CN108921867A - A kind of motion detection and human body recognition method of panoramic picture - Google Patents
A kind of motion detection and human body recognition method of panoramic picture Download PDFInfo
- Publication number
- CN108921867A CN108921867A CN201810562042.2A CN201810562042A CN108921867A CN 108921867 A CN108921867 A CN 108921867A CN 201810562042 A CN201810562042 A CN 201810562042A CN 108921867 A CN108921867 A CN 108921867A
- Authority
- CN
- China
- Prior art keywords
- motion
- data
- panoramic picture
- information
- players
- 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 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000001133 acceleration Effects 0.000 claims abstract description 19
- 238000000926 separation method Methods 0.000 claims abstract description 7
- 230000003252 repetitive effect Effects 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 description 4
- 230000010354 integration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Automation & Control Theory (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of motion detection of panoramic picture and human body recognition methods, include the following steps:S1, sensor acquire the original motion data, pass to information process unit;S2, information process unit handle the original motion data, and motion process data are stored;S3, motion profile is acquired, and passes to image processing unit, synthesize panoramic picture;S4, panoramic picture is subjected to image separation, obtains node image, data information is subjected to sub-frame processing according to the different of timing node, obtains node data;S5, the image of same time node and data are combined.The present invention captures the original motion information of players by six axle sensors, and six axle sensor by 3 axis gyro sensors and the collected motion information result of 3 axle acceleration sensors it is accurate, so that the motion information that information process unit receives is more accurate, the motion detection result of finally obtained panoramic picture is truer, reliably.
Description
Technical field
The present invention relates to motion detection and image identification technical field more particularly to a kind of motion detection of panoramic picture and
Human body recognition method.
Background technique
With the improvement of broadband transmission environment, the video image transmission of high quality will also become future trend, with correlation
Under popular the driving of the universalness and price of computer hardware, the demand of the video image service of high quality also start it is growing day by day,
Since the data volume of high-quality video image itself is comparable huge, in the transmission process for carrying out video image, all
Necessary compression processing must be carried out to video image, it can be efficient suitable under the limitation of limited bandwidth or capacity
Benefit completes video image transmission.Existing motion detection device is typically all the motion information for detecting players, not three
The motion profile and motion information of players are shown in dimension space, and existing technology does not take identification in panoramic picture
The human body information of players.
Therefore, we have proposed a kind of motion detections of panoramic picture and human body recognition method for solving the above problems.
Summary of the invention
The purpose of the present invention is to solve disadvantages existing in the prior art, and a kind of movement of the panoramic picture proposed
Detection and human body recognition method.
A kind of motion detection of panoramic picture, includes the following steps:
S1, the original motion data of players during the motion is acquired using six axle sensors, and by original fortune
Dynamic data pass to information process unit;
S2, information process unit receive the original motion data, and the original motion data is handled, and obtain motion process
Motion process data are transmitted to mobile terminal or cloud carry out the storage of data information by data;
S3, it is equipped with digital flow camera to carry out the motion profile of players on the moving line of players
Acquisition, and collection result is passed into image processing unit, image processing unit is inquired static according to the information of collection result
Image, the video image of low repeatability and the video image of high-repetition-rate, and closed collection result according to different repetitive rates
At panoramic picture;
S4, panoramic picture is subjected to the separation of image branch according to the different of timing node, obtains multiple node images, will deposits
It stores up the data information in mobile terminal or cloud and carries out sub-frame processing according to the different of timing node, obtain node data;
S5, the image of same time node and data are combined.
Preferably, the internal integration of six axle sensor 3 axis gyro sensors and 3 axle acceleration sensors, it is former
Beginning motion profile includes three shaft angle acceleration and 3-axis acceleration, and 3 axis gyro sensors acquire the data of 3-axis acceleration
Information, 3 axle acceleration sensors acquire the data information of 3-axis acceleration, and six axle sensors are located at the body of players
On.
Preferably, the motion process data include the starting point of players during the motion, horizontal displacement distance,
The distance that moves vertically and run duration.
Preferably, the quantity of the digital flow camera has 1216, and digital flow camera is equal with 360 degree of angles
Even placement.
Preferably, the mobile terminal is mobile phone terminal or computer end.
A kind of human body recognition method of panoramic picture, includes the following steps:
S1, it is equipped with digital flow camera to carry out the motion profile of players on the moving line of players
Acquisition, and collection result is passed into image processing unit, image processing unit is inquired static according to the information of collection result
Image, the video image of low repeatability and the video image of high-repetition-rate, and closed collection result according to different repetitive rates
At panoramic picture;
S2, infrared sensor of the human body and infrared non-contact human temperature sensor measure players in different location
Information data, and information data is subjected to sub-frame processing according to the different of timing node, obtain node data;
S3, background model is established according to panoramic picture, panoramic picture is subjected to image according to the different of timing node
Branch separation, obtains multiple node images, determines human motion region using the timing node difference between multiple node images,
And it will be in the human motion region for being filled into same time node of node data;
S4, result progress binary conversion treatment will be filled using maximum between-cluster variance thresholding method, while analyzing segmentation
Effective filling result is uploaded to mobile terminal or cloud, and updates panoramic picture by validity;
S5, the human body information of players in panoramic picture is compared with the human body information of pre-stored players,
And the human body information of the players in mobile terminal display identification.
Preferably, the model LH1958 of the infrared sensor of the human body, the type of infrared non-contact human temperature sensor
Number be MLX90615SSG-DAA.
The beneficial effects of the invention are as follows:
1, of the invention, the original motion information of players is captured by six axle sensors, and six axle sensors are logical
It crosses 3 axis gyro sensors and the collected motion information result of 3 axle acceleration sensors is accurate, so that information process unit connects
The motion information received is more accurate, and the motion detection result of finally obtained panoramic picture is truer, reliably.
2, of the invention, in the synthesis of panoramic picture, by the way that collection result is synthesized according to different repetitive rates, so that
The information conversion of panoramic picture during processing is more acurrate, and error is smaller.
3, of the invention, movement people is measured by using infrared sensor of the human body and infrared non-contact human temperature sensor
Member different location information data so that obtained human body information result is more accurate, finally relatively and the movement that identifies
The result of the human body information of personnel is more true and reliable, and accuracy as a result is higher.
Specific embodiment
Combined with specific embodiments below the present invention is made further to explain.
Embodiment
A kind of motion detection of panoramic picture, includes the following steps:
The internal integration of S1, six axle sensors 3 axis gyro sensors and 3 axle acceleration sensors, original motion rail
Mark includes three shaft angle acceleration and 3-axis acceleration, and 3 axis gyro sensors acquire the data information of 3-axis acceleration, 3 axis
Acceleration transducer acquires the data information of 3-axis acceleration, and six axle sensors are located on the body of players, use six
Axle sensor acquires the original motion data of players during the motion, and the original motion data is passed at information
Manage unit;
S2, information process unit receive the original motion data, and the original motion data is handled, and obtain including fortune
The starting point of moving member during the motion, horizontal displacement distance, the motion process data for the distance and run duration of moving vertically will
Motion process data are transmitted to cell phone end or computer end or cloud carries out the storage of data information;
S3, be equipped with 12-16 digital flow camera on the moving line of players, and number flow camera with
360 degree of even angles are placed to be acquired to the motion profile of players, and collection result is passed to image procossing list
Member, image processing unit inquire static image, the video image and high-repetition-rate of low repeatability according to the information of collection result
Video image, and collection result is synthesized by panoramic picture according to different repetitive rates;
S4, panoramic picture is subjected to the separation of image branch according to the different of timing node, obtains multiple node images, will deposits
It stores up the data information in mobile terminal or cloud and carries out sub-frame processing according to the different of timing node, obtain node data;
S5, the image of same time node and data are combined.
A kind of human body recognition method of panoramic picture, includes the following steps:
S1, it is equipped with digital flow camera to carry out the motion profile of players on the moving line of players
Acquisition, and collection result is passed into image processing unit, image processing unit is inquired static according to the information of collection result
Image, the video image of low repeatability and the video image of high-repetition-rate, and closed collection result according to different repetitive rates
At panoramic picture;
S2, it non-is connect using the infrared sensor of the human body of model LH1958 and the infrared of model MLX90615SSG-DAA
Temperature sensor for human body is touched to measure players in the information data of different location, and by information data according to timing node
Difference carries out sub-frame processing, obtains node data;
S3, background model is established according to panoramic picture, panoramic picture is subjected to image according to the different of timing node
Branch separation, obtains multiple node images, determines human motion region using the timing node difference between multiple node images,
And it will be in the human motion region for being filled into same time node of node data;
S4, result progress binary conversion treatment will be filled using maximum between-cluster variance thresholding method, while analyzing segmentation
Effective filling result is uploaded to mobile terminal or cloud, and updates panoramic picture by validity;
S5, the human body information of players in panoramic picture is compared with the human body information of pre-stored players,
And the human body information of the players in mobile terminal display identification.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (7)
1. a kind of motion detection of panoramic picture, which is characterized in that include the following steps:
S1, the original motion data of players during the motion is acquired using six axle sensors, and by original motion number
According to passing to information process unit;
S2, information process unit receive the original motion data, and the original motion data is handled, and obtain motion process number
According to motion process data are transmitted to the storage that mobile terminal or cloud carry out data information;
S3, digital flow camera is equipped on the moving line of players to adopt to the motion profile of players
Collection, and collection result is passed into image processing unit, image processing unit inquires static figure according to the information of collection result
Picture, the video image of low repeatability and the video image of high-repetition-rate, and synthesized collection result according to different repetitive rates
Panoramic picture;
S4, panoramic picture is subjected to the separation of image branch according to the different of timing node, obtains multiple node images, will be stored in
Mobile terminal or the data information in cloud obtain node data according to the different progress sub-frame processings of timing node;
S5, the image of same time node and data are combined.
2. a kind of motion detection of panoramic picture according to claim 1, which is characterized in that six axle sensor it is interior
Portion incorporates 3 axis gyro sensors and 3 axle acceleration sensors, and original motion trajectory includes that three shaft angle acceleration and three axis add
Speed, and the data information of 3 axis gyro sensors acquisition 3-axis acceleration, 3 axle acceleration sensors acquire 3-axis acceleration
Data information, and six axle sensors are located on the body of players.
3. a kind of motion detection of panoramic picture according to claim 1, which is characterized in that the motion process data packet
Include the starting point of players during the motion, horizontal displacement distance, the distance that moves vertically and run duration.
4. a kind of motion detection of panoramic picture according to claim 1, which is characterized in that the number flow camera
Quantity have 1216, and digital flow camera is placed with 360 degree of even angles.
5. the motion detection and human body recognition method of a kind of panoramic picture according to claim 1, which is characterized in that described
Mobile terminal is mobile phone terminal or computer end.
6. a kind of human body recognition method of panoramic picture, which is characterized in that include the following steps:
S1, digital flow camera is equipped on the moving line of players to adopt to the motion profile of players
Collection, and collection result is passed into image processing unit, image processing unit inquires static figure according to the information of collection result
Picture, the video image of low repeatability and the video image of high-repetition-rate, and synthesized collection result according to different repetitive rates
Panoramic picture;
S2, infrared sensor of the human body and infrared non-contact human temperature sensor measure players in the information of different location
Data, and information data is subjected to sub-frame processing according to the different of timing node, obtain node data;
S3, background model is established according to panoramic picture, panoramic picture is subjected to image branch according to the different of timing node
Separation, obtains multiple node images, human motion region is determined using the timing node difference between multiple node images, and will
In the human motion region for being filled into same time node of node data;
S4, result progress binary conversion treatment will be filled using maximum between-cluster variance thresholding method, while analyzing the effective of segmentation
Property, effective filling result is uploaded into mobile terminal or cloud, and update panoramic picture;
S5, the human body information of players in panoramic picture is compared with the human body information of pre-stored players, and
The human body information of the players of mobile terminal display identification.
7. a kind of human body recognition method of panoramic picture according to claim 6, which is characterized in that the human body infrared passes
The model LH1958, the model MLX90615SSG-DAA of infrared non-contact human temperature sensor of sensor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810562042.2A CN108921867A (en) | 2018-06-01 | 2018-06-01 | A kind of motion detection and human body recognition method of panoramic picture |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810562042.2A CN108921867A (en) | 2018-06-01 | 2018-06-01 | A kind of motion detection and human body recognition method of panoramic picture |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108921867A true CN108921867A (en) | 2018-11-30 |
Family
ID=64419520
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810562042.2A Pending CN108921867A (en) | 2018-06-01 | 2018-06-01 | A kind of motion detection and human body recognition method of panoramic picture |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108921867A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113573273A (en) * | 2021-08-02 | 2021-10-29 | 尧米(重庆)智能科技有限公司 | Wireless intelligent acquisition synchronization method and system based on Bluetooth transmission |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1756313A (en) * | 2004-09-30 | 2006-04-05 | 中国科学院计算技术研究所 | The panorama composing method of sport video |
CN101996307A (en) * | 2009-08-10 | 2011-03-30 | 上海理视微电子有限公司 | Intelligent video human body identification method |
CN104754299A (en) * | 2013-12-31 | 2015-07-01 | 玛珂***分析和开发有限公司 | Method for generating panoramic image |
CN105376500A (en) * | 2014-08-18 | 2016-03-02 | 三星电子株式会社 | Video processing apparatus for generating paranomic video and method thereof |
CN105827946A (en) * | 2015-11-26 | 2016-08-03 | 维沃移动通信有限公司 | Panoramic image generating method, panoramic image playing method and mobile terminal |
CN106331823A (en) * | 2016-08-31 | 2017-01-11 | 北京奇艺世纪科技有限公司 | Video playing method and device |
CN207166600U (en) * | 2017-01-23 | 2018-03-30 | 兹曼软件技术(北京)有限公司 | A kind of panorama camera |
-
2018
- 2018-06-01 CN CN201810562042.2A patent/CN108921867A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1756313A (en) * | 2004-09-30 | 2006-04-05 | 中国科学院计算技术研究所 | The panorama composing method of sport video |
CN101996307A (en) * | 2009-08-10 | 2011-03-30 | 上海理视微电子有限公司 | Intelligent video human body identification method |
CN104754299A (en) * | 2013-12-31 | 2015-07-01 | 玛珂***分析和开发有限公司 | Method for generating panoramic image |
CN105376500A (en) * | 2014-08-18 | 2016-03-02 | 三星电子株式会社 | Video processing apparatus for generating paranomic video and method thereof |
CN105827946A (en) * | 2015-11-26 | 2016-08-03 | 维沃移动通信有限公司 | Panoramic image generating method, panoramic image playing method and mobile terminal |
CN106331823A (en) * | 2016-08-31 | 2017-01-11 | 北京奇艺世纪科技有限公司 | Video playing method and device |
CN207166600U (en) * | 2017-01-23 | 2018-03-30 | 兹曼软件技术(北京)有限公司 | A kind of panorama camera |
Non-Patent Citations (1)
Title |
---|
Z.BILA ET AL: "RANGE AND PANORAMIC IMAGE FUSION INTO A TEXTURED RANGE IMAGE FOR CULTURE HERITAGE DOCUMENTATION", 《ISPRS ANNALS OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113573273A (en) * | 2021-08-02 | 2021-10-29 | 尧米(重庆)智能科技有限公司 | Wireless intelligent acquisition synchronization method and system based on Bluetooth transmission |
CN113573273B (en) * | 2021-08-02 | 2023-09-15 | 重庆优米工业自动化设备有限公司 | Wireless intelligent acquisition synchronization method and system based on Bluetooth transmission |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110457414B (en) | Offline map processing and virtual object display method, device, medium and equipment | |
CN105588543B (en) | A kind of method, apparatus and positioning system for realizing positioning based on camera | |
US7688381B2 (en) | System for accurately repositioning imaging devices | |
US20070076090A1 (en) | Device for generating three dimensional surface models of moving objects | |
CN108733206B (en) | Coordinate alignment method and system and virtual reality system | |
CN101033962B (en) | Measurement method for displacement of model experiment based on optics | |
CN101945284B (en) | Motion estimation device and method | |
CN104981846B (en) | For the device and method of sensing movement sphere | |
CN109982054B (en) | Projection method and device based on positioning tracking, projector and projection system | |
Wang et al. | Tracking a golf ball with high-speed stereo vision system | |
CN108416285A (en) | Rifle ball linkage surveillance method, apparatus and computer readable storage medium | |
CN103907340A (en) | Image generation device and image generation method | |
CN101950550A (en) | Display device for displaying pictures at different angles based on visual angle of viewer | |
CN107027014A (en) | A kind of intelligent optical projection system of trend and its method | |
CN103907341A (en) | Image generation device, and image generation method | |
EP0950984A3 (en) | A moving body recognition apparatus | |
CN103024281A (en) | Infrared and visible video integration system | |
CN106331471A (en) | Automatic tracking image pickup method, apparatus, mobile terminal and rotary support | |
CN108307118B (en) | Inertial navigation parameter manifold optimization-based low-delay video image stabilization method | |
CN108648147A (en) | A kind of super-resolution image acquisition method and system of human eye retina's mechanism | |
CN104115487A (en) | Image processing device, image processing method, and program | |
CN111242988A (en) | Method for tracking target by using double pan-tilt coupled by wide-angle camera and long-focus camera | |
CN108921867A (en) | A kind of motion detection and human body recognition method of panoramic picture | |
CN108900775A (en) | A kind of underwater robot realtime electronic image stabilizing method | |
JP2004338889A (en) | Image recognition 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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181130 |