CN103383266A - Vehicle-mounted artificial intelligence system based on dynamic image recognition - Google Patents
Vehicle-mounted artificial intelligence system based on dynamic image recognition Download PDFInfo
- Publication number
- CN103383266A CN103383266A CN2013103184888A CN201310318488A CN103383266A CN 103383266 A CN103383266 A CN 103383266A CN 2013103184888 A CN2013103184888 A CN 2013103184888A CN 201310318488 A CN201310318488 A CN 201310318488A CN 103383266 A CN103383266 A CN 103383266A
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- artificial intelligence
- intelligence system
- intelligent vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
A vehicle-mounted artificial intelligence system based on dynamic image recognition comprises an STM32 microprocessor, a liquid crystal display, a motor driving module, a power source module and a power source management module, wherein the STM32 microprocessor, the liquid crystal display, the motor driving module, the power source module and the power source management module are carried by an intelligent vehicle. The motor driving module is supplied by the power source module, current output by the power source module is converted by the power source management module and then supplied to power utilization units, the STM32 microprocessor serves as a central processor to control operation of the artificial intelligence system, an image acquisition module for collecting image information is arranged on a head of the intelligent vehicle, a gesture data acquisition module for collecting swinging amplitude of a body of the intelligent vehicle is arranged in the middle of the vehicle body of the intelligent vehicle, the STM32 microprocessor is connected with the power source management module, the motor driving module, the liquid crystal display, the image acquisition module and the gesture data acquisition module respectively, and the image acquisition module is further connected with the liquid crystal display. The vehicle-mounted artificial intelligence system can perform image acquisition, transmission, processing and control on places the intelligent vehicle passes, so that road condition information can be obvious.
Description
Technical field
The present invention relates to a kind of artificial intelligence system, relate to specifically a kind of vehicle-mounted artificial intelligence system based on dynamic image identification.
Background technology
At present, image recognition technology has been widely used in every field, but in unmanned field, it or a technology that haves much room for improvement, not only to improve the conventional images recognition technology, also will the components work relevant to other, finally reach vehicle independent and intelligent, can provide a motion platform for the rugged surroundings that the people that should not drive or people do not arrive, replace people to complete the relevant work that should not operate.
Summary of the invention
The present invention provides a kind of vehicle-mounted artificial intelligence system based on dynamic image identification in order to solve above-mentioned technical matters, and its volume is small and exquisite, flexible, can be used for different applications.The present invention can carry out image acquisition, transmission, processing and control to the place of intelligent vehicle process, makes traffic information very clear.
the technical solution adopted in the present invention is: a kind of vehicle-mounted artificial intelligence system based on dynamic image identification, comprise the STM32 microprocessor that carries on intelligent vehicle, LCDs, motor drive module, power module and power management module, described motor drive module is powered by power module, the output of power module is through each power unit power supply of the backward described artificial intelligence system of power management module conversion, described STM32 microprocessor is controlled the operation of described artificial intelligence system as central processing unit, the headstock of described intelligent vehicle is provided with for the image capture module that gathers image information, this image capture module comprises camera and with the imageing sensor of buffer memory, imageing sensor is by the camera collection image and be stored in buffer memory, the sequential of buffer memory is controlled by the STM32 microprocessor, STM32 microprocessor and LCDs reading images from buffer memory, be provided with in the middle part of the vehicle body of described intelligent vehicle for the attitude data acquisition module that gathers the intelligent vehicle car body amplitude of oscillation, described STM32 microprocessor respectively with power management module, motor drive module, LCDs, image capture module is connected with the attitude data acquisition module, , the image recognition condition of road surface that the STM32 microprocessor gathers according to image capture module, and the amplitude of oscillation of the intelligent vehicle that calculates according to the attitude data acquisition module, control the operation of intelligent vehicle drive motor by controlling motor drive module.
Described STM32 microprocessor adopts the STM32F103VET6 embedded control chip based on the Cortex-M3 kernel.
Described image capture module comprises camera and imageing sensor, and described imageing sensor adopts the OV7670 module with the AL422B high-speed cache.
Described attitude data acquisition module is integrated with 3 axle MEMS gyroscopes, 3 axle mems accelerometers, and an extendible digital moving processor DMP.
Described power management module comprises the conversion chip of MC78M05CT.
Beneficial effect of the present invention: the present invention is simple in structure, has image collecting function, image identification function and car body attitude acquisition function.By the image that collects is carried out data analysis, account for respectively the ratio of four quadrants of LCDs according to the black and white mark, tell the path situation, then dividing gas-distributing motor to do corresponding action adjusts rotating speed or turns to, simultaneously in order to improve reliability, attitude data by the attitude sensor collection carries out closed-loop control to motor, make dolly tracking stably, the present invention can realize unpiloted correlation function on more complicated road, simultaneously also can be applied to some factory floors, realize the associated uses such as intelligent loading-unloading vehicle loading and unloading industrial materials.
Description of drawings
Fig. 1 is structural framing figure of the present invention.
Embodiment
as shown in the figure, a kind of vehicle-mounted artificial intelligence system based on dynamic image identification, comprise the STM32 microprocessor that carries on intelligent vehicle, LCDs, motor drive module, power module and power management module, described motor drive module is powered by power module, the output of power module is through each power unit power supply of the backward described artificial intelligence system of power management module conversion, described STM32 microprocessor is controlled the operation of described artificial intelligence system as central processing unit, the headstock of described intelligent vehicle is provided with for the image capture module that gathers image information, this image capture module comprises camera and with the imageing sensor of buffer memory, imageing sensor is by the camera collection image and be stored in buffer memory, the sequential of buffer memory is controlled by the STM32 microprocessor, STM32 microprocessor and LCDs reading images from buffer memory, be provided with in the middle part of the vehicle body of described intelligent vehicle for the attitude data acquisition module that gathers the intelligent vehicle car body amplitude of oscillation, described STM32 microprocessor respectively with power management module, motor drive module, LCDs, image capture module is connected with the attitude data acquisition module, , the image recognition condition of road surface that the STM32 microprocessor gathers according to image capture module, and the amplitude of oscillation of the intelligent vehicle that calculates according to the attitude data acquisition module, control the operation of intelligent vehicle drive motor by controlling motor drive module.
Described STM32 microprocessor adopts the STM32F103VET6 embedded control chip based on the Cortex-M3 kernel, described image capture module comprises camera and imageing sensor, described imageing sensor adopts the OV7670 module with the AL422B high-speed cache, described attitude data acquisition module is integrated with 3 axle MEMS gyroscopes, 3 axle mems accelerometers, and an extendible digital moving processor DMP, described power management module comprises the conversion chip of MC78M05CT.
STM32 microprocessor of the present invention is as central processing unit, power module, motor drive module, image capture module, attitude data acquisition module have been extended out, the driving voltage of each module is different, therefore adopt the conversion chip as the MC78M05CT of power management module to obtain DC voltage; Control driving circuit by the STM32 microprocessor, make it to be operated in the adjustable on off state of dutycycle, thereby realize the accurate adjustment to motor speed; System gathers the VGA view data according to image capture module, is controlled the center of identification road by the STM32STM32 microprocessor, can also obtain the direction of runway simultaneously, the information such as the curvature of runway; Move stably in order to ensure dolly, system adopts attitude data acquisition module MPU-6050 to determine the attitude of trolley travelling, system's attitude data acquisition module is extrapolated the amplitude of oscillation of intelligent vehicle by the Eulerian angle of computational intelligence car vehicle body, then the STM32 central processing unit judges that according to the amplitude of oscillation of intelligent vehicle intelligent vehicle is on flat road or on bump course.The STM32 main control chip is realized control to intelligent vehicle by pid control algorithm.
Gather image information by image capture module in the present invention, image capture module adopts the OV7670 module with the AL422B high-speed cache, and this module-external is reserved each pin interface of OV7670 sensor, and convenience is connected with external circuit.the view data of OV7670 output first is temporary in AL422B, then read by the STM32 processor, the data output that this shows AL422B is the input of STM32 processor, the data input of AL422B is the output of OV7670, utilize the fifo chip AL422B that the OV7670 module carries to store the QVGA view data for reducing STM32 memory usage and system power dissipation the present invention temporarily, data in liquid crystal display screen needn't obtain from the STM32 internal memory again, the data that only need to obtain storage from FIFO show, greatly reduce the STM32 memory usage, attitude data acquisition module circuit adopts the MPU-6050 chip as system's attitude data collecting unit, by the power module pin powered of drawing.When circuit layout, can not produce the components and parts of mechanical shock and stress around sensor just like button and so on, leave a blank in the zone within 6mm on every side.
The present invention in the course of the work, STM32 is as the central processing unit of whole system, vehicle-mounted STM32 disposal system is by the camera collection image information, and data are carried out Treatment Analysis, the image data transmission after black and white is processed is to the liquid crystal display screen display, then by the black white image data analysis to collecting, analyze the conventional road conditions such as straight way bend, adopt the method for four-quadrant dutycycle uniting and adjustment herein, can reduce calculated amount like this, again can practical function.Judge the path smoothness by the attitude data acquisition module, indirectly retrain the condition that image-recognizing method is realized, reduce the error rate of identification.The STM32 microprocessor carries out to the data that image capture module and attitude data acquisition module obtain speed and the attitude data that Algorithm Analysis obtains intelligent vehicle, dividing simultaneously gas-distributing motor to do corresponding action adjusts rotating speed or turns to, and motor is carried out closed-loop control, make dolly tracking stably.Described image capture module is cmos image sensor, is positioned at the headstock of intelligent vehicle, is used for gathering image information; Described image capture module is provided with TFTLCD liquid crystal display display part, is used for the data that gather are shown; Described attitude data acquisition module MPU-6050 is positioned at the vehicle body middle part of intelligent vehicle, is used for determining the trolley travelling attitude.
The present invention mainly comprises image collecting function, image identification function, security function, dolly carries out image acquisition and image recognition under normal circumstances, when meeting emergency case, when running into situation about the degree of jolting higher road surface even will overturn as dolly, because adopted attitude sensor to gather attitude data, so, in the case, take to continue reduction of speed, or even the burst treating method of stopping, avoid occuring the phenomenon of vehicle damage.
The present invention adopts STM32F103 as central processing unit, and this chip has 16 PWM outputs of 30 passages, RTC clock, 2 high speed SPI, 2 IIC, 5 serial ports, self-carried USB and CAN interface.SRAM with 512K Flash and 64K, this chip functions is powerful, also has very large upgrading space simultaneously, the TFT color screen is as the human-machine interaction data interface, OV7670S camera and MPU-6050 attitude sensor, the collaborative work of L298 motor drive module realizes the function of intelligent vehicle identification path tracking jointly.OV7670 camera and MPU-6050 attitude sensor all carry FIFO, have reduced the requirement to the processor processing speed, can save overall power, and the contact processor constantly is circulated in the burden of capture program.
The present invention is simple in structure, has image collecting function, image identification function and car body attitude acquisition function.By the image that collects is carried out data analysis, account for respectively the ratio of four quadrants of LCDs according to the black and white mark, tell the path situation, then dividing gas-distributing motor to do corresponding action adjusts rotating speed or turns to, simultaneously in order to improve reliability, attitude data by the attitude sensor collection carries out closed-loop control to motor, make dolly tracking stably, the present invention can realize unpiloted correlation function on more complicated road, simultaneously also can be applied to some factory floors, realize the associated uses such as intelligent loading-unloading vehicle loading and unloading industrial materials.
Claims (5)
1. vehicle-mounted artificial intelligence system based on dynamic image identification, comprise the STM32 microprocessor that carries on intelligent vehicle, LCDs, motor drive module, power module and power management module, described motor drive module is powered by power module, the output of power module is through each power unit power supply of the backward described artificial intelligence system of power management module conversion, described STM32 microprocessor is controlled the operation of described artificial intelligence system as central processing unit, it is characterized in that: the headstock of described intelligent vehicle is provided with for the image capture module that gathers image information, this image capture module comprises camera and with the imageing sensor of buffer memory, imageing sensor is by the camera collection image and be stored in buffer memory, the sequential of buffer memory is controlled by the STM32 microprocessor, STM32 microprocessor and LCDs reading images from buffer memory, be provided with in the middle part of the vehicle body of described intelligent vehicle for the attitude data acquisition module that gathers the intelligent vehicle car body amplitude of oscillation, described STM32 microprocessor respectively with power management module, motor drive module, LCDs, image capture module is connected with the attitude data acquisition module, the image recognition condition of road surface that the STM32 microprocessor gathers according to image capture module, and the amplitude of oscillation of the intelligent vehicle that calculates according to the attitude data acquisition module, control the operation of intelligent vehicle drive motor by controlling motor drive module.
2. a kind of vehicle-mounted artificial intelligence system based on dynamic image identification as claimed in claim 1, it is characterized in that: described STM32 microprocessor adopts the STM32F103VET6 embedded control chip based on the Cortex-M3 kernel.
3. a kind of vehicle-mounted artificial intelligence system based on dynamic image identification as claimed in claim 1, it is characterized in that: described image capture module comprises camera and imageing sensor, and described imageing sensor adopts the OV7670 module with the AL422B high-speed cache.
4. a kind of vehicle-mounted artificial intelligence system based on dynamic image identification as claimed in claim 1, it is characterized in that: described attitude data acquisition module is integrated with 3 axle MEMS gyroscopes, 3 axle mems accelerometers, and an extendible digital moving processor DMP.
5. a kind of vehicle-mounted artificial intelligence system based on dynamic image identification as claimed in claim 1, it is characterized in that: described power management module comprises the conversion chip of MC78M05CT.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103184888A CN103383266A (en) | 2013-07-26 | 2013-07-26 | Vehicle-mounted artificial intelligence system based on dynamic image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013103184888A CN103383266A (en) | 2013-07-26 | 2013-07-26 | Vehicle-mounted artificial intelligence system based on dynamic image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103383266A true CN103383266A (en) | 2013-11-06 |
Family
ID=49491121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013103184888A Pending CN103383266A (en) | 2013-07-26 | 2013-07-26 | Vehicle-mounted artificial intelligence system based on dynamic image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103383266A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199460A (en) * | 2014-08-29 | 2014-12-10 | 河南科技大学 | Intelligent four-rotor aircraft reconnoitering system based on image recognition and tracking |
| CN108279680A (en) * | 2018-03-13 | 2018-07-13 | 河北工业大学 | A kind of agricultural machinery collecting cart intelligence system for tracking based on GPS and visual identity |
| CN109522823A (en) * | 2018-10-30 | 2019-03-26 | 杭州鸿泉物联网技术股份有限公司 | A kind of image analysis apparatus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005119099A1 (en) * | 2004-05-21 | 2005-12-15 | Renault S.A.S. | Method for downshifting on braking to first gear |
| CN102944224A (en) * | 2012-11-09 | 2013-02-27 | 大连理工大学 | Automatic environmental perception system for remotely piloted vehicle and work method for automatic environmental perception system |
| CN202815590U (en) * | 2012-07-30 | 2013-03-20 | 中国航天科工集团第三研究院第八三五七研究所 | Control system for mini self-driving unmanned vehicle |
| CN103204161A (en) * | 2013-04-11 | 2013-07-17 | 浙江吉利汽车研究院有限公司杭州分公司 | Automatic brake system and method for automobile in unmanned state |
-
2013
- 2013-07-26 CN CN2013103184888A patent/CN103383266A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005119099A1 (en) * | 2004-05-21 | 2005-12-15 | Renault S.A.S. | Method for downshifting on braking to first gear |
| CN202815590U (en) * | 2012-07-30 | 2013-03-20 | 中国航天科工集团第三研究院第八三五七研究所 | Control system for mini self-driving unmanned vehicle |
| CN102944224A (en) * | 2012-11-09 | 2013-02-27 | 大连理工大学 | Automatic environmental perception system for remotely piloted vehicle and work method for automatic environmental perception system |
| CN103204161A (en) * | 2013-04-11 | 2013-07-17 | 浙江吉利汽车研究院有限公司杭州分公司 | Automatic brake system and method for automobile in unmanned state |
Non-Patent Citations (1)
| Title |
|---|
| 王祥好: "模糊PID控制算法在智能小车中的研究与应用", 《中国学位论文全文数据库》, 19 October 2009 (2009-10-19) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199460A (en) * | 2014-08-29 | 2014-12-10 | 河南科技大学 | Intelligent four-rotor aircraft reconnoitering system based on image recognition and tracking |
| CN108279680A (en) * | 2018-03-13 | 2018-07-13 | 河北工业大学 | A kind of agricultural machinery collecting cart intelligence system for tracking based on GPS and visual identity |
| CN109522823A (en) * | 2018-10-30 | 2019-03-26 | 杭州鸿泉物联网技术股份有限公司 | A kind of image analysis apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200363534A1 (en) | Imaging device and electronic device | |
| CN104159078B (en) | One kind point paints formula standalone module dynamic trajectory rear camera reversing aid system and its method | |
| CN203443592U (en) | Vehicle-mounted artificial intelligence system based on dynamic image identification | |
| CN206162197U (en) | Two -wheeled self -balancing bluetooth intelligent vehicle | |
| CN104175308A (en) | Self-service robot | |
| CN103383266A (en) | Vehicle-mounted artificial intelligence system based on dynamic image recognition | |
| CN105643590B (en) | A kind of wheeled mobile robot and its operating method of gesture control | |
| CN103544714A (en) | Visual tracking system and method based on high-speed image sensor | |
| CN106375669A (en) | Image stabilization method and apparatus, and drone | |
| CN103914071A (en) | Visual navigation path recognition system of grain combine harvester | |
| CN108490931B (en) | Intelligent vehicle driving control system and method based on improved Sobel operator | |
| CN205068166U (en) | But remote control two -wheeled is upright from balancing trolley | |
| Gomez et al. | Wearable, energy-opportunistic vision sensing for walking speed estimation | |
| CN203472854U (en) | Video monitoring trolley | |
| CN106708029A (en) | Intelligent inspection trolley system with low cost | |
| CN209070376U (en) | A kind of holder tracing system based on image recognition | |
| CN207807743U (en) | A kind of spherical shape self-balancing is looked for something robot | |
| CN204209679U (en) | Autonomous service robot | |
| CN204236612U (en) | Two crawler belt intelligence based on controlled in wireless search and rescue car | |
| CN210258861U (en) | Unmanned aerial vehicle takes photo by plane based on ARM and FPGA | |
| JP5674716B2 (en) | Vehicle detection device | |
| Kudo et al. | A platform on all-programmable SoC for micro autonomous robots | |
| Peng | Design and Implementation of Intelligent Car based on Machine Vision | |
| CN207541499U (en) | Intelligent track telecar based on VR | |
| CN207106493U (en) | A kind of automobile track based on imaging identification technology keeps accessory system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131106 |
|
| RJ01 | Rejection of invention patent application after publication |