CN101025790A - Image-based bus passenger number automatic statistics meter - Google Patents
Image-based bus passenger number automatic statistics meter Download PDFInfo
- Publication number
- CN101025790A CN101025790A CN 200710000571 CN200710000571A CN101025790A CN 101025790 A CN101025790 A CN 101025790A CN 200710000571 CN200710000571 CN 200710000571 CN 200710000571 A CN200710000571 A CN 200710000571A CN 101025790 A CN101025790 A CN 101025790A
- Authority
- CN
- China
- Prior art keywords
- chip
- image
- dsp
- programmable logic
- dsp chip
- 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
- Image Processing (AREA)
Abstract
The invention discloses an image-based in-bus person automatic counter, comprising: image collecting and processing module and image processing algorithm, where the image collecting and processing module comprises CCD camera, video decoding chip, programmable logic chip and DSP chip, where the output of the CCD camera is connected with the input of the video decoding chip, the control and output ends of the video decoding chip are connected with the programmable logic chip, and the programmable logic chip is connected with the DSP chip; the programmable logic chip is written with a HDL program for implementing data exchange, control and buffering between the video decoding chip and the DSP chip; the DSP chip runs image processing and recognizing software. And the invention adopts high speed DSP and FPGA design and makes image recognition by advanced image processing and recognizing algorithm, and the whole system has high calculating rate and can implement real-time and accurate person number recognition; and its hardware structure is simple, having stable performance and convenient to install and debug.
Description
Technical field
The present invention relates to a kind of embedded digital treatment circuit and a kind of image processing algorithm, specifically, relate to a kind of image recognition and application technology based on the DSP digital processing circuit.
Background technology
The technology that is used for the bus passenger flow statistics at present mainly contains: photoelectric detection method, pressure sensing method, photoelectric sensing method, IC-card read method and video analysis method.
Photoelectric detection method requires the shape of object to be detected unified and standard, and the motor behavior strict conformance is used bus passenger flow and detected, and has several factors to consider.Such as: passenger's individual difference is very big, the fat or thin difference of height, the action of passenger loading simultaneously also is not quite similar, and adds, and possible portable thing is easy to cause misoperation.Passenger loading will carry out successively, in order to make a distinction, also will leave the space each other, so this kind detect the method for passenger flow, still is that the installation site of optoelectronic switch all has comparatively strict requirement to passenger's behavior, specifically implements bigger difficulty.
The pressure sensing method is less to people's individual difference requirement, but still requires the passenger to get on the bus successively, can not crowd, otherwise, still may produce misoperation.This kind method requires the performance of pressure transducer very high, can long-term stable operation.This scheme feasibility is bigger.For the passenger stands in the pedal place when preventing that bus is crowded, causes the perseveration of pressure transducer, and cause the error of detection that ad hoc fixed car door opening signal only under the situation of car door opening, just makes the pressure transducer counting effective.Though the method has exploitativeness preferably, passenger's behavior also there is strict requirement, especially in the passenger peak period, realize getting on or off the bus of passenger simultaneously, pressure transducer can not be accomplished.
The photoelectric sensing method is the data of gathering passenger getting on/off by various sensor, calculates the current volume of the flow of passengers through special passenger flow processor, and this product just is in the pre-stage test stage at home.
Domestic production passenger flow product relatively specialty have only scrupulously and respectfully two companies of hundred million big and labor, external production passenger flow product mainly contain German Dilax company and Canadian INFODEV company, because they adopt different sensors to carry out the data acquisition of passenger flow, passenger flow statistics has the regular hour delay, and all there is higher False Rate (be about 7-8% between low peak period, the peak period is about 12-15%).
IC-card reads the mode of method detection passenger flow to the fairly simple convenience of the detection of passenger loading, has both made full use of resource, again passenger's behavior is not had strict standard.But all uncomfortable use IC-card of domestic a lot of people is consumed, and causes it to apply at home.
The video analysis method is noted the situation of passenger getting on/off, utilizes technology such as image recognition technology and software analysis then, identifies the passengers quantity of getting on or off the bus.This method more complicated, price is higher, and the construction cycle is longer, is unfavorable for large-scale production.
The basic thought of photoelectric detection method and pressure sensing method is: at first passenger loading number and the number of getting off are added up respectively, the summation that then two numerical value added up has just obtained the volume of the flow of passengers of motorbus.Photoelectric detection method requires passenger's shape unified and standard, the motor behavior strict conformance.Because passenger's individual difference is very big, specifically implements bigger difficulty.Though the pressure sensing method has exploitativeness preferably, in passenger peak period, the passenger is at the Qianmen or back door when getting on or off the bus simultaneously, and pressure transducer just can't be differentiated the passenger and gets on the bus or get off, so the method is invalid.The advantage that IC-card reads method is simple, accurate, but not every people uses IC-card to consume.The statistical precision of photoelectric sensing method during normal passenger flow can reach 92%-93%, but the statistical precision during the commuter rush hour drops to 83%-85%, and the statistical delay that especially exists during the commuter rush hour is very big to the operational efficiency influence of total system.Video analysis method complex structure, cost an arm and a leg, be difficult for to realize.
Summary of the invention
The present invention is just at the technical matters of above-mentioned existence and the bus passenger number automatic statistics meter based on image that a kind of detection speed is fast, statistical precision is high that designs.
The technical solution adopted for the present invention to solve the technical problems is: a kind of bus passenger number automatic statistics meter based on image comprises image acquisition, processing module and image processing algorithm.Image acquisition, processing module comprise CCD camera, video decoding chip, programmable logic chip and dsp chip; The output of CCD camera links to each other with the input of video decoding chip, and the control of video decoding chip links to each other with programmable logic chip with output terminal, and programmable logic chip links to each other with dsp chip.Write in the programmable logic chip and used the hardware description language written program, comprised the program that is used to realize video decoding chip and dsp chip exchanges data, control and buffer memory; Runs image processing and identification software on the dsp chip.
The memory chip of described bus passenger number automatic statistics meter based on image links to each other with programmable logic chip, and memory chip is as the external memory storage of dsp chip; Can wipe storage chip and link to each other with dsp chip by programmable logic chip, memory image is handled and identification software, is the dsp chip loading procedure during starting.
Perhaps, the memory chip of described bus passenger number automatic statistics meter based on image directly links to each other with dsp chip as the external memory storage of dsp chip; Can wipe storage chip and link to each other with dsp chip, memory image is handled and identification software, is the dsp chip loading procedure during starting.
The memory chip of described bus passenger number automatic statistics meter based on image is SRAM, SDRAM or DDRAM; The described storage chip of wiping is FLASH, EPROM or EEPROM.
The memory chip of described bus passenger number automatic statistics meter based on image is SRAM; The described storage chip of wiping is FLASH.
The programmable logic device (PLD) of described bus passenger number automatic statistics meter based on image is large-scale F PGA chip or extensive CPLD chip.
The programmable logic chip of described bus passenger number automatic statistics meter based on image is a large-scale F PGA chip.
The dsp chip of described bus passenger number automatic statistics meter based on image is the high-speed dsp chip.
The serial communication interface control end of described bus passenger number automatic statistics meter based on image links to each other with programmable logic chip, and the serial communication interface input end links to each other with dsp chip, and output terminal links to each other with the LED circuit.
Described bus passenger number automatic statistics meter based on image, Flame Image Process of moving on its dsp chip and recognition methods are to digitized processing after capturing at video decoding chip, and separating trip field sync signal, parity field marking signal and pixel clock signal, the gray level image that is output as 8bits is handled.At first digital picture is strengthened with improved medium filtering noise reduction, normalized and greyscale transformation; Discern the number of getting on or off the bus according to imagery exploitation hair pixel number percent, people's face pixel number percent and gradation of image average after the enhancement process then, at last result of calculation is outputed to serial communication interface, serial communication interface shows result of calculation in real time by LED.
Bus passenger number automatic statistics meter principle of work based on image is: at first, in the time of driver's manual unlocking car door, the triggering system electrification reset, enter original state (FPGA resets and program loading, DSP carry out BOOT bootstrapping, image capture module self-starting), treat after the program loading of system through a few tens of milliseconds, with program the CCD camera is set and captures a frame background image, when having the passenger to set foot on the high-rise pedal of passenger vehicle, sonac just triggers the CCD camera and captures a width of cloth passenger head portrait; Secondly, the image of being captured is isolated picture signal, row field sync signal, parity field marking signal and pixel clock signal through video decoding chip SAA7111, programmable logic device (PLD) FPGA utilizes these signals to realize the storage of image, when finishing the one-off pattern number conversion, steering logic produces the image memory address and image is temporarily stored among the SRAM, after a width of cloth integrated image collection finishes, FPGA interrupts to the DSP application, and DSP takes data away and puts into the SDRAM preparation processing that DSP expands from SRAM; DSP is the image noise reduction to collecting earlier, judge with the background frames gray average again and adopt which cover greyscale transformation criterion and image is carried out normalized, and then extract the foundation of the statistical nature (hair pixel number percent, people's face pixel number percent, image average) of image as pattern-recognition; At last, with recognition result under FPGA control through communication serial port real-time be presented at LED.
Bus passenger number automatic statistics meter based on image adopts various mature technologies, avoided difficult problems such as bigger False Rate of photoelectric detection method and direction detection effectively.The sensitivity of CCD camera, resolution, noise are controlled well.For different environment, adaptive faculty is more intense.Field programmable logic device FPGA speed is fast, integrated level is high, powerful and dirigibility good.The performance of dsp chip improves constantly, price descends continuously.
The invention has the beneficial effects as follows: utilize the sonac control CCD camera short time to take a two field picture, reduced the working temperature of CCD, and improved the signal to noise ratio (S/N ratio) of picture signal.Based on the processing of still image, than previous photoelectricity testing part that adopts and sensor data acquisition technology acuracy height; The demographics that adopts mode identification technology to carry out has made full use of the statistical property of gray level image, and the utilization simple but effective method has realized the real-time statistics of number; Utilize DSP to carry out Flame Image Process, system's fast operation can be accomplished in real time, number identification accurately, and hardware configuration is simple, and easy operating and Installation and Debugging are convenient; Because every technology that the present invention uses is all quite ripe, properties of product are stable, need not often detect maintenance; With regard to present stage more advanced both at home and abroad passenger flow statistical system, the normal period of number recognition accuracy is about 85%, is about 93% peak period, this product number accuracy of identification height, no matter be normal period or peak period, its recognition accuracy is up to 97%-98%.
Description of drawings
Fig. 1 is an overall system block diagram of the present invention.
Fig. 2 is the overall system block diagram of further embodiment of this invention.
Fig. 3 is CCD camera installation site synoptic diagram on bus.
Fig. 4 is the representative passenger's head portraits of on-the-spot five width of cloth of capturing of CCD camera.
Fig. 5 is the image before the greyscale transformation.
Fig. 6 is the image after the greyscale transformation.
Embodiment
The present invention is further described below in conjunction with drawings and Examples.
As shown in Figure 1, a kind of bus passenger number automatic statistics meter based on image comprises image acquisition, processing module and image processing algorithm.Image acquisition, processing module comprise CCD camera, video decoding chip, programmable logic chip and dsp chip; The output of CCD camera links to each other with the input of video decoding chip, and the control of video decoding chip links to each other with programmable logic chip with output terminal, and programmable logic chip links to each other with dsp chip.Write in the programmable logic chip and used the hardware description language written program, comprised the program that is used to realize video decoding chip and dsp chip exchanges data, control and buffer memory; Runs image processing and identification software on the dsp chip.The memory chip of described bus passenger number automatic statistics meter based on image links to each other with programmable logic chip, and memory chip is as the external memory storage of dsp chip; Can wipe storage chip and link to each other with dsp chip by programmable logic chip, memory image is handled and identification software, is the dsp chip loading procedure during starting.
As shown in Figure 2, a kind of bus passenger number automatic statistics meter based on image comprises image acquisition, processing module and image processing algorithm.Image acquisition, processing module comprise CCD camera, video decoding chip, programmable logic chip and dsp chip; The output of CCD camera links to each other with the input of video decoding chip, and the control of video decoding chip links to each other with programmable logic chip with output terminal, and programmable logic chip links to each other with dsp chip.Write in the programmable logic chip and used the hardware description language written program, comprised the program that is used to realize video decoding chip and dsp chip exchanges data, control and buffer memory; Runs image processing and identification software on the dsp chip.The memory chip of described bus passenger number automatic statistics meter based on image directly links to each other with dsp chip as the external memory storage of dsp chip; Can wipe storage chip and link to each other with dsp chip, memory image is handled and identification software, is the dsp chip loading procedure during starting.
, and send the result to the LED circuit and show by image acquisition, processing and identification are realized passenger number automatic statistics based on the bus passenger number automatic statistics meter of image, the algorithm that operates among the DSP has been carried out strict emulation.Its implementation procedure is as follows:
1, the realization of image acquisition
At first when passenger loading was stepped on the high-rise pedal of passenger vehicle, sonac was just controlled the black-white CCD camera current passenger's head portrait is captured; Secondly the analog image that collects is delivered to video decoding chip carries out digitized processing, with the form output of gray-scale image; Last digital picture is temporarily stored among the SRAM under the control of FPGA, waits for that DSP handles, the usefulness of identification.This module is made up of the candid photograph of head portrait, the digitizing of image, the storage of image.
1) candid photograph of head portrait: as shown in Figure 3, on the iron hurdle of bus door 4 high-rise pedals, adorn a correlation sonac 3.When car door 4 was opened, car door 4 opening signals were ordered about sensor 3 and are powered on and start working.Because passenger 2 obstruction makes a termination of sensor 3 can not receive signal, sensor 3 is passed to CCD black and white camera 1 with a switching value signal and is made it to take a complete passenger image.Passenger 2 whenever steps on the high-rise pedal of a passenger vehicle, and sensor 3 just provides a switching value signal, and CCD black and white camera 1 is just gathered a width of cloth passenger head portrait.In the time of the manually opened car door of driver 4, and connect the car door opening signal, make 3 of sonacs just effective in car door opening, with prevent to close the door 4 afterwards people stand in sonac 3 places and cause erroneous judgement.The BWC-55C that CCD black and white camera 1 selects for use Shanghai Pu Hai Electronics Co., Ltd. (ProAhead) to produce.This camera adopts the output of standard analog image, has standard external form and pilot hole, wide, the advanced technology of power range.Meet the requirement of native system fully.
2) digitizing of image: the standard analog picture signal of CCD black and white camera output enters video decoding chip SAA7111, after the A/D conversion and decoding through SAA7111, all directly draw from line synchronizing signal, field sync signal, parity field marking signal, pixel clock signal that the standard analog picture signal separates out by the pin of SAA7111, thereby saved the design of clock synchronization circuit in the past, its reliability and convenience are greatly improved.
3) storage of image: programmable logic device (PLD) FPGA is according to realizing the logic control of image storage from the various signals of video decoding chip SAA7111 output by writing the VHDL program.Under the fpga logic time sequence control, data are stored among the synchronous dynamic random access memory SDRAM of DSP expansion through FPGA inner integrated fifo fifo and SRAM, handle to wait for DSP.SRAM selects for use capacity just passable greater than the commonplace components of 4MBits.
2, the realization of Flame Image Process
At first utilize improved non-linear medium filtering that image is carried out noise reduction, can significantly improve the quality of original image; Secondly by greyscale transformation image is carried out enhancement process, increase the internal feature of part interested, and then image is carried out normalized; The gray average that extracts the number percent of image hair, people's face pixel and image at last carries out the effect that suitable value reaches pattern-recognition as feature to these three features.Image processing function is realized by DSP.
1) noise reduction: because noise spot and marginal point all are the comparatively violent pixels of grey scale change, common medium filtering can change the edge pixel gray-scale value to a certain extent when changing the noise spot gray-scale value.But noise spot nearly all is the extreme value of field pixel, and the edge is not, therefore can utilize this characteristic to limit medium filtering.Improve one's methods: when handling this pixel, see that this pixel is the very big or minimal value that filter window covers down neighborhood territory pixel, if then handle this pixel with normal medium filtering.If not, then do not handle.The method computing is simple, is convenient to realize, is showing fabulous characteristic aspect filtering Additive White Noise and the long-tail superimposed noise, and details that can well guard signal in filtering impulsive noise especially is so can keep image boundary information preferably.
2) strengthen: at first, image is carried out greyscale transformation strengthen,, choose corresponding transformation rule according to different illumination condition (fine, cloudy, night); Then, image being carried out normalized, mainly is the speed for the processing of accelerating data, guarantees little not lost of numerical value in the data simultaneously.We can take corresponding greyscale transformation rule according to the difference of image background frame average.Increase the contrast of image with greyscale transformation, influence that can removal of images light and shade inequality helps the identification of people's face and hindbrain.By day under the Qing Tian illumination condition, the image that we are captured with camera draws greyscale transformation rule as shown in table 1 after MATLAB emulation.
Table 1
| Gray-scale value before the conversion | Gray-scale value after the conversion | |
| Hair | [0，80] | 0 |
| People's face | [135，195] | 160 |
| Background | [200，255] | 255 |
3) feature extraction and pattern-recognition: at first, to 2) in the later image of greyscale transformation carry out the number statistics of hair pixel and people's face pixel, calculate their shared separately number percent; Then, the average of combining image is discerned passenger's the number of getting on or off the bus., because may wearing the influence that dark suit or the clothes close with the colour of skin can bring the statistics of hair pixel or people's face pixel, the people has two conditions to satisfy just to think accurate recognition in order to eliminate as long as we arrange three conditions.At last, a large amount of images of gathering also emulation of foundation are determined the dynamic range of above three conditions, the final rationale of dynamic range as pattern-recognition.Below just under the condition with the fine day on daytime, select five representative passenger's head portraits as shown in Figure 4, its simulation result is as shown in table 2.
Table 2
| Image ordinal number (from left to right) | The hair proportion | People's face proportion | Average |
| 1 | 7.32％ | 21.56％ | 217.61 |
| 2 | 23.89％ | 4.92％ | 199.44 |
| 3 | 16.23％ | 49.62％ | 132.47 |
| 4 | 31.45％ | 25.65％ | 118.14 |
| 5 | 43.81％ | 10.78％ | 105.29 |
4) display module as a result
Display module function as a result: at first after a two field picture is handled, under the fpga logic time sequence control, will be stored in that testing result is sent to FPGA and testing result is decoded into pulse signal in the DSP metadata cache; Then by the asynchronous communication serial ports pulse signal is passed to LED, LED demonstrates the dynamic number on the current motorbus through counter, code translator and drive processes.
5) the MATLAB simulation result shows after the greyscale transformation
Have only and gather the also image of a large amount of passenger getting on/offs of emulation, could determine the dynamic change scope of hair pixel number percent under every kind of situation, people's face pixel number percent and image average, determine the number of getting on or off the bus according to this dynamic range.The figure image intensifying adopts the greyscale transformation method that following two advantages are arranged: help the differentiation of hair, people's face and background, made things convenient for the statistics of hair pixel and people's face pixel number percent; Widened the gray scale difference value of hair, people's face and background in the image through greyscale transformation, also widened the gap of image average simultaneously, be beneficial to again with the image average and discern the number of getting on or off the bus.Below just under the condition with the fine day on daytime, select the simulation result of representative passenger's head portrait and display gray scale conversion, shown in Fig. 5,6.
The present invention is not limited to above-mentioned preferred forms, and other any identical with the present invention or akin products that anyone draws under enlightenment of the present invention all drop within protection scope of the present invention.
Claims (10)
1, a kind of bus passenger number automatic statistics meter based on image comprises image acquisition, processing module and image processing algorithm; It is characterized in that: image acquisition, processing module comprise CCD camera, video decoding chip, programmable logic chip and dsp chip; The output of CCD camera links to each other with the input of video decoding chip, and the control of video decoding chip links to each other with programmable logic chip with output terminal, and programmable logic chip links to each other with dsp chip; Write in the programmable logic chip and used the hardware description language written program, comprised the program that is used to realize video decoding chip and dsp chip exchanges data, control and buffer memory; Runs image processing and identification software on the dsp chip.
2, the bus passenger number automatic statistics meter based on image according to claim 1, it is characterized in that: memory chip links to each other with programmable logic chip, and memory chip is as the external memory storage of dsp chip; Can wipe storage chip and link to each other with dsp chip by programmable logic chip, memory image is handled and identification software, is the dsp chip loading procedure during starting.
3, the bus passenger number automatic statistics meter based on image according to claim 1 is characterized in that: memory chip directly links to each other with dsp chip as the external memory storage of dsp chip; Can wipe storage chip and link to each other with dsp chip, memory image is handled and identification software, is the dsp chip loading procedure during starting.
4, according to claim 2 or 3 described bus passenger number automatic statistics meters based on image, it is characterized in that: described memory chip is SRAM, SDRAM or DDRAM; The described storage chip of wiping is FLASH, EPROM or EEPROM.
5, according to claim 2 or 3 described bus passenger number automatic statistics meters based on image, it is characterized in that: described memory chip is SRAM; The described storage chip of wiping is FLASH.
6, the bus passenger number automatic statistics meter based on image according to claim 1 is characterized in that: described programmable logic chip is large-scale F PGA chip or extensive CPLD chip.
7, according to claim 1 or 6 described bus passenger number automatic statistics meters based on image, it is characterized in that: described programmable logic chip is a large-scale F PGA chip.
8, the bus passenger number automatic statistics meter based on image according to claim 1 is characterized in that: described dsp chip is the high-speed dsp chip.
9, the bus passenger number automatic statistics meter based on image according to claim 1, it is characterized in that: described serial communication interface control end links to each other with programmable logic chip, the serial communication interface input end links to each other with dsp chip, and output terminal links to each other with the LED circuit.
10, the bus passenger number automatic statistics meter based on image according to claim 1, it is characterized in that: Flame Image Process of moving on the described dsp chip and recognition methods are to digitized processing after capturing at video decoding chip, and separating trip field sync signal, parity field marking signal and pixel clock signal, the gray level image that is output as 8 bits is handled; At first digital picture is strengthened with improved medium filtering noise reduction, normalized and greyscale transformation; Discern the number of getting on or off the bus according to imagery exploitation hair pixel number percent, people's face pixel number percent and gradation of image average after the enhancement process then, at last result of calculation is outputed to serial communication interface, serial communication interface shows result of calculation in real time by LED.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100005715A CN100530221C (en) | 2007-01-15 | 2007-01-15 | Image-based bus passenger number automatic statistics meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100005715A CN100530221C (en) | 2007-01-15 | 2007-01-15 | Image-based bus passenger number automatic statistics meter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101025790A true CN101025790A (en) | 2007-08-29 |
| CN100530221C CN100530221C (en) | 2009-08-19 |
Family
ID=38744072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007100005715A Expired - Fee Related CN100530221C (en) | 2007-01-15 | 2007-01-15 | Image-based bus passenger number automatic statistics meter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100530221C (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201895B (en) * | 2007-09-20 | 2010-06-02 | 北京清大维森科技有限责任公司 | Built-in human face recognizing monitor and detecting method thereof |
| CN101916428A (en) * | 2010-08-18 | 2010-12-15 | 中国科学院光电技术研究所 | Image processing device for image data |
| CN101673423B (en) * | 2009-08-26 | 2011-07-20 | 深圳市飞瑞斯科技有限公司 | Bus passenger number statistical system capable of analyzing by means of video |
| CN103475799A (en) * | 2013-09-15 | 2013-12-25 | 贵州大学 | Real-time detection device for fruit tree agronomic parameters |
| CN103714698A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | Bus passenger flow statistics system based on distance images |
| CN104859448A (en) * | 2015-04-16 | 2015-08-26 | 深圳市华宝电子科技有限公司 | Passenger car overload monitoring system and method |
| CN106295633A (en) * | 2016-08-09 | 2017-01-04 | 成都联众智科技有限公司 | A kind of Optoelectronic hybrid pattern recognition system |
| CN106875725A (en) * | 2017-04-05 | 2017-06-20 | 合肥酷睿网络科技有限公司 | A kind of bus scheduling system |
| CN107004133A (en) * | 2017-02-16 | 2017-08-01 | 深圳市锐明技术股份有限公司 | Patronage statistical method and device in a kind of vehicle |
| WO2017206152A1 (en) * | 2016-06-02 | 2017-12-07 | 深圳市锐明技术股份有限公司 | Method and device for counting vehicle passengers |
| CN108229452A (en) * | 2018-03-20 | 2018-06-29 | 东北大学 | People counting device and method based on deep neural network and dsp chip |
| CN108345878A (en) * | 2018-04-16 | 2018-07-31 | 泰华智慧产业集团股份有限公司 | Public transport passenger flow quantity monitoring method based on video and system |
| CN110231295A (en) * | 2019-06-28 | 2019-09-13 | 中国计量大学 | A kind of image acquisition and processing system of portable colloidal gold CCD readout instrument |
| CN112255642A (en) * | 2020-10-15 | 2021-01-22 | 安徽富煌科技股份有限公司 | Video passenger flow device based on laser radar technology |
-
2007
- 2007-01-15 CN CNB2007100005715A patent/CN100530221C/en not_active Expired - Fee Related
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201895B (en) * | 2007-09-20 | 2010-06-02 | 北京清大维森科技有限责任公司 | Built-in human face recognizing monitor and detecting method thereof |
| CN101673423B (en) * | 2009-08-26 | 2011-07-20 | 深圳市飞瑞斯科技有限公司 | Bus passenger number statistical system capable of analyzing by means of video |
| CN101916428A (en) * | 2010-08-18 | 2010-12-15 | 中国科学院光电技术研究所 | Image processing device for image data |
| CN103475799A (en) * | 2013-09-15 | 2013-12-25 | 贵州大学 | Real-time detection device for fruit tree agronomic parameters |
| CN103714698A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | Bus passenger flow statistics system based on distance images |
| CN103714698B (en) * | 2013-12-26 | 2016-09-21 | 苏州清研微视电子科技有限公司 | Public transit vehicle passenger flow volume statistical system based on range image and method |
| CN104859448A (en) * | 2015-04-16 | 2015-08-26 | 深圳市华宝电子科技有限公司 | Passenger car overload monitoring system and method |
| WO2017206152A1 (en) * | 2016-06-02 | 2017-12-07 | 深圳市锐明技术股份有限公司 | Method and device for counting vehicle passengers |
| CN106295633A (en) * | 2016-08-09 | 2017-01-04 | 成都联众智科技有限公司 | A kind of Optoelectronic hybrid pattern recognition system |
| WO2018148896A1 (en) * | 2017-02-16 | 2018-08-23 | 深圳市锐明技术股份有限公司 | Method and device for counting number of passengers in vehicle |
| CN107004133A (en) * | 2017-02-16 | 2017-08-01 | 深圳市锐明技术股份有限公司 | Patronage statistical method and device in a kind of vehicle |
| CN106875725A (en) * | 2017-04-05 | 2017-06-20 | 合肥酷睿网络科技有限公司 | A kind of bus scheduling system |
| CN108229452A (en) * | 2018-03-20 | 2018-06-29 | 东北大学 | People counting device and method based on deep neural network and dsp chip |
| CN108229452B (en) * | 2018-03-20 | 2024-05-03 | 东北大学 | People counting device and method based on deep neural network and DSP chip |
| CN108345878A (en) * | 2018-04-16 | 2018-07-31 | 泰华智慧产业集团股份有限公司 | Public transport passenger flow quantity monitoring method based on video and system |
| CN108345878B (en) * | 2018-04-16 | 2020-03-24 | 泰华智慧产业集团股份有限公司 | Public transport passenger flow monitoring method and system based on video |
| CN110231295A (en) * | 2019-06-28 | 2019-09-13 | 中国计量大学 | A kind of image acquisition and processing system of portable colloidal gold CCD readout instrument |
| CN112255642A (en) * | 2020-10-15 | 2021-01-22 | 安徽富煌科技股份有限公司 | Video passenger flow device based on laser radar technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100530221C (en) | 2009-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100530221C (en) | Image-based bus passenger number automatic statistics meter | |
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| CN103968845B (en) | A kind of DSP Yu FPGA parallel multi-mode star image processing method for star sensor | |
| CN101409825B (en) | Nighttime vision monitoring method based on information fusion | |
| CN109640007A (en) | Artificial intelligence image sensing apparatus | |
| CN104598897A (en) | Visual sensor, image processing method and device and visual interactive device | |
| CN109409368A (en) | Mine leather belt is vertical to tear detection device and detection method | |
| CN114999002B (en) | Behavior recognition method fusing human body posture information | |
| CN205721986U (en) | A kind of cable visual defects detection and character recognition device | |
| CN111830039A (en) | Intelligent product quality detection method and device | |
| CN101763513A (en) | Foreground extraction method for removing light effect | |
| CN202872972U (en) | Image monitoring and processing device | |
| CN100367281C (en) | Pulsed laser spot software synchronization acquisition method | |
| CN102609729B (en) | Method and system for recognizing faces shot by multiple cameras | |
| CN103679917A (en) | High-speed banknote serial number extraction and identification system based on FPGA (field programmable gate array) and implementation method thereof | |
| CN205193833U (en) | Image acquisition circuit and including biological equipment of this circuit | |
| CN105138971A (en) | Fingerprint acquisition method and apparatus | |
| CN115426442A (en) | Optical information collector and method | |
| Yan et al. | Research on moving target tracking system based on FPGA | |
| CN202261623U (en) | Partial image recognition replacing system of motion body | |
| CN105426849A (en) | Multi-modal biological recognition device and image acquisition method thereof | |
| CN113744189A (en) | Self-adaptive threshold edge detection system and method based on FPGA | |
| CN104952143A (en) | Color change detection method and color change detection system for red waterlines of bill images | |
| CN105472336B (en) | A kind of low power image compression module | |
| CN205621024U (en) | Face detection identification system based on embedded platform |
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 | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090819 Termination date: 20100222 |