CN103179401A - Processing method and device for multi-agent cooperative video capturing and image stitching - Google Patents
Processing method and device for multi-agent cooperative video capturing and image stitching Download PDFInfo
- Publication number
- CN103179401A CN103179401A CN2013100870452A CN201310087045A CN103179401A CN 103179401 A CN103179401 A CN 103179401A CN 2013100870452 A CN2013100870452 A CN 2013100870452A CN 201310087045 A CN201310087045 A CN 201310087045A CN 103179401 A CN103179401 A CN 103179401A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- video acquisition
- intelligent body
- information
- 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
Images
Abstract
The invention discloses processing method and device for multi-agent cooperative video capturing and image stitching. The device comprises a monocular agent video capturing module, a DSP (digital signal processing) image processing unit module, a WIFI (wireless fidelity) communication module and an upper computer image-stitching module. The agent video capturing module acquires images of the surrounding in real time through an embedded camera of a mobile agent. The images acquired by the camera are subjected to JPEG (joint photographic experts group) compressed encoding by a DSP image processing unit on a monocular agent, and then the compressed image data are transmitted to an upper computer through the WIFI communication module. The upper computer uses a VC-prepared (visual C-prepared) control software interface, the image data are decoded by the image-stitching module, multiple images are stitched by an image processing algorithm, the redundant images are detected, and unknown environmental information is extracted. Software includes the image-stitching module.
Description
Technical field
The present invention relates to multiple agent application in robot cooperated system, relate to specifically the collaborative video acquisition of a kind of multiple agent and image information splicing processing method and device.
Background technology
At present, along with the development of Robotics makes the machine Man's Power improve constantly, the field of robot application and scope be constantly expansion also.On the one hand, people wish that robot can complete more complicated task under the environment of many danger, and these complicated tasks are difficult to complete by single robot, need the mutual coordination and cooperation of multirobot jointly to complete.In the Multi agent Robot Cooperative system, each robot is to according to system's general assignment target. planning motion sequence separately dynamically, rather than planned by the centralized planning device.Each robot can give full play to its intelligence and independent behaviour cooperates with other robot.
The intelligent characteristic of intelligent body just is that it has the work function of mutually coordinating with the external world.In this respect, visual performance, Proximity function, feeling function have significant role, and the visual performance of intelligent body is considered to the important perceptibility of intelligent body.The vision system of intelligent body as people's eyes, is important " organ " of robot perception local environment, and simultaneously the environmental information of perception realizes collection and judgement to ambient condition information according to this.When obtaining the information of many hazardous environments, will put into the intelligent body of vision system and carry out information gathering in environment.But because the camera angle of visual field of single intelligent body is limited, easily cause information dropout, and information gathering efficient is lower.For above-mentioned situation, use a plurality of monocular intelligent bodies to work in coordination with and carry out information gathering, in real time image information is sent to host computer by WiFi after encoding.In order to reduce the redundancy of image information, host computer integrates by merging algorithm for images the image information that each intelligent body transmits, and therefrom obtains useful data message.
Through the retrieval of existing document is learnt, Chinese patent application number is: 200910084926.2, name is called: a kind of multi-agent visual servo-coordination control method, this patent application has proposed a kind of by visual information controlled motion body or motion position and the attitude with respect to object or a target signature collection, completes the method for the tasks such as target monitoring, tracking.Chinese patent application number is: 02156202.4, and name is called: intelligent monitoring device for four-picture image acquisition method, the method have been described intelligent collector and have been received the instruction that microcomputer sends, and complete IMAQ, preserve transmission, judgement, alarm lamp function.But this method all lays particular emphasis on intelligent acquisition, the processing of image, do not consider image compression encoding, improve the transmission rate of image, do not consider the redundancy of view data yet, not to technical finesses such as the picture that gathers splice, with the minimizing image redundancy, thereby improve the speed of information extraction.
Summary of the invention
The object of the present invention is to provide the collaborative video acquisition of a kind of multiple agent and image information splicing processing method, collaborative video acquisition by a plurality of monocular intelligent bodies, the efficient image information of intactly obtaining surrounding environment, and send image information to host computer in real time, host computer gets the data message of complete circumstances not known by merging algorithm for images, can effectively reduce the injury that circumstances not known brings, realize obtaining accurately and efficiently the video image information under unknown hazardous environment.
The present invention is by technology such as video acquisition, image compression, radio communication, Image Mosaics, utilize vision system and the vision processor Real-time Collection ambient condition information of a plurality of monocular intelligent bodies, compression coded image is transferred to host computer by WiFi and carries out many Image Mosaics and information extraction.
To achieve these goals, the invention provides the collaborative video acquisition of a kind of multiple agent and image information splicing processing unit, it is achieved through the following technical solutions:
The collaborative video acquisition of a kind of multiple agent and image information splicing processing unit comprise monocular intelligent body video acquisition module, DSP image processor block, WiFi communication module and host computer Image Mosaics processing module; Monocular intelligent body video acquisition module is obtained the image information of surrounding environment in real time by the embedded camera on intelligent mobile agent, DSP image processor on intelligent mobile agent carries out the JPEG compressed encoding with the image that camera obtains, then the image data transmission after compressing by the WiFi communication module is to host computer Image Mosaics processing module, host computer Image Mosaics processing module is decode image data at first, use image processing algorithm to carry out the multiple image splicing after decoding, complete the extraction to circumstances not known information.
Described monocular intelligent body video acquisition module, comprise one with the intelligent body dolly of embedded camera and WiFi communication function, use the dsp processor of an ADI blackfin series as the nucleus module of intelligent body dolly, complete the functions such as intelligent body dolly video acquisition and image processing.
Described DSP image processor block has write the code with the JPEG compression coded image of host computer same-code form in processor, the image information that the collection of intelligent body dolly comes is compressed.
Described WiFi communication module with the image transmission after compressed encoding to host computer in, host computer is controlled the intelligent body dolly by this module sending controling instruction.
Described host computer Image Mosaics processing module, use VC to write one and control software interface, software application the multithreading in VC be used for receiving the view data that the different intelligent body transmits, software has also embedded the OpenCV function library simultaneously in conjunction with the SIFT merging algorithm for images, completes the splicing of multiple image.
Another program of the present invention is to provide the collaborative video acquisition of a kind of multiple agent and image information splicing processing method, and its content comprises the following steps:
The first step: each monocular intelligent body gathers the surrounding environment video information by embedded camera, by dsp processor, image information is carried out compressed encoding;
Second step: view data is sent to the PC control software interface by the WiFi module;
The 3rd step: after PC control software is received view data, at first carry out the decoding of data, then picture is kept under the path of appointment, added image in the OpenCV function library of SIFT merging algorithm for images to process function by use several pictures have been spliced processing, remove the pictorial information of redundancy, complete the extraction of effective information, can also use OpenCV by spliced picture is carried out rim detection, the Camshift target following, the processing such as people's face detection.
Owing to adopting technique scheme, compared with prior art, the invention has the beneficial effects as follows: the intelligent and ability to cooperate that takes full advantage of multi-agent system, efficient complete collection the image information of unknown hazardous environment, by being spliced, processes multiple image, reduce the redundancy of multiimage, improved the efficient that the ambient image data are extracted.
Description of drawings
Fig. 1 is that the system of the collaborative video acquisition of a kind of multiple agent of the present invention and image information splicing processing unit embodiment forms block diagram;
Fig. 2 is the flow chart of the collaborative video acquisition of a kind of multiple agent of the present invention and image information splicing processing method.
Embodiment
Below in conjunction with accompanying drawing and embodiment, the present invention is described in further detail:
The present embodiment is implemented under take technical solution of the present invention as prerequisite, provided detailed implementation method and concrete operating process, but protection scope of the present invention is not limited to following example.
as shown in Figure 1, the collaborative video acquisition of a kind of multiple agent and image information processing device, it comprises: a plurality of monocular intelligent body video acquisition module 1, 2, 3, it is the CMOS camera of OV9650 that model is installed on each intelligent body, corresponding to the DSP image processor block 4 on each monocular intelligent body, 5, 6, it is the dsp processor of ADI BF537 that processor module adopts model, WiFi communication module 7, host computer Image Mosaics processing module 8, wherein: a plurality of monocular intelligent body video acquisition module 1, 2, 3 by the collaborative surrounding environment breath that gathers of the embedded camera of self, pass through afterwards DSP image processor 4 separately, 5, 6 carry out compressed encoding with the pictorial information that collects, image compression adopts the compression method of JPEG, data after encoding by WiFi communication module 7 send to the host computer Image Mosaics and process, module 8 will be completed the splicing of multiple image and the extraction of important image information after the image information decompress(ion).
the collaborative video acquisition of a kind of multiple agent and image information splicing processing method, as shown in Figure 2, at first in flow process 1, a plurality of monocular intelligent bodies gather the information of surrounding environment simultaneously by embedded camera, integrality for guarantee information, a plurality of intelligent bodies can adopt yi word pattern formation side by side to complete the collection of information, use the compression method of JPEG to compress the environmental information that collects by the dsp processor module in flow process 2 afterwards, the compression after in flow process 3 by wireless WIFI with image transmission to the host computer in flow process 4, after host computer receives image information, obtain original image by the jpeg decompression compression algorithm, the availability of judgement view data, thereby judge whether to preserve image, use merging algorithm for images that place identical in image information is removed if need to preserve, image after processing is at last preserved by flow process 6.How to return from newly gathering new environmental information by flow process 1 if mustn't preserve.
Claims (6)
1. a multiple agent is worked in coordination with video acquisition and image information splicing processing unit, and it is characterized in that: it comprises monocular intelligent body video acquisition module, DSP image processor block, WiFi communication module, host computer Image Mosaics processing module; Monocular intelligent body video acquisition module is obtained the image information of surrounding environment in real time by the embedded camera on intelligent mobile agent, DSP image processor on intelligent mobile agent carries out the JPEG compressed encoding with the image that camera obtains, then the image data transmission after compressing by the WiFi communication module is to host computer Image Mosaics processing module, host computer Image Mosaics processing module is decode image data at first, use image processing algorithm to carry out the multiple image splicing after decoding, complete the extraction to circumstances not known information.
2. the collaborative video acquisition of a kind of multiple agent according to claim 1 and image information are spliced processing unit, it is characterized in that: described monocular intelligent body video acquisition module, comprise one with the intelligent body dolly of embedded camera and WiFi communication function, use the dsp processor of an ADI blackfin series as the nucleus module of intelligent body dolly, complete the functions such as intelligent body dolly video acquisition and image processing.
3. the collaborative video acquisition of a kind of multiple agent according to claim 1 and image information are spliced processing unit, it is characterized in that: described DSP image processor block, write the code with the JPEG compression coded image of host computer same-code form in processor, the image information that the collection of intelligent body dolly comes has been compressed.
4. the collaborative video acquisition of a kind of multiple agent according to claim 1 and image information are spliced processing unit, it is characterized in that: described WiFi communication module with the image transmission after compressed encoding to host computer in, host computer is controlled the intelligent body dolly by this module sending controling instruction.
5. the collaborative video acquisition of a kind of multiple agent according to claim 1 and image information are spliced processing unit, it is characterized in that: described host computer Image Mosaics processing module, use VC to write one and control software interface, software application the multithreading in VC be used for receiving the view data that the different intelligent body transmits, software has also embedded the OpenCV function library simultaneously in conjunction with the SIFT merging algorithm for images, completes the splicing of multiple image.
6. a multiple agent is worked in coordination with video acquisition and image information splicing processing method, and it is characterized in that: its content comprises the following steps:
The first step: each monocular intelligent body gathers the surrounding environment video information by embedded camera, by dsp processor, image information is carried out compressed encoding;
Second step: view data is sent to the PC control software interface by the WiFi module;
The 3rd step: after PC control software is received view data, at first carry out the decoding of data, then picture is kept under the path of appointment, added image in the OpenCV function library of SIFT merging algorithm for images to process function by use several pictures have been spliced processing, remove the pictorial information of redundancy, complete the extraction of effective information, can also use OpenCV by spliced picture is carried out rim detection, the Camshift target following, the processing such as people's face detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100870452A CN103179401A (en) | 2013-03-19 | 2013-03-19 | Processing method and device for multi-agent cooperative video capturing and image stitching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100870452A CN103179401A (en) | 2013-03-19 | 2013-03-19 | Processing method and device for multi-agent cooperative video capturing and image stitching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103179401A true CN103179401A (en) | 2013-06-26 |
Family
ID=48638982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013100870452A Pending CN103179401A (en) | 2013-03-19 | 2013-03-19 | Processing method and device for multi-agent cooperative video capturing and image stitching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103179401A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036477A (en) * | 2014-06-06 | 2014-09-10 | 上海大学 | Large-view-field image splicing device and method based on two biomimetic eyes |
| CN104243851A (en) * | 2014-09-28 | 2014-12-24 | 联想(北京)有限公司 | Image generation method and electronic device |
| CN104535047A (en) * | 2014-09-19 | 2015-04-22 | 燕山大学 | Multi-agent target tracking global positioning system and method based on video stitching |
| CN105389829A (en) * | 2015-10-15 | 2016-03-09 | 上海交通大学 | Low-complexity dynamic object detecting and tracking method based on embedded processor |
| WO2017012396A1 (en) * | 2015-07-21 | 2017-01-26 | 杭州海康威视数字技术股份有限公司 | Camera and integrated circuit board |
| CN106569831A (en) * | 2016-11-10 | 2017-04-19 | 上海电机学院 | Method of realizing multiple light stream algorithm on single interface |
| CN108564057A (en) * | 2018-04-25 | 2018-09-21 | 浙江传媒学院 | Method for establishing human similarity system based on opencv |
| CN110099237A (en) * | 2018-01-31 | 2019-08-06 | 腾讯科技（深圳）有限公司 | Image processing method, electronic device and computer readable storage medium |
| CN110825088A (en) * | 2019-11-29 | 2020-02-21 | 燕山大学 | Multi-view vision guiding ship body cleaning robot system and cleaning method |
| CN111510717A (en) * | 2019-01-31 | 2020-08-07 | 杭州海康威视数字技术股份有限公司 | Image splicing method and device |
| CN111654676A (en) * | 2020-06-10 | 2020-09-11 | 上海趣人文化传播有限公司 | Cooperative shooting system and shooting method thereof |
| CN112689125A (en) * | 2020-12-18 | 2021-04-20 | 中标慧安信息技术股份有限公司 | Multi-terminal safety monitoring method and system based on Internet of things |
| CN113301239A (en) * | 2021-07-27 | 2021-08-24 | 康达洲际医疗器械有限公司 | Imaging system group control method and system based on function sharing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1780359A (en) * | 2004-11-18 | 2006-05-31 | 北京大学 | CMOS imaging and information processing system for unmanned apparatus remote platform |
| CN101056404A (en) * | 2007-04-26 | 2007-10-17 | 广东威创日新电子有限公司 | Multi-block parallel compression video data device based on the MCU and its compression method |
| CN101588480A (en) * | 2009-05-27 | 2009-11-25 | 北京航空航天大学 | Multi-agent visual servo-coordination control method |
| CN101751121A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | OCR-based wireless scanning input device and method |
| CN101794349A (en) * | 2010-02-09 | 2010-08-04 | 北京邮电大学 | Experimental system and method for augmented reality of teleoperation of robot |
| CN102170550A (en) * | 2011-03-04 | 2011-08-31 | 哈尔滨工业大学 | Method and device of image mosaic imaging in background of wide field of view |
| CN102915465A (en) * | 2012-10-24 | 2013-02-06 | 河海大学常州校区 | Multi-robot combined team-organizing method based on mobile biostimulation nerve network |
-
2013
- 2013-03-19 CN CN2013100870452A patent/CN103179401A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1780359A (en) * | 2004-11-18 | 2006-05-31 | 北京大学 | CMOS imaging and information processing system for unmanned apparatus remote platform |
| CN101056404A (en) * | 2007-04-26 | 2007-10-17 | 广东威创日新电子有限公司 | Multi-block parallel compression video data device based on the MCU and its compression method |
| CN101751121A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | OCR-based wireless scanning input device and method |
| CN101588480A (en) * | 2009-05-27 | 2009-11-25 | 北京航空航天大学 | Multi-agent visual servo-coordination control method |
| CN101794349A (en) * | 2010-02-09 | 2010-08-04 | 北京邮电大学 | Experimental system and method for augmented reality of teleoperation of robot |
| CN102170550A (en) * | 2011-03-04 | 2011-08-31 | 哈尔滨工业大学 | Method and device of image mosaic imaging in background of wide field of view |
| CN102915465A (en) * | 2012-10-24 | 2013-02-06 | 河海大学常州校区 | Multi-robot combined team-organizing method based on mobile biostimulation nerve network |
Non-Patent Citations (1)
| Title |
|---|
| XUN S. ZHOU ET AL: "Multi-robot SLAM with Unknown Initial Correspondence: The Robot Rendezvous Case", 《INTELLIGENT ROBOTS AND SYSTEMS》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036477A (en) * | 2014-06-06 | 2014-09-10 | 上海大学 | Large-view-field image splicing device and method based on two biomimetic eyes |
| CN104535047A (en) * | 2014-09-19 | 2015-04-22 | 燕山大学 | Multi-agent target tracking global positioning system and method based on video stitching |
| CN104243851A (en) * | 2014-09-28 | 2014-12-24 | 联想(北京)有限公司 | Image generation method and electronic device |
| US10602060B2 (en) | 2015-07-21 | 2020-03-24 | Hangzhou Hikvision Digital Technology Co., Ltd. | Camera and integrated circuit board |
| WO2017012396A1 (en) * | 2015-07-21 | 2017-01-26 | 杭州海康威视数字技术股份有限公司 | Camera and integrated circuit board |
| CN105389829A (en) * | 2015-10-15 | 2016-03-09 | 上海交通大学 | Low-complexity dynamic object detecting and tracking method based on embedded processor |
| CN106569831A (en) * | 2016-11-10 | 2017-04-19 | 上海电机学院 | Method of realizing multiple light stream algorithm on single interface |
| CN110099237A (en) * | 2018-01-31 | 2019-08-06 | 腾讯科技（深圳）有限公司 | Image processing method, electronic device and computer readable storage medium |
| CN110099237B (en) * | 2018-01-31 | 2021-08-17 | 腾讯科技（深圳）有限公司 | Image processing method, electronic device, and computer-readable storage medium |
| CN108564057A (en) * | 2018-04-25 | 2018-09-21 | 浙江传媒学院 | Method for establishing human similarity system based on opencv |
| CN108564057B (en) * | 2018-04-25 | 2022-05-13 | 浙江传媒学院 | Method for establishing person similarity system based on opencv |
| CN111510717A (en) * | 2019-01-31 | 2020-08-07 | 杭州海康威视数字技术股份有限公司 | Image splicing method and device |
| CN111510717B (en) * | 2019-01-31 | 2022-04-26 | 杭州海康威视数字技术股份有限公司 | Image splicing method and device |
| CN110825088A (en) * | 2019-11-29 | 2020-02-21 | 燕山大学 | Multi-view vision guiding ship body cleaning robot system and cleaning method |
| CN110825088B (en) * | 2019-11-29 | 2021-10-01 | 燕山大学 | Multi-view vision guiding ship body cleaning robot system and cleaning method |
| CN111654676B (en) * | 2020-06-10 | 2021-11-19 | 上海趣人文化传播有限公司 | Cooperative shooting system and shooting method thereof |
| CN111654676A (en) * | 2020-06-10 | 2020-09-11 | 上海趣人文化传播有限公司 | Cooperative shooting system and shooting method thereof |
| CN112689125A (en) * | 2020-12-18 | 2021-04-20 | 中标慧安信息技术股份有限公司 | Multi-terminal safety monitoring method and system based on Internet of things |
| CN113301239A (en) * | 2021-07-27 | 2021-08-24 | 康达洲际医疗器械有限公司 | Imaging system group control method and system based on function sharing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103179401A (en) | Processing method and device for multi-agent cooperative video capturing and image stitching | |
| US9928605B2 (en) | Real-time cascaded object recognition | |
| WO2018150083A1 (en) | A method and technical equipment for video processing | |
| US20210200190A1 (en) | Action imitation method and robot and computer readable storage medium using the same | |
| CN102663375B (en) | Active target identification method based on digital watermark technology in H.264 | |
| CN111259748A (en) | Edge calculation and communication system for video monitoring | |
| JP7448679B2 (en) | Image processing method and device | |
| CN107332977B (en) | Augmented reality method and augmented reality equipment | |
| Fawzi et al. | Embedded real-time video surveillance system based on multi-sensor and visual tracking | |
| CN113312966B (en) | Action recognition method and device based on first person viewing angle | |
| CN104853150A (en) | Multi-camera objective cooperatively tracking technology | |
| CN103475877A (en) | Video transmission method and system | |
| CN106293078A (en) | Virtual reality exchange method based on photographic head and device | |
| CN113630609B (en) | Video encoding method, decoding method, storage medium and terminal equipment | |
| CN103037206A (en) | Method and system of video transmission | |
| CN113761965B (en) | Motion capture method, motion capture device, electronic equipment and storage medium | |
| CN116152906A (en) | Image recognition method, device, communication equipment and readable storage medium | |
| CN104763471B (en) | Emergency communication device by projected virtual operation screen and emergency communication method | |
| CN112650596B (en) | Cross-process sharing method, device and equipment for target data and storage medium | |
| WO2020107376A1 (en) | Image processing method, device, and storage medium | |
| CN112434575B (en) | Gesture recognition-based remote control method and system for electric power Internet of things equipment | |
| CN205120683U (en) | Air pollution intelligent monitoring cloud platform | |
| CN205356555U (en) | Air pollution intelligence surveillance camera machine | |
| CN205068122U (en) | Water pollution intelligent monitoring system | |
| CN105120213A (en) | Noise pollution intelligent monitoring system |
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 |
Application publication date: 20130626 |
|
| RJ01 | Rejection of invention patent application after publication |