CN1546993A - Infrared target detecting, tracking and identifying system - Google Patents
Infrared target detecting, tracking and identifying system Download PDFInfo
- Publication number
- CN1546993A CN1546993A CNA2003101090702A CN200310109070A CN1546993A CN 1546993 A CN1546993 A CN 1546993A CN A2003101090702 A CNA2003101090702 A CN A2003101090702A CN 200310109070 A CN200310109070 A CN 200310109070A CN 1546993 A CN1546993 A CN 1546993A
- Authority
- CN
- China
- Prior art keywords
- infrared
- image
- signal
- data
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Transforming Light Signals Into Electric Signals (AREA)
Abstract
The invention is a kind of infrared object tracing and identifying system which includes infrared imaging, infrared image receiving, infrared image processing and image and result displaying. The infrared image is acquired through the infrared imaging device, the digital image data and output control signal are transmitted to the infrared image receiving part through digital output difference port and difference single-end circuit, the receiving part of the image uses field programmable gate array FPGA to receive 14 bits difference signal, then the data is transmitted to the infrared image processing part double digital signal processor DSP board system through token bus, carries on object detecting and tracing and identifying to the infrared image, the processing result and the original data is transmitted to the monitor through the computer bus.
Description
Technical field:
The present invention relates to a kind of infrared target and detect tracking and recognition system, be in order to obtain the high-performance infrared target image, and the infrared image target detection is followed the tracks of and discerned and the hardware platform of design, be based on the passive infrared detection system that the advanced person stares focal plane arrays (FPA).Can be widely used in fields such as sophisticated and futuristic weapons system, security monitoring, intelligent transportation and industrial automation detection.
Background technology:
Along with the development of infrared eye technology, thermal imaging system adopted unit or polynary discrete detector to add one dimension or two-dimentional opto-mechanical scanner from the past and has developed into gazing type imaging device without optical mechaical scanning.Based on the infrared thermal imaging detection system of staring focal plane arrays (FPA), no matter on temperature control and spatial resolution, still on frame frequency and spectral response, all be greatly improved.Since the focal plane stare thermal imaging system exclusive premium properties, become the new and high technology that research and develop energetically countries in the world.As one of key link of Intelligentized Information, it is puzzlement and the bottleneck problem that restricts the infrared imaging detection Practical Performance and technological difficulties and need to be resolved hurrily that infrared target detects imaging tracking and recognition technology always, caused at present domestic and international expert's great attention, and carried out deep, extensive studies around this problem.
Infrared target detect to follow the tracks of with identifying in, need detect and lock target to be identified as soon as possible, but the low signal-to-noise ratio infrared target detects with identification and is faced with numerous technical barriers under to empty varying background.These technical barriers mainly contain:
1. target does not have information such as size, shape and texture, and traditional image processing method can't be used;
2. varying background causes echo signal often to be submerged among the noise;
3. data volume is big, is difficult to real-time processing.
The researchist has proposed certain methods at the target detection Tracking Recognition in the low signal-to-noise ratio infrared image both at home and abroad, as three-dimensional matched filtering, block sequential likelihood ratio detection method, dynamic programming, high-order correlation method, wavelet analysis and neural net method etc., but calculated amount is very big, is difficult to handle in real time sequence of video images.In addition, the defective that significantly restricts above-mentioned algorithm practice is that mainly various algorithms are based upon noise profile, even on the basis of target distribution as priori.Although above hypothesis is brought convenience in detection algorithm design, algorithm performance analysis and interpretation of result, because in actual conditions, most applications is not satisfy hypothesis to distribute, inevitably like this introduced error, even obtained wrong conclusion.
Summary of the invention:
The objective of the invention is to some problems of existing in the existing infrared imaging detection system, providing a kind of infrared target to detect follows the tracks of and recognition system, can improve the infrared image image quality, improve infrared target and detect tracking, accuracy of identification, reach desirable practical function.
For realizing such purpose, innovative point of the present invention is to adopt infrared thermoviewer and high-speed image receiving trap and real time data processing integrated circuit board, has set up a whole set of infrared target and has detected tracking and recognition system.
Infrared target of the present invention detects to follow the tracks of with recognition system to be made up of four parts: comprise infrared imaging, infrared image receives, infrared image processing and image and result show four parts, the infrared imaging part is made of infrared thermoviewer, its Serial Control port connects main frame, an output port connects video display, another digital output port is the output of differential signal RS422 numeral, change single-end circuit through difference and connect the infrared image receiving unit, the infrared image receiving unit adopts a cover field programmable gate array FPGA integrated circuit board, its digital input/output port is set to input pattern, FPGA integrated circuit board reads image data, sequential according to signal, utilize control frame signal, row control signal and pixel clock signal are provided with the moment of reading images, with data latching in the middle of the FIFO stack FIFO, FIFO reads enable signal to one whenever and sends once, infrared image processing partly adopts even numbers word signal Processing dsp board card, read the state of DSP deal with data by the register that is arranged on the image receiving unit, coordinate the reception and the processing of view data, after the Flame Image Process of a frame is intact with the zone bit set of register, can read the next frame data with expression, two dsp board cards comprise that infrared target detects, three modules of infrared object tracking and infrared identification, the output of infrared target detection module connects infrared object tracking and infrared identification module, and infrared target detects, the output of infrared object tracking and three modules of infrared identification transmits by the FIFO on the token bus between integrated circuit board; End product and raw image data are delivered to image and display part as a result by the bus of main frame, image and as a result the display part with intensity profile 0～2
14Source images to be mapped as intensity profile be 0～2
8Image and show.
During system works, infrared image at first obtains by infrared thermoviewer, change single-end circuit by numeral output difference RS422 port and difference, Digital Image Data and output control signal are delivered to the digital input/output port of FPGA integrated circuit board, digital input/output port is set to input pattern.FPGA integrated circuit board reads image data is delivered to data in two dsp board card systems and is handled by being integrated in token bus on the integrated circuit board, and the content of processing comprises that target detection is followed the tracks of, identification.Result that target detection is followed the tracks of, discerned and raw image data are delivered on the display by the pci bus of computing machine and are shown.
Infrared target of the present invention detects to follow the tracks of with recognition system has following beneficial effect:
Infrared target of the present invention detects to be followed the tracks of and recognition system, be based on the passive infrared detection system that the advanced person stares focal plane arrays (FPA), have advantages such as investigative range is wide, bearing accuracy is high, recognition capability is strong, operating distance is far away, for the significant and practical value of subsequent treatment work of application system.
Description of drawings:
Fig. 1 is that infrared target of the present invention detects tracking and recognition system structure principle chart.
Fig. 2 uses the sequential of infrared thermoviewer output signal for the present invention.
Fig. 3 is the image in the embodiment of the invention.
Among Fig. 3, (a) and (b) are real scene shooting images, (c), (d) be image that sky is taken and the result that adopts the mathematical morphology filter technology and go out based on the feature detection of local energy maximum, (e), (f) be the result who adopts threshold value associating seed points growing method to cut apart to empty real scene shooting image and face.
Embodiment:
Below in conjunction with drawings and Examples technical scheme of the present invention is further described.
In the embodiments of the invention, utilize the high-performance infrared thermoviewer photograph respectively Fig. 3 (a) (b) target over the ground and staff, Fig. 3 (c), (e) take is to null object.Adopt system of the present invention to carry out infrared target and detect tracking and identification, the concrete implementation detail of each several part is as follows:
Infrared target detects to follow the tracks of with recognition system to be made up of four parts: comprise that infrared imaging, infrared image reception, infrared image processing and image and result show four parts.The infrared head that the high-performance infrared thermoviewer is adopted is that Fu Lade company of French institute produces.Infrared thermoviewer one has two output ports and a Serial Control port.One of them of two output ports is used for video output, utilizes a video monitor just can observe the video simulation image of infrared thermoviewer output; The another one output port is the output of differential signal RS422 numeral.The Serial Control port links to each other with main frame, main effect is the performance of regulating infrared thermoviewer, as: regulate the output speed (25 frame/seconds, 50 frame/seconds and 100 frame/seconds are optional) of digital picture, integral time and the correcting image of regulating image have reached best imaging effect.
The digital output format of infrared camera is to adopt the RS422 differential signal, and sort signal can be restrained the common mode interference that produces between the signal in the transmission course, grows Distance Transmission.Port is exported 14 bit data and 3 control signals.3 control signals are respectively pixel clock signal, row control signal and frame synchronization control signal.In order to guarantee that data can transmit under the situation of lower transmission error rates, must make full use of these control signals, and these control signals are at large analyzed.Sequential relationship between them is seen shown in Figure 2.
The transmission course of data has adopted three groups of control signals.Sometime, a downward pulse appears in control frame signal before the view data of a frame arrives, and is ready to the transmission of rising edge presentation video, waits for the row control signal.When first row control signal arrives, with the sign of this signal rising edge as data arrival.Rising edge of clock signal is as to the sign that latchs of pixel data, the corresponding time clock of pixel.Only send piece image (76800 pixels) between two control frame signals; Only send delegation's signal (320 pixels) between two capable control signals; A clock period sends a pixel.Thereby avoided between image data frame and the frame, row with capable between and the error code between the pixel, and then guaranteed to obtain high-quality infrared digital image.
The front is mentioned, and RS422 is a kind of differential signal, and a signal is represented with two signal line, bars transmission actual signal, the inverse value of another transmission real data.The control signal and the data-signal that record in actual signal one side all have reasonable temporal aspect, but the common mode interference of signal has produced very big influence in the system that enters the FPGA integrated circuit board, to such an extent as to pixel clock signal produces a lot of burrs, make the image that shows shake.Therefore native system must change into single-ended signal with differential signal.Change-over circuit has adopted the difference of chip Motorola to change single-ended chip MC3486.
The reception of infrared image and the hardware using of processing be master card HEPC9, field programmable gate array integrated circuit board HERON-FPGA3S and the digital signal processing dsp board card HERON4 that Hunter company produces.HEPC9 is a master card, handles the carrier of integrated circuit board as various Hunter company.HERON-FPGA3S is a FPGA integrated circuit board, is responsible for receiving infrared picture data; HERON4 is the dsp board card, is responsible for the target in the image is detected tracking and identification.After the differential data that transmits from infrared thermoviewer is transformed into single-ended signal by change-over circuit, directly enter the on-site programmable gate array FPGA chip.The FPGA programming realizes the conversion of control signal, will consider two groups of control signals altogether, and one group of signal comes from infrared thermoviewer, as pixel clock, row control signal and frame synchronization control signal; Another group signal comes from digital signal processor DSP, and DSP is provided with the state of this signal according to own computing situation, when DSP handles a frame signal and is in waiting status, to this home position signal, to represent receiving data.FPGA writes view data according to these signals on a FIFO stack FIFO who self opens up.After view data writes among the FIFO, wait for that the dsp board card is responded to read signal, so that the data among the FIFO are carried out read operation, thereby finish the reception of data.Two dsp board clampings receive after the view data of a frame that a DSP that will at first distribute to wherein carries out the target detection tracking, and at this moment, another piece DSP may just discern the target of previous frame image or be in waiting status.First DSP is used for the infrared target detection and Identification, at first adopted the signal to noise ratio (S/N ratio) that improves infrared target image based on the image pre-processing method of elliptic paraboloid volume, by thresholding is set, finally obtains testing result through test of hypothesis then.Testing result is delivered to another part program and is carried out target following, the infrared object tracking algorithm has been considered the inter-frame correlation information of image and the continuity of target travel, randomness according to clutter and noise profile is carried out data association, adopts current statistical model and Kalman filtering algorithm to follow the tracks of real goal.After finishing target detection and tracking, first DSP stops computing, waits for the infrared picture data of next frame.Result after the target detection also will deliver on another piece DSP and carry out Target Recognition, the infrared identification algorithm at first adopts the method for seed points region growing to carry out image segmentation, target is carried out feature extraction and classification after dividing processing, adopt and based on invariable rotary morphology neural network target is classified; The mode standard storehouse has been adopted in the sample mode storehouse.After having finished aforesaid operations, second DSP waits for the data of first DSP.
Infrared image and the display part of handling the back image.What the demonstration of infrared image was adopted is Pentium III 866 industrial computers, internal memory 128M, and result after DSP handles and untreated image can be delivered on the display by pci bus and show.The C Programming with Pascal Language is adopted in the display part.Because the data of infrared camera are 14 data, can't use 14 grades of image gray on the WINDOWS platform, have only it to be mapped to 8 image space, just image can be shown for the user and use.Analyze the histogram of 14 potential source images and find that the pixel distribution of image often concentrates on a part, if simply carry out the linear mapping of image, because the quantity of information of 8 pixels reduces, the image after the conversion is often lost many information.Bring influence in order to overcome this image information uneven distribution, native system has adopted source images intensity profile 0～2
14Being mapped to intensity profile is 0～2
8Image, can reflect the information of former figure.
As shown in Figure 3, (a) and (b) are real scene shooting images, (c), (d) be image that sky is taken and the result that adopts the mathematical morphology filter technology and go out based on the feature detection of local energy maximum, (e), (f) be the result who adopts threshold value associating seed points growing method to cut apart to empty real scene shooting image and face.Target detection probability can reach 99%, and false-alarm probability is 0.1%; The tracking elementary probability of target can reach 94%; Employing is based on the infrared sequence image target identification method of invariable rotary morphology neural network, target by point target when the transition of appearance mark, recognition correct rate when training sample and detection sample strong correlation is 94.9%, and the recognition correct rate when training sample is weak relevant with the detection sample is 91.9%.The travelling speed of whole algorithm in two dsp board card system can reach the live effect of frame p.s.s 25.Thereby as can be seen, system of the present invention has advantages such as investigative range is wide, bearing accuracy is high, recognition capability is strong, operating distance is far away.
Claims (2)
1, a kind of infrared target detects to be followed the tracks of and recognition system, comprise infrared imaging, infrared image receives, infrared image processing and image and result show four parts, it is characterized in that the infrared imaging part is made of infrared thermoviewer, its Serial Control port connects main frame, an output port connects video display, another digital output port is the output of differential signal RS422 numeral, change single-end circuit through difference and connect the infrared image receiving unit, the infrared image receiving unit adopts a cover field programmable gate array FPGA integrated circuit board, its digital input/output port is set to input pattern, FPGA integrated circuit board reads image data, sequential according to signal, utilize control frame signal, row control signal and pixel clock signal are provided with the moment of reading images, with data latching in the middle of the FIFO stack FIFO, FIFO reads enable signal to one whenever and sends once, infrared image processing partly adopts even numbers word signal Processing dsp board card, read the state of DSP deal with data by the register that is arranged on the image receiving unit, coordinate the reception and the processing of view data, after the Flame Image Process of a frame is intact with the zone bit set of register, can read the next frame data with expression, two dsp board cards comprise that infrared target detects, three modules of infrared object tracking and infrared identification, the output of infrared target detection module connects infrared object tracking and infrared identification module, and infrared target detects, the output of infrared object tracking and three modules of infrared identification transmits by the FIFO on the token bus between integrated circuit board; End product and raw image data are delivered to image and display part as a result by the bus of main frame, image and as a result the display part with intensity profile 0～2
14Source images to be mapped as intensity profile be 0～2
8Image and show.
2, infrared target as claimed in claim 1 detects and follows the tracks of and recognition system, it is characterized in that described infrared target detection module adopts the signal to noise ratio (S/N ratio) that improves infrared target image based on the image pre-processing method of elliptic paraboloid volume, then by thresholding is set, obtain testing result through test of hypothesis, infrared object tracking adopts current statistical model and Kalman filtering algorithm to follow the tracks of real goal, and the infrared identification module adopts the method for seed points region growing to carry out carrying out feature extraction and classification after the target image dividing processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200310109070 CN1235037C (en) | 2003-12-04 | 2003-12-04 | Infrared target detecting, tracking and identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200310109070 CN1235037C (en) | 2003-12-04 | 2003-12-04 | Infrared target detecting, tracking and identifying system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1546993A true CN1546993A (en) | 2004-11-17 |
| CN1235037C CN1235037C (en) | 2006-01-04 |
Family
ID=34335012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200310109070 Expired - Fee Related CN1235037C (en) | 2003-12-04 | 2003-12-04 | Infrared target detecting, tracking and identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1235037C (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100385251C (en) * | 2005-08-18 | 2008-04-30 | 上海交通大学 | Real-time detection method of multiple small targets under infrared large visual field environment |
| CN100498806C (en) * | 2007-09-19 | 2009-06-10 | 中国科学院上海技术物理研究所 | Device and method for outputting signal of emulation infrared detector |
| CN100498821C (en) * | 2007-07-06 | 2009-06-10 | 哈尔滨工程大学 | Infrared image real-time target identification and tracking device for movement background, and the method |
| CN101286236B (en) * | 2008-06-05 | 2010-06-16 | 上海交通大学 | Infrared object tracking method based on multi- characteristic image and average drifting |
| CN1967180B (en) * | 2006-04-27 | 2010-12-01 | 广州科易光电技术有限公司 | Infrared thermal-image data real-time compression/decompression method and infrared temperature monitoring device and system |
| CN101296368B (en) * | 2007-04-28 | 2011-07-06 | 长春奥普光电技术股份有限公司 | Image recognition tracking apparatus of television tracking machine |
| CN102333205A (en) * | 2011-07-28 | 2012-01-25 | 北京中科戎大信息技术有限公司 | Infrared moving target detecting and tracking device |
| CN102435142A (en) * | 2011-10-26 | 2012-05-02 | 合肥寰景信息技术有限公司 | Active infrared action identifying method |
| CN102510481A (en) * | 2011-11-10 | 2012-06-20 | 中国科学院上海技术物理研究所 | Signal processing method for low power consumption infrared real-time signal processing system |
| CN102693526A (en) * | 2011-03-23 | 2012-09-26 | 中国科学院上海技术物理研究所 | Infrared image processing method based on reconfigurable computing |
| CN102830391A (en) * | 2011-06-16 | 2012-12-19 | 中国科学院沈阳自动化研究所 | Accuracy index calculating method of infrared search and track system |
| CN103293167A (en) * | 2013-06-08 | 2013-09-11 | 湖南竟宁科技有限公司 | Automatic detection method and system of copper grains in foam nickel |
| CN103646232A (en) * | 2013-09-30 | 2014-03-19 | 华中科技大学 | Aircraft ground moving target infrared image identification device |
| CN104243889A (en) * | 2014-10-22 | 2014-12-24 | 成都市晶林科技有限公司 | Method for matching digital video signal transmission format of infrared thermal imaging machine core |
| CN104751157A (en) * | 2013-12-31 | 2015-07-01 | 中核控制系统工程有限公司 | FPGA (Field Programmable Gate Array)-based detection tracking method |
| CN106989251A (en) * | 2017-05-11 | 2017-07-28 | 蔡子昊 | A kind of high performance intelligent shooting tripod head |
| CN107123129A (en) * | 2017-04-28 | 2017-09-01 | 中国工程物理研究院应用电子学研究所 | A kind of image processing apparatus and method |
| CN108061602A (en) * | 2017-10-25 | 2018-05-22 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of highlighted suppressing method based on infrared imaging system |
| CN108170132A (en) * | 2018-01-09 | 2018-06-15 | 电子科技大学成都学院 | A kind of modularization EPS devices and its bus processing method based on universal serial bus |
| CN110907948A (en) * | 2019-11-19 | 2020-03-24 | 宁波展海电子科技有限公司 | Infrared signal filtering method applied to ship collision avoidance system |
| CN110942584A (en) * | 2019-11-07 | 2020-03-31 | 陈盈盈 | Laboratory access door |
| CN111052129A (en) * | 2017-07-28 | 2020-04-21 | 美国西门子医学诊断股份有限公司 | Deep learning volumetric quantification method and apparatus |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400153B (en) * | 2013-07-15 | 2017-05-10 | 中国航天科工集团第三研究院第八三五八研究所 | Serial filtering matching method and system for real-time image identification |
-
2003
- 2003-12-04 CN CN 200310109070 patent/CN1235037C/en not_active Expired - Fee Related
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100385251C (en) * | 2005-08-18 | 2008-04-30 | 上海交通大学 | Real-time detection method of multiple small targets under infrared large visual field environment |
| CN1967180B (en) * | 2006-04-27 | 2010-12-01 | 广州科易光电技术有限公司 | Infrared thermal-image data real-time compression/decompression method and infrared temperature monitoring device and system |
| CN101296368B (en) * | 2007-04-28 | 2011-07-06 | 长春奥普光电技术股份有限公司 | Image recognition tracking apparatus of television tracking machine |
| CN100498821C (en) * | 2007-07-06 | 2009-06-10 | 哈尔滨工程大学 | Infrared image real-time target identification and tracking device for movement background, and the method |
| CN100498806C (en) * | 2007-09-19 | 2009-06-10 | 中国科学院上海技术物理研究所 | Device and method for outputting signal of emulation infrared detector |
| CN101286236B (en) * | 2008-06-05 | 2010-06-16 | 上海交通大学 | Infrared object tracking method based on multi- characteristic image and average drifting |
| CN102693526A (en) * | 2011-03-23 | 2012-09-26 | 中国科学院上海技术物理研究所 | Infrared image processing method based on reconfigurable computing |
| CN102830391B (en) * | 2011-06-16 | 2014-10-22 | 中国科学院沈阳自动化研究所 | Accuracy index calculating method of infrared search and track system |
| CN102830391A (en) * | 2011-06-16 | 2012-12-19 | 中国科学院沈阳自动化研究所 | Accuracy index calculating method of infrared search and track system |
| CN102333205A (en) * | 2011-07-28 | 2012-01-25 | 北京中科戎大信息技术有限公司 | Infrared moving target detecting and tracking device |
| CN102435142A (en) * | 2011-10-26 | 2012-05-02 | 合肥寰景信息技术有限公司 | Active infrared action identifying method |
| CN102510481A (en) * | 2011-11-10 | 2012-06-20 | 中国科学院上海技术物理研究所 | Signal processing method for low power consumption infrared real-time signal processing system |
| CN103293167A (en) * | 2013-06-08 | 2013-09-11 | 湖南竟宁科技有限公司 | Automatic detection method and system of copper grains in foam nickel |
| CN103646232A (en) * | 2013-09-30 | 2014-03-19 | 华中科技大学 | Aircraft ground moving target infrared image identification device |
| CN103646232B (en) * | 2013-09-30 | 2016-08-17 | 华中科技大学 | Aircraft ground moving target infrared image identification device |
| CN104751157B (en) * | 2013-12-31 | 2018-07-27 | 中核控制系统工程有限公司 | Detecting and tracking method based on FPGA |
| CN104751157A (en) * | 2013-12-31 | 2015-07-01 | 中核控制系统工程有限公司 | FPGA (Field Programmable Gate Array)-based detection tracking method |
| WO2016061915A1 (en) * | 2014-10-22 | 2016-04-28 | 成都晶林科技有限公司 | Method for matching digital video signal transmission format of infrared thermal imaging machine core |
| CN104243889B (en) * | 2014-10-22 | 2018-01-30 | 成都市晶林科技有限公司 | Infrared thermal imaging movement digital signal transmission format match method |
| CN104243889A (en) * | 2014-10-22 | 2014-12-24 | 成都市晶林科技有限公司 | Method for matching digital video signal transmission format of infrared thermal imaging machine core |
| CN107123129A (en) * | 2017-04-28 | 2017-09-01 | 中国工程物理研究院应用电子学研究所 | A kind of image processing apparatus and method |
| CN106989251A (en) * | 2017-05-11 | 2017-07-28 | 蔡子昊 | A kind of high performance intelligent shooting tripod head |
| CN111052129A (en) * | 2017-07-28 | 2020-04-21 | 美国西门子医学诊断股份有限公司 | Deep learning volumetric quantification method and apparatus |
| CN111052129B (en) * | 2017-07-28 | 2024-03-08 | 美国西门子医学诊断股份有限公司 | Deep learning volume quantification method and apparatus |
| US11657593B2 (en) | 2017-07-28 | 2023-05-23 | Siemens Healthcare Diagnostics Inc. | Deep learning volume quantifying methods and apparatus |
| CN108061602B (en) * | 2017-10-25 | 2020-05-19 | 中国航空工业集团公司洛阳电光设备研究所 | Highlight inhibition method based on infrared imaging system |
| CN108061602A (en) * | 2017-10-25 | 2018-05-22 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of highlighted suppressing method based on infrared imaging system |
| CN108170132B (en) * | 2018-01-09 | 2022-04-01 | 电子科技大学成都学院 | Modular EPS bus processing method based on serial bus |
| CN108170132A (en) * | 2018-01-09 | 2018-06-15 | 电子科技大学成都学院 | A kind of modularization EPS devices and its bus processing method based on universal serial bus |
| CN110942584A (en) * | 2019-11-07 | 2020-03-31 | 陈盈盈 | Laboratory access door |
| CN110942584B (en) * | 2019-11-07 | 2021-04-20 | 宁波顺超轴承有限公司 | Laboratory access door |
| CN110907948A (en) * | 2019-11-19 | 2020-03-24 | 宁波展海电子科技有限公司 | Infrared signal filtering method applied to ship collision avoidance system |
| CN110907948B (en) * | 2019-11-19 | 2023-08-29 | 宁波展海电子科技有限公司 | Infrared signal filtering method applied to marine collision avoidance system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1235037C (en) | 2006-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1235037C (en) | Infrared target detecting, tracking and identifying system | |
| Saedi et al. | A deep neural network approach towards real-time on-branch fruit recognition for precision horticulture | |
| Boult et al. | Into the woods: Visual surveillance of noncooperative and camouflaged targets in complex outdoor settings | |
| CN109801265B (en) | Real-time transmission equipment foreign matter detection system based on convolutional neural network | |
| CN110033431A (en) | Non-contact detection device and detection method for detecting corrosion area on surface of steel bridge | |
| CN110335233B (en) | Highway guardrail plate defect detection system and method based on image processing technology | |
| CN1417739A (en) | CMOS image sensor with chip mode identifying function | |
| CN109670398A (en) | Pig image analysis method and pig image analysis equipment | |
| CN113139489B (en) | Crowd counting method and system based on background extraction and multi-scale fusion network | |
| CN110175506B (en) | Pedestrian re-identification method and device based on parallel dimensionality reduction convolutional neural network | |
| CN106407966B (en) | A kind of face identification method applied to attendance | |
| CN113962274A (en) | Abnormity identification method and device, electronic equipment and storage medium | |
| CN109977251A (en) | A method of building identifies commodity based on RGB histogram feature | |
| Zhang et al. | Gesture recognition system based on improved YOLO v3 | |
| CN111242057A (en) | Product sorting system, method, computer device and storage medium | |
| CN110751667A (en) | Method for detecting infrared dim small target under complex background based on human visual system | |
| Liu et al. | Implementation System of Human Eye Tracking Algorithm Based on FPGA. | |
| CN109376719A (en) | A kind of camera light Photo-Response Non-Uniformity fingerprint extraction and comparison method based on assemblage characteristic expression | |
| CN109815784A (en) | A kind of intelligent method for classifying based on thermal infrared imager, system and storage medium | |
| Yang et al. | Contrast limited adaptive histogram equalization for an advanced stereo visual slam system | |
| Qing et al. | Multi-Class on-Tree Peach Detection Using Improved YOLOv5s and Multi-Modal Images. | |
| Dahirou et al. | Motion Detection and Object Detection: Yolo (You Only Look Once) | |
| CN114529906A (en) | Method and system for detecting abnormity of digital instrument of power transmission equipment based on character recognition | |
| CN113888428A (en) | Infrared dim target detection method and device based on local contrast | |
| Zhang et al. | Fully automatic system for fish biomass estimation based on deep neural network |
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 | ||
| C19 | Lapse of patent right due to non-payment of the annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |