CN104320570A - Embedded moving object detector - Google Patents
Embedded moving object detector Download PDFInfo
- Publication number
- CN104320570A CN104320570A CN201410389603.5A CN201410389603A CN104320570A CN 104320570 A CN104320570 A CN 104320570A CN 201410389603 A CN201410389603 A CN 201410389603A CN 104320570 A CN104320570 A CN 104320570A
- Authority
- CN
- China
- Prior art keywords
- moving object
- embedded
- pandaboard
- detector
- frame
- 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
Abstract
The invention discloses an embedded moving object detector and relates to application of a PandaBoard embedded development board for video capture and processing. The embedded moving object detector adopts the PandaBoard embedded development board and a USB (Universal Serial Bus) camera as video signal collection devices; a video frame-to-frame difference method is implemented through Simulink, and a moving object is detected on the PandaBoard through operating the method; a USB mouse and keyboard combining a mouse and a keyboard into one is taken as a detector control device; and an HDMI (High Definition Multimedia Interface) interface display is connected to the PandaBoard to display a detection result. According to the embedded moving object detector, video collection and moving object detection processes only utilize the camera and the PandaBoard embedded development, so that the embedded moving object detector can independently operate without an upper computer.
Description
Technical field
The present invention relates to a kind of object detector, be specifically related to a kind of embedded video moving object segmentation device participating in data processing without the need to host computer, belong to technical field of video processing.
Background technology
Moving object segmentation can be realized by the observation video using specific algorithm process to collect.First current most correlation technique by the camera acquisition video in video monitoring system, then transfers to host computer and specifically processes, realize moving object segmentation.Various video Processing Algorithm can be realized at host computer based on Simulink development environment and carry out moving object segmentation.But the running of the existing various Mobile object detection methods based on Simulink exploitation relies on host computer, not corresponding embedded solution, range of application is limited.
Summary of the invention
The present invention is directed at present based on the problem that the video moving object detection scheme dependence host computer of Simulink exploitation could run, a kind of embedded video object detector based on Simulink exploitation is provided.This device runs and realizes on PandaBoard embedded board.
Technical scheme of the present invention is: a kind of moving object segmentation device carrying out video acquisition and process based on PandaBoard embedded board, comprises (1) and adopts PandaBoard embedded board and USB camera as video signal acquisition device; (2) realize video frame-to-frame differences method by Simulink, and on PandaBoard, run the method moving object is detected; (3) use mouse the USB mouse key that unites two into one of keyboard as detector actuation means; (4) adopt HDMI display to be connected with PandaBoard to realize testing result and show.
Preferred version: adopt PandaBoard embedded board and USB camera as video signal acquisition device, camera is fixed, and background is static relative to camera, and examined object is relative to cam movement.
Preferred version: the picture format of camera collection is YCbCr4:2:2, detector is only to illuminance information Y process wherein.
Preferred version: frame-to-frame differences method need not store previous frame image, Postponement module need only be adopted, namely after the output signal of camera module, add a branch, video signal delay one frame exports by this branch, then the signal after delay and original signal are delivered to subtraction module simultaneously.
Preferred version: the moving object segmentation algorithm based on frame-to-frame differences method is designed in host computer platform by Simulink, then download on PandaBoard embedded board and run, realize the function of moving object segmentation, this detector can depart from host computer independent operating.
Preferred version: after detector and host computer depart from, opens a terminal with USB mouse key in embedded Ubuntu system, and input command starts or closes detector.
Preferred version: in the result shown by display, background is shown as black, moving object especially its edge is shown as white.
Accompanying drawing explanation
Accompanying drawing is a kind of structure chart of embedded moving object segmentation device.
Embodiment
Below in conjunction with accompanying drawing and example, the invention will be further described:
As shown in the figure, a kind of moving object segmentation device carrying out video acquisition and process based on PandaBoard embedded board of the present embodiment comprises and adopts PandaBoard embedded board 2 and USB camera 1 as video signal acquisition device; Realize video frame-to-frame differences method by Simulink3, and on PandaBoard2, run the method moving object is detected; Use mouse the USB mouse key 4 that unites two into one of keyboard as detector 6 actuation means; Adopt HDMI display 5 to be connected with PandaBoard2 to realize testing result and show.
Further illustrate: adopt PandaBoard embedded board 2 and USB camera 1 as video signal acquisition device, camera is fixed, and background is static relative to camera, the relative cam movement of examined object.
Further illustrate: the picture format that camera 1 gathers is YCbCr4:2:2, and detector 6 is only to illuminance information Y process wherein.
Further illustrate: frame-to-frame differences method need not store previous frame image, Postponement module need only be adopted, namely after the output signal of camera module, add a branch, video signal delay one frame exports by this branch, then the signal after delay and original signal are delivered to subtraction module simultaneously.
Further illustrate: the moving object segmentation algorithm based on frame-to-frame differences method is designed on host computer 3 platform by Simulink, then download on PandaBoard embedded board 2 and run, realize the function of moving object segmentation, this detector 6 can depart from host computer 3 independent operating.
Further illustrate: after detector 6 and host computer 3 depart from, open a terminal with USB mouse key 4 in embedded Ubuntu system, input command starts or closes detector.
Further illustrate: in the result shown by display 5, background is shown as black, moving object especially its edge is shown as white.
Claims (7)
1. an embedded moving object segmentation device, is characterized in that:
(1) adopt PandaBoard embedded board and USB camera as video signal acquisition device;
(2) realize video frame-to-frame differences method by Simulink, and on PandaBoard, run the method moving object is detected;
(3) use mouse the USB mouse key that unites two into one of keyboard as detector actuation means;
(4) adopt HDMI display to be connected with PandaBoard to realize testing result and show.
2. the embedded moving object segmentation device of one according to claim 1, is characterized in that: in (1), camera is fixed, and background is static relative to camera, and examined object is relative to cam movement.
3. the embedded moving object segmentation device of one according to claim 1, is characterized in that: in (1), and the picture format of camera collection is YCbCr4:2:2, and detector is only to illuminance information Y process wherein.
4. the embedded moving object segmentation device of one according to claim 1, it is characterized in that: in (2), frame-to-frame differences method need not store previous frame image, Postponement module need only be adopted, namely after the output signal of camera module, a branch is added, video signal delay one frame exports by this branch, then the signal after delay and original signal is delivered to subtraction module simultaneously.
5. the embedded moving object segmentation device of one according to claim 1, it is characterized in that: in (2), moving object segmentation algorithm based on frame-to-frame differences method is designed in host computer platform by Simulink, then download on PandaBoard embedded board and run, realize the function of moving object segmentation, this detector can depart from host computer independent operating.
6. the embedded moving object segmentation device of one according to claim 1, it is characterized in that: in (3), after detector and host computer depart from, open a terminal with USB mouse key in embedded Ubuntu system, input command starts or closes detector.
7. the embedded moving object segmentation device of one according to claim 1, it is characterized in that: in (4), in the result shown by display, background is shown as black, and moving object especially its edge is shown as white.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410389603.5A CN104320570A (en) | 2014-08-10 | 2014-08-10 | Embedded moving object detector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410389603.5A CN104320570A (en) | 2014-08-10 | 2014-08-10 | Embedded moving object detector |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104320570A true CN104320570A (en) | 2015-01-28 |
Family
ID=52375734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410389603.5A Pending CN104320570A (en) | 2014-08-10 | 2014-08-10 | Embedded moving object detector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104320570A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101159859A (en) * | 2007-11-29 | 2008-04-09 | 北京中星微电子有限公司 | Motion detection method, device and an intelligent monitoring system |
| CN101404760A (en) * | 2008-10-28 | 2009-04-08 | 大连理工大学 | Self-perception portable image wireless monitoring equipment and use method thereof |
-
2014
- 2014-08-10 CN CN201410389603.5A patent/CN104320570A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101159859A (en) * | 2007-11-29 | 2008-04-09 | 北京中星微电子有限公司 | Motion detection method, device and an intelligent monitoring system |
| CN101404760A (en) * | 2008-10-28 | 2009-04-08 | 大连理工大学 | Self-perception portable image wireless monitoring equipment and use method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 傅松寅: "基于嵌入式的视频监控前端智能化相关技术的研究及实现", 《中国优秀硕士学位论文全文数据库，信息科技辑》, no. 07, 15 July 2011 (2011-07-15) * |
| 汤武当: "基于FPGA的运动物体检测系统设计", 《中国优秀硕士学位论文全文数据库，信息科技辑》, no. 03, 15 March 2011 (2011-03-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| NZ761040A (en) | A refuse collection system | |
| WO2011119337A3 (en) | System and method for data capture, storage, and retrieval | |
| CN102662498A (en) | Wireless control method and system for projection demonstration | |
| CN111753701B (en) | Method, device, equipment and readable storage medium for detecting violation of application program | |
| CN104049861B (en) | The method of electronic device and the operation electronic device | |
| CN111640112B (en) | Image detection method, system, platform, device, medium, and image processing apparatus | |
| GB2473168A (en) | System and method for remote control of a computer | |
| Mankani et al. | Real-time implementation of object detection and tracking on DSP for video surveillance applications | |
| CN105320270A (en) | Method for performing a face tracking function and an electric device having the same | |
| CN105323484A (en) | Rapidly photographing method and electronic device | |
| JP2010166288A5 (en) | ||
| US11348254B2 (en) | Visual search method, computer device, and storage medium | |
| CN111191556A (en) | Face recognition method and device and electronic equipment | |
| US20150002275A1 (en) | Methods, apparatuses, and computer program products for data transfer between wireless memory tags | |
| WO2013188442A3 (en) | Photographic stage | |
| US10083720B2 (en) | Method and system for video data stream storage | |
| CN104320570A (en) | Embedded moving object detector | |
| CN104702833A (en) | Information processing method and electronic equipment | |
| KR20100118317A (en) | Gesture recognition method using portable terminal with camera by camera movement tracking and thereof system | |
| CN202548758U (en) | Interactive projection system | |
| WO2018165148A1 (en) | Foreground object detection | |
| US11181923B2 (en) | Detection system, detection method, and program | |
| CN114359160A (en) | Screen detection method and device, electronic equipment and storage medium | |
| US20150006667A1 (en) | Dynamic data compression system | |
| JP2023500667A (en) | Method and apparatus for image frame freeze detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150128 |