claimed in any of claims 2 to 5 wherein the comparing device is in the form of a processor which identifies and generates data which is indicative of movement in the preselected location.
7. A monitoring system as claimed in any of the preceding claims wherein the data generated by the comparing device includes any one or more of the group consisting of sensor location, location of image, time of sensing, weather conditions, size of tody, proximity to other sensed objects, group or cluster size, speed of travel of body, direction of travel of body, and degree of randomness of movement of the body.
8. A monitoring device as claimed in any of the preceding claims wherein the data capture means is in the form of a processor.
9. A monitoring device as claimed in any of the preceding claims wherein the specific parameters include any one or more of the group consisting of speed of movement of body, topography of surroundings, direction of movement, contour of surroundings, group size in cases of multiple bodies and randomness of movement.
10. A monitoring device as claimed in any of the preceding claims wherein the behavioural patterns include any one or more of the group consisting of the existence of a scent trail and existence of signage and images capable of being interpreted by humans.
11. A monitoring system as claimed in any of the preceding claims wherein data from multiple sensors are used to create an image of the path of movement of the body.
12. A method of identifying and tracking humans, which method includes at least the steps of:
sensing movement of a body;
capturing data relative to the movement of the body;
comparing the captured data to a database of behavioural patterns of animals and humans: and
generating an alarm signai when a predetermined pattern is identified.
13. A method as claimed in claim 8 wherein the comparing of the captured data to a database of behavioural patterns of animals and humans is performed by means of a processor configured to execute an algorithm, which algorithm, based on specific parameters, analyses and compares the captured data to a database of existing behavioural patterns of animals and humans and to generate an alarm signal when a predetermined pattern is identified.
14. A monitoring system, according to the invention, substantially as hereinbefore described or exemplified.
15. A monitoring system as specifically described with reference tc or 3$ illustrated in any one of the accompanying drawings.
16. A monitoring system, including any new and inventive integer or combination of integers, substantially as herein described.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
ZA201307015 | 2013-09-18 | ||
ZA2013/07015 | 2013-09-18 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015058219A1 true WO2015058219A1 (en) | 2015-04-23 |
Family
ID=52828804
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/ZA2014/000052 WO2015058219A1 (en) | 2013-09-18 | 2014-09-18 | System for identification and tracking of humans |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2015058219A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110459027A (en) * | 2019-08-15 | 2019-11-15 | 青岛文达通科技股份有限公司 | A kind of Community Safety means of defence and system based on multi-source heterogeneous data fusion |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080169929A1 (en) * | 2007-01-12 | 2008-07-17 | Jacob C Albertson | Warning a user about adverse behaviors of others within an environment based on a 3d captured image stream |
WO2011036661A1 (en) * | 2009-09-24 | 2011-03-31 | Elbit Systems Ltd. | System and method for long-range surveillance of a scene and alerting of predetermined unusual activity |
CN102246705A (en) * | 2010-05-19 | 2011-11-23 | 张彩凤 | Method and system for analyzing animal behaviours by using signal processing technology |
KR20110130033A (en) * | 2010-05-27 | 2011-12-05 | 박용헌 | Active image monitoring system using motion pattern database, and method thereof |
-
2014
- 2014-09-18 WO PCT/ZA2014/000052 patent/WO2015058219A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080169929A1 (en) * | 2007-01-12 | 2008-07-17 | Jacob C Albertson | Warning a user about adverse behaviors of others within an environment based on a 3d captured image stream |
WO2011036661A1 (en) * | 2009-09-24 | 2011-03-31 | Elbit Systems Ltd. | System and method for long-range surveillance of a scene and alerting of predetermined unusual activity |
CN102246705A (en) * | 2010-05-19 | 2011-11-23 | 张彩凤 | Method and system for analyzing animal behaviours by using signal processing technology |
KR20110130033A (en) * | 2010-05-27 | 2011-12-05 | 박용헌 | Active image monitoring system using motion pattern database, and method thereof |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110459027A (en) * | 2019-08-15 | 2019-11-15 | 青岛文达通科技股份有限公司 | A kind of Community Safety means of defence and system based on multi-source heterogeneous data fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102153591B1 (en) | Method and apparatus for detecting garbage dumping action in real time on video surveillance system | |
JP7147420B2 (en) | OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD AND COMPUTER PROGRAM FOR OBJECT DETECTION | |
JP5121258B2 (en) | Suspicious behavior detection system and method | |
KR101788269B1 (en) | Method and apparatus for sensing innormal situation | |
JP7078021B2 (en) | Object detection device, object detection method and computer program for object detection | |
CA3043400C (en) | Systems and methods for detecting flying animals | |
CN106448160B (en) | Target person tracking method combining vehicle running track and monitoring video data | |
JP2017512991A (en) | Target object detection method, detection apparatus, and robot | |
JP7000805B2 (en) | Animal rescue systems and methods, as well as the servers and programs used in them. | |
Bhadwal et al. | Smart border surveillance system using wireless sensor network and computer vision | |
CN106341661A (en) | Patrol robot | |
US10212396B2 (en) | Remote tracking of objects | |
JP2014194686A (en) | Crime prevention system | |
CA2876131C (en) | Gnss jammer detection system with optical tracking and identification | |
KR101454644B1 (en) | Loitering Detection Using a Pedestrian Tracker | |
CN102244769B (en) | Object and key person monitoring system and method thereof | |
CN103152558A (en) | Intrusion detection method based on scene recognition | |
Yang et al. | On-road collision warning based on multiple FOE segmentation using a dashboard camera | |
CA2920823C (en) | Object detection apparatus, object detection method, and object detection system | |
WO2015058219A1 (en) | System for identification and tracking of humans | |
Choubisa et al. | An optical-camera complement to a PIR sensor array for intrusion detection and classfication in an outdoor environment | |
CN109815921A (en) | The prediction technique and device of the class of activity in hydrogenation stations | |
CN202904792U (en) | Intelligent visualized alarm system | |
CN102999988B (en) | Intelligent visualization alarm system and method for alarming by using system | |
KR101920342B1 (en) | Method for surveillance based on image and apparatus for using the method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14853556 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14853556 Country of ref document: EP Kind code of ref document: A1 |