CN103200394A - Target image real time transmission and tracking method based on digital signal processor (DSP) and target image real time transmission and tracking device based on digital signal processor (DSP) - Google Patents
Target image real time transmission and tracking method based on digital signal processor (DSP) and target image real time transmission and tracking device based on digital signal processor (DSP) Download PDFInfo
- Publication number
- CN103200394A CN103200394A CN2013101174190A CN201310117419A CN103200394A CN 103200394 A CN103200394 A CN 103200394A CN 2013101174190 A CN2013101174190 A CN 2013101174190A CN 201310117419 A CN201310117419 A CN 201310117419A CN 103200394 A CN103200394 A CN 103200394A
- Authority
- CN
- China
- Prior art keywords
- target
- tracking
- image
- dsp
- signal
- 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.)
- Granted
Links
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
本发明公开了一种基于DSP的目标图像实时传输与跟踪方法及其装置。本发明图像跟踪部分的方法采用连通域算法和模板匹配算法结合的方式，用连通域算法获得要跟踪的目标，建立目标对象的图像模板，用模板匹配法对目标进行跟踪；结合用最小二乘法预测的目标运动轨迹，在波门内搜索目标；如果模板匹配法跟踪失败，则用连通域算法重新捕获目标，重新建立图像模板，继续跟踪，直到跟踪结束。本发明的装置包括图像处理单元、瞄具、随动系统、交换机、远程终端和综合管理PC。本发明能够实现对运动目标的跟踪，并将跟踪过程传输到以太网，网络上的可以远程监控目标跟踪过程，综合管理计算机还可以改变要跟踪的目标以及切换跟踪方式。
The invention discloses a method and device for real-time transmission and tracking of target images based on DSP. The method of the image tracking part of the present invention adopts the combination of the connected domain algorithm and the template matching algorithm, obtains the target to be tracked with the connected domain algorithm, sets up the image template of the target object, and uses the template matching method to track the target; combined with the least squares method According to the predicted trajectory of the target, the target is searched in the wave gate; if the template matching method fails to track, the connected domain algorithm is used to recapture the target, re-establish the image template, and continue to track until the end of the track. The device of the invention includes an image processing unit, a sight, a follow-up system, a switch, a remote terminal and a comprehensive management PC. The invention can realize the tracking of the moving target, and transmit the tracking process to the Ethernet, the target tracking process can be remotely monitored on the network, and the comprehensive management computer can also change the target to be tracked and switch the tracking mode.
Description
Technical field
The invention belongs to a kind of image handles and image transmission technology, particularly a kind of target image real-time Transmission and tracking and device thereof based on DSP.
Background technology
General image tracking system is to be imaging sensor with the camera, produces a kind of photoelectronic tracking device of tracking error signal with the image tracker.Image tracking system mainly is made up of four parts such as camera, image tracker, servo system and monitor.Camera is the key component of image tracking system, is used for absorbing the scenery image of (comprising target), and optical imagery is converted to the vision signal that meets television system, generally uses CCD camera, infrared thermoviewer, laser camera etc.The image tracker is the core of entire image tracking system, its major function is that the image that collects is handled, and comprises the preliminary treatment of image, the identification of image (image is cut apart, target recognition and tracking), the processing of output image signal synchronously (stack of ripple door, tracking mark arrange etc.).The image tracking cell provides the tracing deviation value on target bearing and the pitch position, with this servo system that drives the back to the real-time tracking of realization of goal.Servo system is the enforcement parts of following the tracks of, and mainly comprises orientation, pitching, roll three-axle steady platform and phase control unit.Monitor is used for display system to the Video signal processing result.
Image tracking system is to realize by the image of following the tracks of intended target to the tracking of target, yet because factors such as the complexity of the motion of target, background and intensity variations make tracking often can not carry out under desirable condition.At the influence of some objective factors to target following, people have designed multiple track algorithm.Some common algorithms have: methods such as connected domain algorithm, edge tracking, peak time tracking and template matching algorithm.Using in image tracking system at present is connected domain algorithm and template matching algorithm more widely.
Prior art systems generally can only be selected tracking target automatically, can't manually select tracking target; Single connected domain algorithm or the template matching algorithm of general employing merges two algorithms; System does not generally have the Ethernet transfer function.
Summary of the invention
The object of the present invention is to provide a kind of visible images that can utilize that moving target is followed the tracks of, and tracking image can be transmitted by Ethernet, and the computer on the network can be monitored tracing process, and the integrated management computer can also change the target that will follow the tracks of and target image real-time Transmission and tracking and the device thereof based on DSP that switches tracking mode.
The technical solution that realizes the object of the invention is:
A kind of target image real-time Transmission and tracking based on DSP may further comprise the steps:
Step 1: video monitoring signal is connected to the video inputs of graphics processing unit by the output of video camera, finishes the input of vision signal, and the signal of input is the video standard signal of Phase Alternation Line system or TSC-system;
Step 2: the vision signal through the graphics processing unit video inputs is converted into data image signal by Video Decoder, and the Phase Alternation Line system or the TSC-system vision signal that are about to standard are converted to digital difference signal, and its output format is ITU-R BT.656;
Step 3: carry out carrying out image threshold segmentation and binaryzation, target and background is separated, namely adopt maximum variance between clusters to choose the threshold value that image is cut apart automatically according to the luminance signal in every frame of digital color difference signal, brightness value is set to 255 greater than the brightness of the pixel of threshold value, is set to 0 less than the brightness of the pixel of threshold value;
Step 4: utilize the connected domain algorithm, the target in the binary image is divided into a plurality of zones, extract the target that to follow the tracks of according to the criterion of the setting in the algorithm;
Step 5: the To Template of setting up images match with the luminance signal of tracked target, at the Bo Mennei ferret out, calculate the similarity when front template and To Template, with the position of the highest point of similarity as tracked target, if highest similarity is greater than the value of setting, then carry out template renewal, be about to the highest template of similarity as To Template;
Step 6: according to the track of target travel, utilize the position that a bit may occur under the least square method target of prediction, centered by this point, and with fixing ripple door size, the search gate of next frame is set, and send the cradle head control order by serial ports, make The Cloud Terrace move under the target position of a bit;
Step 7: if do not search target at the Bo Mennei of present frame, then in next frame, expand and be twice ripple door size and come ferret out, if next frame does not also search target, then from following frame, adopt the search of connected domain algorithm full screen scanning, up to regaining target;
Step 8: treated image by the Fast Ethernet physical layer, is adopted H.264 standard code compression, transmit the computer decoding vision signal on the network, remote monitoring target following process with the UDP host-host protocol at Ethernet;
Step 9: the integrated management computer sends related command by Ethernet to graphics processing unit, and the target that change will be followed the tracks of and switching tracking mode namely adopt from motion tracking and still manually follow the tracks of.
A kind of target image real-time Transmission and tracking means based on DSP, comprise graphics processing unit, take aim at tool, hunting gear, switch, remote terminal and integrated management PC, wherein, graphics processing unit is respectively with switch, hunting gear with take aim at tool and be connected, switch also is connected with remote terminal with integrated management PC, takes aim at tool and also is connected with hunting gear; Take aim at the visible light vision signal that the camera handle in the tool is gathered, pass to graphics processing unit by the AV video transmission line, graphics processing unit carries out target image and follows the tracks of processing, extract target information, control command is sent to hunting gear by serial ports, hunting gear control is taken aim at tool and is rotated the pursuit movement target, and the processed video image is transferred to switch, switch carries out remote transmission, and the remote terminal on the Ethernet and integrated management PC can monitor tracing process behind the decoded video signal.
The present invention compared with prior art, its remarkable advantage is:
(1) system of the present invention can select tracking target automatically, also can change the target that will follow the tracks of by the integrated management computer;
(2) tracking mode of the present invention can freely changed automatically or manually by the integrated management computer;
(3) system of the present invention adopts the mode that connected domain algorithm and template matching algorithm combine, and realizes the tracking to moving target.With respect to single connected domain algorithm or template matching algorithm, the mode of both combinations can effectively improve the success rate of tracking;
(4) there is Ethernet real-time Transmission function in system of the present invention, can allow real-time monitoring of computer target following process on the network, has novelty and practicality.
Below in conjunction with accompanying drawing the present invention is described in further detail.
Description of drawings
Fig. 1 the present invention is based on the target image real-time Transmission of DSP and the structural representation of tracking means.
Fig. 2 is the composition schematic diagram that the present invention is based on the graphics processing unit of the target image real-time Transmission of DSP and tracking means.
Fig. 3 the present invention is based on the target image real-time Transmission of DSP and the flow chart of tracking.
Embodiment
Referring to Fig. 1, the present invention a kind of target image real-time Transmission and tracking and device thereof based on DSP, its device comprises graphics processing unit, takes aim at tool, hunting gear, switch, remote terminal and integrated management PC, wherein, graphics processing unit is respectively with switch, hunting gear with take aim at tool and be connected, switch also is connected with remote terminal with integrated management PC, takes aim at tool and also is connected with hunting gear; Take aim at the visible light vision signal that the camera handle in the tool is gathered, pass to graphics processing unit by the AV video transmission line, graphics processing unit carries out target image and follows the tracks of processing, extract target information, control command is sent to hunting gear by serial ports, hunting gear control is taken aim at tool and is rotated the pursuit movement target, and the processed video image is transferred to switch, switch carries out remote transmission, and the remote terminal on the Ethernet and integrated management PC can monitor tracing process behind the decoded video signal.
Referring to Fig. 2, graphics processing unit comprises dsp processor, power circuit, reset circuit, clock circuit, debugging interface, serial ports, Fast Ethernet mouth, data memory Flash, synchronous dynamic storage SDRAM and decoder, wherein, dsp processor is connected with Video Decoder with power circuit, reset circuit, clock circuit, debugging interface, serial ports, Fast Ethernet mouth, data memory Flash, synchronous dynamic storage SDRAM respectively.Graphics processing unit is the core component of whole system, it is converted to digital signal gathering the visible light vision signal through Video Decoder, sending into little dsp processor then handles, extract target information on the one hand, the information of gathering is carried out target image follow the tracks of processing, the digital signal after by the Fast Ethernet interface coding being compressed uploads to Ethernet.It is real-time streaming protocol that RTSP is adopted in the Ethernet transmission, UDP is the real time video image transmission technology of bottom host-host protocol, RTSP can provide temporal information and realize that stream synchronously, provide reliable transfer mechanism for transmitting packet in order, flow control or congested control are provided, can make the efficiency of transmission optimization with effective feedback and minimum expense, adopt H.264 video image compression standard, save the network bandwidth.By certain algorithm process, calculate the target location on the other hand, take aim at tool by servomechanism control and rotate the pursuit movement target.Dsp processor is selected high-performance DM642 chip for use, the TVP515O video decoding chip that decoder adopts TI company to produce.
Referring to Fig. 3, a kind of target image real-time Transmission and tracking based on DSP may further comprise the steps:
1.1 video monitoring signal is connected to the video inputs of graphics processing unit by the output of video camera, finishes the input of vision signal, the signal of input is the video standard signal of Phase Alternation Line system or TSC-system.
1.2 the vision signal through the graphics processing unit video inputs is converted into data image signal by Video Decoder, the Phase Alternation Line system or the TSC-system vision signal that are about to standard are converted to digital difference signal, and its output format is ITU-R BT.656.
1.3 carry out carrying out image threshold segmentation and binaryzation, target and background is separated, namely adopt maximum variance between clusters to choose the threshold value that image is cut apart automatically according to the luminance signal in every frame of digital color difference signal, brightness value is set to 255 greater than the brightness of the pixel of threshold value, is set to 0 less than the brightness of the pixel of threshold value.
1.4 utilize the connected domain algorithm based on pixel, the target in the binary image is divided into a plurality of zones, follow the criterion according to the setting in the algorithm to extract the target that will follow the tracks of.
1.5 set up the To Template of images match with the luminance signal of tracked target, the To Template size is got the 20*20 pixel; At the Bo Mennei ferret out, calculate the similarity of real-time subarea image and To Template, calculating formula of similarity is as follows:
Wherein (i j) is reference template image to t, is of a size of M * N.(i j) is real-time subarea image to f;
Similarity satisfies | and r (u, v) | (u, maximum v) is best matched position to≤1, r.In the images match tracing process, the To Template image is sliding in the early pulse, and makes related operation with real-time subarea image, seeks best match point, with the match point of the best position as tracked target.When the similarity of the match point of the best greater than the value of setting, then carry out template renewal, the value of setting is got the number greater than 0.9; The template that adopts refreshes strategy and is:
Wherein, T is new template,
Be the subgraph at current optimal match point place,
For working as front template, α is the confidence level of current optimal match point virgin figure, 0＜α＜1.
1.6 according to the track of target travel, utilize under the least square method target of prediction position that a bit may occur, with preceding 3 positions of target, come under the target of prediction position of any in the algorithm.The trajectory predictions equation is:
X(k+1)=(4x(k)+x(k-1)?-2x(k-2))/3
Y(k+1)=(4y(k)+y(k-1)?-2y(k-2))/3
Wherein x (t) be target in the position of X direction, y (t) be target in the position of y direction, k is the integer more than or equal to 2;
Centered by this future position, and with the ripple door of 60*60 pixel size, the search gate of next frame is set, and sends the cradle head control order by serial ports, make The Cloud Terrace move under the target position of a bit.
If 1.7 do not search target at the Bo Mennei of present frame, then enlarge ripple door size and come ferret out in next frame, the ripple door size of expansion is 80*80; If next frame does not also search target, then from following frame, adopt the search of connected domain algorithm full screen scanning, up to regaining target.
1.8 treated image by the Fast Ethernet physical layer, is adopted H.264 standard code compression, transmits the computer decoding vision signal on the network, remote monitoring target following process with the UDP host-host protocol at Ethernet.
1.9 integrated management computer monitoring target following process, by the system synthesis administration interface, the tracking mode that system can be set is to adopt from motion tracking or manually tracking, being camera from motion tracking realizes tracking to target according to the tracking control in the algorithm, manually following the tracks of is that the monitor staff is according to video image, send camera by Ethernet to graphics processing unit at the integrated management interface and rotate order, thus control camera tracking target; The monitor staff also can double-click in video window and want the target of following the tracks of, thereby changes the target that will follow the tracks of.
Claims (4)
1. target image real-time Transmission and tracking based on a DSP is characterized in that: may further comprise the steps:
Step 1: video monitoring signal is connected to the video inputs of graphics processing unit by the output of video camera, finishes the input of vision signal, and the signal of input is the video standard signal of Phase Alternation Line system or TSC-system;
Step 2: the vision signal through the graphics processing unit video inputs is converted into data image signal by Video Decoder, and the Phase Alternation Line system or the TSC-system vision signal that are about to standard are converted to digital difference signal, and its output format is ITU-R BT.656;
Step 3: carry out carrying out image threshold segmentation and binaryzation, target and background is separated, namely adopt maximum variance between clusters to choose the threshold value that image is cut apart automatically according to the luminance signal in every frame of digital color difference signal, brightness value is set to 255 greater than the brightness of the pixel of threshold value, is set to 0 less than the brightness of the pixel of threshold value;
Step 4: utilize the connected domain algorithm, the target in the binary image is divided into a plurality of zones, extract the target that to follow the tracks of according to the criterion of the setting in the algorithm;
Step 5: the To Template of setting up images match with the luminance signal of tracked target, at the Bo Mennei ferret out, calculate the similarity when front template and To Template, with the position of the highest point of similarity as tracked target, if highest similarity is greater than the value of setting, then carry out template renewal, be about to the highest template of similarity as To Template;
Step 6: according to the track of target travel, utilize the position that a bit may occur under the least square method target of prediction, centered by this point, and with fixing ripple door size, the search gate of next frame is set, and send the cradle head control order by serial ports, make The Cloud Terrace move under the target position of a bit;
Step 7: if do not search target at the Bo Mennei of present frame, then in next frame, expand and be twice ripple door size and come ferret out, if next frame does not also search target, then from following frame, adopt the search of connected domain algorithm full screen scanning, up to regaining target;
Step 8: treated image by the Fast Ethernet physical layer, is adopted H.264 standard code compression, transmit the computer decoding vision signal on the network, remote monitoring target following process with the UDP host-host protocol at Ethernet;
Step 9: the integrated management computer sends related command by Ethernet to graphics processing unit, and the target that change will be followed the tracks of and switching tracking mode namely adopt from motion tracking and still manually follow the tracks of.
2. a kind of target image real-time Transmission and tracking based on DSP according to claim 1 is characterized in that: the ripple door size in the step 6 for the 50*50 pixel to the 80*80 pixel.
3. target image real-time Transmission and tracking means based on a DSP, it is characterized in that: comprise graphics processing unit, take aim at tool, hunting gear, switch, remote terminal and integrated management PC, wherein, graphics processing unit is respectively with switch, hunting gear with take aim at tool and be connected, switch also is connected with remote terminal with integrated management PC, takes aim at tool and also is connected with hunting gear; The camera of taking aim in the tool passes to graphics processing unit to the visible light vision signal of gathering, graphics processing unit carries out target image and follows the tracks of processing, extract target information, control command is sent to hunting gear by serial ports, hunting gear control is taken aim at tool and is rotated the pursuit movement target, and the processed video image is transferred to switch, and switch carries out remote transmission, and the remote terminal on the Ethernet and integrated management PC can monitor tracing process behind the decoded video signal.
4. a kind of target image real-time Transmission and tracking means based on DSP according to claim 3, it is characterized in that: described graphics processing unit comprises dsp processor, power circuit, reset circuit, clock circuit, debugging interface, serial ports, Fast Ethernet mouth, data memory Flash, synchronous dynamic storage SDRAM and decoder, wherein, dsp processor is connected with Video Decoder with power circuit, reset circuit, clock circuit, debugging interface, serial ports, Fast Ethernet mouth, data memory Flash, synchronous dynamic storage SDRAM respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117419.0A CN103200394B (en) | 2013-04-07 | 2013-04-07 | Based on the target image real-time Transmission of DSP and tracking and device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310117419.0A CN103200394B (en) | 2013-04-07 | 2013-04-07 | Based on the target image real-time Transmission of DSP and tracking and device thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103200394A true CN103200394A (en) | 2013-07-10 |
| CN103200394B CN103200394B (en) | 2016-04-20 |
Family
ID=48722735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310117419.0A Expired - Fee Related CN103200394B (en) | 2013-04-07 | 2013-04-07 | Based on the target image real-time Transmission of DSP and tracking and device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103200394B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103391430A (en) * | 2013-07-22 | 2013-11-13 | 南通大学 | DSP (digital signal processor) based relevant tracking method and special device |
| CN103838258A (en) * | 2014-02-26 | 2014-06-04 | 上海微小卫星工程中心 | Automatic tracking method and system applied to space-based space target |
| CN104038744A (en) * | 2013-07-22 | 2014-09-10 | 南通大学 | Correlation tracking method based on DSP (digital signal processor) with high tracking success rate |
| CN104065925A (en) * | 2013-07-22 | 2014-09-24 | 南通大学 | Correlation Tracking Method Based on DSP with Low Power Consumption |
| CN106131482A (en) * | 2016-06-27 | 2016-11-16 | 西安应用光学研究所 | Unmanned carrier optoelectronic aims of systems capture systems and method |
| CN108196729A (en) * | 2018-01-16 | 2018-06-22 | 安徽慧视金瞳科技有限公司 | A kind of finger tip point rapid detection method based on infrared video |
| CN108665487A (en) * | 2017-10-17 | 2018-10-16 | 国网河南省电力公司郑州供电公司 | Substation's manipulating object and object localization method based on the fusion of infrared and visible light |
| CN108769550A (en) * | 2018-05-16 | 2018-11-06 | 中国人民解放军军事科学院军事医学研究院 | A kind of notable analysis system of image based on DSP and method |
| CN109302592A (en) * | 2018-11-29 | 2019-02-01 | 中通服咨询设计研究院有限公司 | A kind of analysis of animal house Image Acquisition and Transmission system based on FPGA |
| CN109871813A (en) * | 2019-02-25 | 2019-06-11 | 沈阳上博智像科技有限公司 | A kind of realtime graphic tracking and system |
| CN109978912A (en) * | 2019-02-27 | 2019-07-05 | 北方民族大学 | A kind of object tracking methods and system based on Bessel square |
| CN110895120A (en) * | 2018-09-13 | 2020-03-20 | 中国舰船研究设计中心 | Image processing technology-based ship cannon system precision detection device and detection method |
| CN112613524A (en) * | 2020-10-30 | 2021-04-06 | 西安方元明科技股份有限公司 | Searching and tracking rotary table image processing system |
| CN113505444A (en) * | 2021-09-09 | 2021-10-15 | 中国电子科技集团公司第二十八研究所 | Self-attention-based multi-dimensional trajectory prediction method and device |
| CN115877328A (en) * | 2023-03-06 | 2023-03-31 | 成都鹰谷米特科技有限公司 | Signal receiving and transmitting method of array radar and array radar |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127887A (en) * | 2007-08-28 | 2008-02-20 | 湖南大学 | Intelligent visual monitoring method and device |
| CN102497543A (en) * | 2012-01-06 | 2012-06-13 | 合肥博微安全电子科技有限公司 | Multi-target tracking method based on DSP and system thereof |
-
2013
- 2013-04-07 CN CN201310117419.0A patent/CN103200394B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127887A (en) * | 2007-08-28 | 2008-02-20 | 湖南大学 | Intelligent visual monitoring method and device |
| CN102497543A (en) * | 2012-01-06 | 2012-06-13 | 合肥博微安全电子科技有限公司 | Multi-target tracking method based on DSP and system thereof |
Non-Patent Citations (1)
| Title |
|---|
| 卢莉萍，李翰山，张宏: "一种轨道式动态目标跟踪算法", 《南京航空航天大学学报》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104038744A (en) * | 2013-07-22 | 2014-09-10 | 南通大学 | Correlation tracking method based on DSP (digital signal processor) with high tracking success rate |
| CN103391430B (en) * | 2013-07-22 | 2014-09-10 | 南通大学 | DSP (digital signal processor) based relevant tracking method and special device |
| CN104065925A (en) * | 2013-07-22 | 2014-09-24 | 南通大学 | Correlation Tracking Method Based on DSP with Low Power Consumption |
| CN104065925B (en) * | 2013-07-22 | 2017-02-08 | 南通大学 | Low-power-consumption DSP-based relevant tracking method |
| CN103391430A (en) * | 2013-07-22 | 2013-11-13 | 南通大学 | DSP (digital signal processor) based relevant tracking method and special device |
| CN103838258A (en) * | 2014-02-26 | 2014-06-04 | 上海微小卫星工程中心 | Automatic tracking method and system applied to space-based space target |
| CN103838258B (en) * | 2014-02-26 | 2016-05-25 | 上海微小卫星工程中心 | A kind of automatic tracking method and system that is applied to Space-based Space |
| CN106131482A (en) * | 2016-06-27 | 2016-11-16 | 西安应用光学研究所 | Unmanned carrier optoelectronic aims of systems capture systems and method |
| CN106131482B (en) * | 2016-06-27 | 2019-01-11 | 西安应用光学研究所 | Unmanned carrier optoelectronic aims of systems capture systems and method |
| CN108665487B (en) * | 2017-10-17 | 2022-12-13 | 国网河南省电力公司郑州供电公司 | Substation operating object and target location method based on infrared and visible light fusion |
| CN108665487A (en) * | 2017-10-17 | 2018-10-16 | 国网河南省电力公司郑州供电公司 | Substation's manipulating object and object localization method based on the fusion of infrared and visible light |
| CN108196729A (en) * | 2018-01-16 | 2018-06-22 | 安徽慧视金瞳科技有限公司 | A kind of finger tip point rapid detection method based on infrared video |
| CN108769550A (en) * | 2018-05-16 | 2018-11-06 | 中国人民解放军军事科学院军事医学研究院 | A kind of notable analysis system of image based on DSP and method |
| CN108769550B (en) * | 2018-05-16 | 2020-07-07 | 中国人民解放军军事科学院军事医学研究院 | Image significance analysis system and method based on DSP |
| CN110895120A (en) * | 2018-09-13 | 2020-03-20 | 中国舰船研究设计中心 | Image processing technology-based ship cannon system precision detection device and detection method |
| CN110895120B (en) * | 2018-09-13 | 2022-04-08 | 中国舰船研究设计中心 | Image processing technology-based ship cannon system precision detection device and detection method |
| CN109302592A (en) * | 2018-11-29 | 2019-02-01 | 中通服咨询设计研究院有限公司 | A kind of analysis of animal house Image Acquisition and Transmission system based on FPGA |
| CN109871813A (en) * | 2019-02-25 | 2019-06-11 | 沈阳上博智像科技有限公司 | A kind of realtime graphic tracking and system |
| CN109978912A (en) * | 2019-02-27 | 2019-07-05 | 北方民族大学 | A kind of object tracking methods and system based on Bessel square |
| CN112613524A (en) * | 2020-10-30 | 2021-04-06 | 西安方元明科技股份有限公司 | Searching and tracking rotary table image processing system |
| CN113505444A (en) * | 2021-09-09 | 2021-10-15 | 中国电子科技集团公司第二十八研究所 | Self-attention-based multi-dimensional trajectory prediction method and device |
| CN115877328A (en) * | 2023-03-06 | 2023-03-31 | 成都鹰谷米特科技有限公司 | Signal receiving and transmitting method of array radar and array radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103200394B (en) | 2016-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103200394A (en) | Target image real time transmission and tracking method based on digital signal processor (DSP) and target image real time transmission and tracking device based on digital signal processor (DSP) | |
| Wang et al. | Enabling edge-cloud video analytics for robotics applications | |
| US9928605B2 (en) | Real-time cascaded object recognition | |
| CN108154523B (en) | A kind of real-time modeling method system and method in airborne photoelectric platform | |
| CN110175587B (en) | Video tracking method based on face recognition and gait recognition algorithm | |
| CN104298348B (en) | A kind of infrared gesture recognition, image capture method, device and video camera | |
| US10366482B2 (en) | Method and system for automated video image focus change detection and classification | |
| CN103327310A (en) | Monitoring and cruising method based on mouse trail tracking | |
| Jiang et al. | Perceive, interact, predict: Learning dynamic and static clues for end-to-end motion prediction | |
| CN114913200B (en) | Multi-target tracking method and system based on spatiotemporal trajectory association | |
| CN105550655A (en) | Gesture image obtaining device and method | |
| Sgouropoulos et al. | Counting and tracking people in a smart room: An IoT approach | |
| WO2012163129A1 (en) | Intelligent video surveillance system and method | |
| Qi et al. | A dataset and system for real-time gun detection in surveillance video using deep learning | |
| CN108615243B (en) | Method, device and system for determining stereoscopic multimedia information | |
| JP5625443B2 (en) | Imaging system and imaging apparatus | |
| KR20110114957A (en) | Data transmission apparatus and method, network data transmission system and method using same | |
| WO2018057449A1 (en) | Auto-directing media construction | |
| US9065975B2 (en) | Method and apparatus for hands-free control of a far end camera | |
| US20220294971A1 (en) | Collaborative object detection | |
| CN105245845A (en) | Method for controlling camera to follow and shoot automatically based on gathering trend in match field | |
| CN108696725A (en) | A kind of camera long-range control method Internet-based and system | |
| JP2018023153A5 (en) | ||
| CN112052785A (en) | Intelligent monitoring system of inspection robot | |
| Liu et al. | Petri: Reducing bandwidth requirement in smart surveillance by edge-cloud collaborative adaptive frame clustering and pipelined bidirectional tracking |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160420 Termination date: 20180407 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |