CN106210633A - Line detection alarm method and device are got in a kind of wisdom gold eyeball identification - Google Patents
Line detection alarm method and device are got in a kind of wisdom gold eyeball identification Download PDFInfo
- Publication number
- CN106210633A CN106210633A CN201610564031.9A CN201610564031A CN106210633A CN 106210633 A CN106210633 A CN 106210633A CN 201610564031 A CN201610564031 A CN 201610564031A CN 106210633 A CN106210633 A CN 106210633A
- Authority
- CN
- China
- Prior art keywords
- image
- dimensional
- monitoring region
- moving target
- target
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of wisdom gold eyeball identification and get over line detection alarm method and device, described method comprises the following steps: S1. sets up the threedimensional model in monitoring region, and generates simulation warning line in the three-dimensional model；S2. the three dimensional depth image in binocular image acquisition module Real-time Collection monitoring region is utilized；S3. extract the moving target in three dimensional depth image, and according to image depth information, moving target is projected in threedimensional model；Calculate the vertical dimension of moving target and simulation warning line the most in the three-dimensional model: if vertical dimension is less than the distance threshold preset, it is believed that cross-lane occurs, carry out more report from a liner alert.The present invention is capable of identify that cross-lane, and reports to the police when cross-lane occurs, and is conducive to adopting right measures in time, it is to avoid the harm that cross-lane brings.
Description
Technical field
The present invention relates to a kind of wisdom gold eyeball identification and get over line detection alarm method and device.
Background technology
At present in safety-security area, general by the event in photographic head detection current region, in detection monitoring region
Movable people or thing；But existing detection technique can only shoot the content of image, it is impossible to the content of image is done further
Analyze: when line situation occurs getting in current monitored area, it is impossible to and alarm, it is unfavorable for gathering correct counter-measure.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, it is provided that line detection alarm method is got in the eyeball identification of a kind of intelligent gold
And device, it is possible to identify the more line situation in monitoring region, and then it is alert to carry out more report from a liner in time.
It is an object of the invention to be achieved through the following technical solutions: line detection warning side is got in a kind of wisdom gold eyeball identification
Method, including:
S1. set up the threedimensional model in monitoring region, and generate simulation warning line in the three-dimensional model；
S2. the three dimensional depth image in binocular image acquisition module Real-time Collection monitoring region is utilized；
S3. extract the moving target in three dimensional depth image, and according to image depth information, moving target projected to three-dimensional mould
In type；
S4. calculate moving target according to threedimensional model and simulate the vertical dimension of warning line:
(1) if vertical dimension is less than the distance threshold preset, there is cross-lane, enter step S5；
(2) if vertical dimension is not less than predetermined threshold value, there is not cross-lane, return step S2.
S5. more report from a liner is carried out alert.
Described step S1 includes following sub-step:
S11. gather one frame monitoring region nobody time three dimensional depth image；
S12. according to three dimensional depth image information, the threedimensional model in monitoring region is set up.
Described binocular image acquisition module includes two dimension photographic head and three-dimensional visual sensor, in described step S2,
Utilize two dimension camera collection monitoring region two-dimensional image information, utilize the graphics in three-dimensional visual sensor acquisition monitoring region
As information, and according to the image information acquisition picture depth collected, obtain three dimensional depth image.
Described step S3 includes following sub-step:
S31. algorithm of target detection is used to detect and obtain the pixel that the target entered in monitoring region occupies in video image
Point set；
S32. according to described pixel set, object extraction algorithm is used to obtain the target entered in monitoring region at video figure
Position in Xiang and size；
S33. according to the target extracted from video image, use effective target feature recognition algorithms, identify in video image
Moving target；
S34. according to the depth of view information of three dimensional depth image, moving target is projected in threedimensional model.
Line detection alarm device is got in a kind of wisdom gold eyeball identification, including:
Three-dimension modeling module, for setting up the threedimensional model in monitoring region；
Binocular image acquisition module, for the three dimensional depth image in acquisition monitoring region, including two dimension photographic head and 3D vision
Sensor；
Target projection module, for extracting moving target, and according to image depth information, by motion mesh from three dimensional depth image
Mark projects in threedimensional model；
Distance calculation module, for calculating the vertical dimension of moving target in threedimensional model and simulation warning line, and will vertically away from
Compare from distance threshold；
Alarm command generation module, for generating alarm command when vertical dimension is less than distance threshold；
Alarm module, for the alarm command of the response alert judge module of more report from a liner, carries out more report from a liner alert.
The invention has the beneficial effects as follows: set up the threedimensional model in monitoring region and generate simulation warning line, to real-time three
Dimension image information is analyzed, and extracts moving target head and projects in threedimensional model, according to moving target and simulation warning line
Vertical dimension judges whether to occur cross-lane, and reports to the police when there is cross-lane, is conducive to taking in time correctly to arrange
Execute, it is to avoid the harm that cross-lane brings.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of the present invention；
Fig. 2 is assembly of the invention theory diagram.
Detailed description of the invention
Technical scheme is described in further detail below in conjunction with the accompanying drawings, but protection scope of the present invention is not limited to
The following stated.
As it is shown in figure 1, line detection alarm method is got in a kind of wisdom gold eyeball identification, including:
S1. set up the threedimensional model in monitoring region, and generate simulation warning line in the three-dimensional model；
S2. the three dimensional depth image in binocular image acquisition module Real-time Collection monitoring region is utilized；
S3. extract the moving target in three dimensional depth image, and according to image depth information, moving target projected to three-dimensional mould
In type；
S4. calculate moving target according to threedimensional model and simulate the vertical dimension of warning line:
(1) if vertical dimension is less than the distance threshold preset, there is cross-lane, enter step S5；
(2) if vertical dimension is not less than predetermined threshold value, there is not cross-lane, return step S2.
Here vertical dimension refers to the vertical dimension of moving target and simulation warning line place perpendicular
S5. more report from a liner is carried out alert.
In the application, moving target and simulation warning line distance the least (during less than distance threshold), it is possible to determine that this target
Get over line, therefore carry out more report from a liner alert.
In one embodiment, in order to make more report from a liner alert more accurate, in vertical dimension less than the distance threshold preset, send out
During raw cross-lane, can judge whether to report to the police according to moving target position in the three-dimensional model: i.e. described step
Rapid S5 includes: be the most very that threedimensional model is divided into warning region and normal region by position according to simulation warning line: if motion
Target is in warning region and there occurs cross-lane, illustrate that moving target just more line goes to normal region, does not reports
Alert；If moving target there occurs again cross-lane in being in normal region, illustrate that moving target just goes to from normal region
Warning region, needs to carry out more report from a liner alert.
In another embodiment, in order to make more report from a liner alert more accurate, can in conjunction with more line direction judge whether into
Row is reported to the police, and i.e. described step S5 includes: the most very according to simulation warning line be position threedimensional model is divided into warning region and
Normal region；In vertical dimension less than the distance threshold preset, when there is cross-lane, (delay time can to carry out time delay setting
From Row sum-equal matrix),
Then moving target is tracked detection, in delay time, extracts the moving target in each frame three dimensional depth image,
And according to depth of view information, moving target is projected in threedimensional model, obtain in moving target delay time in the three-dimensional model
Track, may determine that the more line direction of moving target: if moving target goes to normal district from warning region according to movement locus
Territory, does not reports to the police, if moving target goes to warning region from normal region, then carries out more report from a liner alert.
At different application scenarios, for warning region (not allowing the region arbitrarily entered) and normal region (allow into
The region entered) division be different:
Such as between bank ATM, in warning region i.e. warning line, normal region is outside warning line；
And for example in railroad platform, warning region is outside warning line, is susceptible to security incident；In normal region is warning line,
Can walk about and not worry safety problem.
Described step S1 includes following sub-step:
S11. gather one frame monitoring region nobody time three dimensional depth image；
S12. according to three dimensional depth image information, the threedimensional model in monitoring region is set up.
Described binocular image acquisition module includes two dimension photographic head and three-dimensional visual sensor, in described step S2,
Utilize two dimension camera collection monitoring region two-dimensional image information, utilize the graphics in three-dimensional visual sensor acquisition monitoring region
As information (i.e. monitoring the three-dimensional scene information in region)；According to three-dimensional scene information or Binocular Vision Principle, figure all can be obtained
The degree of depth of picture, therefore the two-dimentional photographic head and three-dimensional visual sensor collection by binocular image acquisition module can obtain three dimensional depth
Image.
Described step S3 includes following sub-step:
S31. algorithm of target detection is used to detect and obtain the pixel that the target entered in monitoring region occupies in video image
Point set；
Further, the algorithm of target detection of employing is the Gaussian Mixture Background Algorithm in background subtraction class algorithm, and this algorithm is
Prior art, the ultimate principle of this algorithm is: in video image, there is gray difference, video figure between target and background
The grey level histogram of picture can present and background, target multimodal one to one, by many for the grey level histogram of video image peak characters
It is considered as the superposition of multiple Gauss distribution, the segmentation of the background in video image and target can be realized.
S32. according to described pixel set, use object extraction algorithm to obtain the target entered in monitoring region and regarding
Frequently the position in image and size:
S321. utilize region-growing method obtain described in the growth district of pixel set；
Specifically, with each pixel in the pixel set obtained for sub pixel point, and with the ash of these pixels
Angle value sets up growth district Gauss distribution as mathematical expectation；
The each pixel meeting growth district Gauss distribution in each sub pixel point surrounding neighbors is merged respectively as growing point
In the region at each sub pixel point place, then using each growing point as new sub pixel point, repeat this step to the newest
Growing point occur, can obtain the growth district of pixel set, and then each target obtaining entering in monitoring region exists
Position in video image.
S322. K characteristics of mean clustering procedure is used to obtain each target entered in monitoring region chi in video image
Very little.
Specifically, use K characteristics of mean clustering procedure, choose the average point of each growth district as cluster centre, meter
Calculate each sample distance to cluster centre, each sample is grouped into the class from its that nearest cluster centre place, and root
According to calculating each the data object meansigma methods clustered formed, obtain new cluster centre, repeat this step to adjacent twice
The cluster centre obtained is not changed in, then show that sample adjusts and terminate, and clustering criteria function has been restrained, and i.e. can obtain entering prison
Each target in control region size in video image.
S33. according to the target extracted from video image, use effective target feature recognition algorithms, identify video figure
Moving target in Xiang；
S34. according to the depth of view information of three dimensional depth image, moving target is projected in threedimensional model.
As in figure 2 it is shown, line detection alarm device is got in a kind of wisdom gold eyeball identification, including:
Three-dimension modeling module, for setting up the threedimensional model in monitoring region；
Binocular image acquisition module, for the three dimensional depth image in acquisition monitoring region；
Target projection module, for extracting moving target, and according to image depth information, by motion mesh from three dimensional depth image
Mark projects in threedimensional model；
Distance calculation module, for calculating the vertical dimension of moving target in threedimensional model and simulation warning line, and will vertically away from
Compare from distance threshold；
Alarm command generation module, for generating alarm command when vertical dimension is less than distance threshold；
Alarm module, for the alarm command of the response alert judge module of more report from a liner, carries out more report from a liner alert.
Described image capture module includes two dimension photographic head and three-dimensional visual sensor.
Above example is only in order to illustrate technical scheme and unrestricted, although with reference to preferred embodiment to this
Bright it is described in detail, it will be understood by those within the art that, technical scheme can be modified
Or equivalent, without deviating from objective and the scope of technical solution of the present invention, it all should contain the claim in the present invention
In the middle of scope.
Claims (6)
1. line detection alarm method is got in a wisdom gold eyeball identification, it is characterised in that: comprise the following steps:
S1. set up the threedimensional model in monitoring region, and generate simulation warning line in the three-dimensional model；
S2. the three dimensional depth image in binocular image acquisition module Real-time Collection monitoring region is utilized；
S3. extract the moving target in three dimensional depth image, and according to image depth information, moving target projected to three-dimensional mould
In type；
S4. calculate moving target according to threedimensional model and simulate the vertical dimension of warning line:
(1) if vertical dimension is less than the distance threshold preset, there is cross-lane, enter step S5；
(2) if vertical dimension is not less than predetermined threshold value, there is not cross-lane, return step S2；
S5. more report from a liner is carried out alert.
Line detection alarm method is got in a kind of wisdom gold eyeball identification the most according to claim 1, it is characterised in that: described step
Rapid S1 includes following sub-step:
S11. gather one frame monitoring region nobody time three dimensional depth image；
S12. according to three dimensional depth image information, the threedimensional model in monitoring region is set up.
Line detection alarm method is got in a kind of wisdom gold eyeball identification the most according to claim 1, it is characterised in that: described is double
Mesh image capture module includes two dimension photographic head and three-dimensional visual sensor, in described step S2, utilizes two dimension photographic head to adopt
Collection monitoring region two-dimensional image information, utilizes the three-dimensional image information in three-dimensional visual sensor acquisition monitoring region, and according to adopting
The image information acquisition picture depth that collection arrives, obtains three dimensional depth image.
Line detection alarm method is got in a kind of wisdom gold eyeball identification the most according to claim 1, it is characterised in that: described step
Rapid S3 includes following sub-step:
S31. algorithm of target detection is used to detect and obtain the pixel that the target entered in monitoring region occupies in video image
Point set；
S32. according to described pixel set, object extraction algorithm is used to obtain the target entered in monitoring region at video figure
Position in Xiang and size；
S33. according to the target extracted from video image, use effective target feature recognition algorithms, identify in video image
Moving target；
S34. according to the depth of view information of three dimensional depth image, moving target is projected in threedimensional model.
5. line detection alarm device is got in a wisdom gold eyeball identification, it is characterised in that: including:
Three-dimension modeling module, for setting up the threedimensional model in monitoring region；
Binocular image acquisition module, for the three dimensional depth image in acquisition monitoring region；
Target projection module, for extracting moving target, and according to image depth information, by motion mesh from three dimensional depth image
Mark projects in threedimensional model；
Distance calculation module, for calculating the vertical dimension of moving target in threedimensional model and simulation warning line, and will vertically away from
Compare from distance threshold；
Alarm command generation module, for generating alarm command when vertical dimension is less than distance threshold；
Alarm module, for the alarm command of the response alert judge module of more report from a liner, carries out more report from a liner alert.
Line detection alarm method is got in a kind of wisdom gold eyeball identification the most according to claim 5, it is characterised in that: described is double
Mesh image capture module includes two dimension photographic head and three-dimensional visual sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610564031.9A CN106210633A (en) | 2016-07-18 | 2016-07-18 | Line detection alarm method and device are got in a kind of wisdom gold eyeball identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610564031.9A CN106210633A (en) | 2016-07-18 | 2016-07-18 | Line detection alarm method and device are got in a kind of wisdom gold eyeball identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106210633A true CN106210633A (en) | 2016-12-07 |
Family
ID=57492862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610564031.9A Pending CN106210633A (en) | 2016-07-18 | 2016-07-18 | Line detection alarm method and device are got in a kind of wisdom gold eyeball identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106210633A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108156430A (en) * | 2018-02-22 | 2018-06-12 | 天津天地伟业信息***集成有限公司 | Warning area projection camera and video recording method |
| CN109658374A (en) * | 2017-10-06 | 2019-04-19 | 罗伯特·博世有限公司 | For the method for assembly station, assembly station, equipment, computer program and the computer-readable medium for implementing the above method |
| CN109887141A (en) * | 2019-02-28 | 2019-06-14 | 浙江大唐乌沙山发电有限责任公司 | Applied to the managerial intelligent managing and control system of power plant safety and management-control method |
| CN109920186A (en) * | 2019-04-19 | 2019-06-21 | 沈阳风驰软件股份有限公司 | A kind of detection of platform edge and geofence control system and method |
| CN110334670A (en) * | 2019-07-10 | 2019-10-15 | 北京迈格威科技有限公司 | Object monitor method and device, electronic equipment, storage medium |
| CN111524309A (en) * | 2020-05-09 | 2020-08-11 | 南宁市第三中学 | ATM anti-riot alarm method based on skeleton tracking |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110205363A1 (en) * | 2010-02-24 | 2011-08-25 | Denso Corporation | Boundary line detection system with improved detection-performance |
| CN202600885U (en) * | 2012-05-18 | 2012-12-12 | 成都百威讯科技有限责任公司 | Intelligent video perimeter fence system |
| CN103400120A (en) * | 2013-08-02 | 2013-11-20 | 上海泓申科技发展有限公司 | Video analysis-based bank self-service area push behavior detection method |
| CN104902246A (en) * | 2015-06-17 | 2015-09-09 | 浙江大华技术股份有限公司 | Video monitoring method and device |
-
2016
- 2016-07-18 CN CN201610564031.9A patent/CN106210633A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110205363A1 (en) * | 2010-02-24 | 2011-08-25 | Denso Corporation | Boundary line detection system with improved detection-performance |
| CN202600885U (en) * | 2012-05-18 | 2012-12-12 | 成都百威讯科技有限责任公司 | Intelligent video perimeter fence system |
| CN103400120A (en) * | 2013-08-02 | 2013-11-20 | 上海泓申科技发展有限公司 | Video analysis-based bank self-service area push behavior detection method |
| CN104902246A (en) * | 2015-06-17 | 2015-09-09 | 浙江大华技术股份有限公司 | Video monitoring method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658374A (en) * | 2017-10-06 | 2019-04-19 | 罗伯特·博世有限公司 | For the method for assembly station, assembly station, equipment, computer program and the computer-readable medium for implementing the above method |
| CN108156430A (en) * | 2018-02-22 | 2018-06-12 | 天津天地伟业信息***集成有限公司 | Warning area projection camera and video recording method |
| CN108156430B (en) * | 2018-02-22 | 2023-12-22 | 天津天地伟业信息***集成有限公司 | Guard zone projection camera and video recording method |
| CN109887141A (en) * | 2019-02-28 | 2019-06-14 | 浙江大唐乌沙山发电有限责任公司 | Applied to the managerial intelligent managing and control system of power plant safety and management-control method |
| CN109920186A (en) * | 2019-04-19 | 2019-06-21 | 沈阳风驰软件股份有限公司 | A kind of detection of platform edge and geofence control system and method |
| CN110334670A (en) * | 2019-07-10 | 2019-10-15 | 北京迈格威科技有限公司 | Object monitor method and device, electronic equipment, storage medium |
| CN110334670B (en) * | 2019-07-10 | 2021-08-17 | 北京迈格威科技有限公司 | Object monitoring method and device, electronic equipment and storage medium |
| CN111524309A (en) * | 2020-05-09 | 2020-08-11 | 南宁市第三中学 | ATM anti-riot alarm method based on skeleton tracking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106210633A (en) | Line detection alarm method and device are got in a kind of wisdom gold eyeball identification | |
| CN106128053A (en) | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device | |
| CN106128022B (en) | A kind of wisdom gold eyeball identification violent action alarm method | |
| CN105574501B (en) | A kind of stream of people's video detecting analysis system | |
| CN103077423B (en) | To run condition detection method based on crowd's quantity survey of video flowing, local crowd massing situation and crowd | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
| CN106980829B (en) | Abnormal behaviour automatic testing method of fighting based on video analysis | |
| CN109934848B (en) | Method for accurately positioning moving object based on deep learning | |
| CN103279791B (en) | Based on pedestrian's computing method of multiple features | |
| CN103020606B (en) | Pedestrian detection method based on spatio-temporal context information | |
| CN109255298A (en) | Safety helmet detection method and system in dynamic background | |
| CN104821056A (en) | Intelligent guarding method based on radar and video integration | |
| CN103164858A (en) | Adhered crowd segmenting and tracking methods based on superpixel and graph model | |
| CN106210635A (en) | A kind of wisdom gold eyeball identification is moved through method and apparatus of reporting to the police | |
| CN106682573B (en) | A kind of pedestrian tracting method of single camera | |
| CN104616438A (en) | Yawning action detection method for detecting fatigue driving | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
| CN104318578A (en) | Video image analyzing method and system | |
| CN105931429B (en) | A kind of wisdom gold eyeball identification night proximity sensing method and apparatus | |
| CN103177247A (en) | Target detection method fused with multi-angle information | |
| CN106228709A (en) | It is a kind of that wisdom gold eyeball identification is single adds paper money alarm method and device | |
| CN109035305A (en) | Indoor human body detection and tracking in the case of a kind of low visual angle based on RGB-D | |
| CN113362374A (en) | High-altitude parabolic detection method and system based on target tracking network | |
| CN113436229A (en) | Multi-target cross-camera pedestrian trajectory path generation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |