CN112462788A - Balance car automatic following implementation method and system based on mechanical vision and AI technology - Google Patents
Balance car automatic following implementation method and system based on mechanical vision and AI technology Download PDFInfo
- Publication number
- CN112462788A CN112462788A CN202011469211.1A CN202011469211A CN112462788A CN 112462788 A CN112462788 A CN 112462788A CN 202011469211 A CN202011469211 A CN 202011469211A CN 112462788 A CN112462788 A CN 112462788A
- Authority
- CN
- China
- Prior art keywords
- balance car
- vision
- platform
- module
- owner
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000009471 action Effects 0.000 claims abstract description 15
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62K—CYCLES; CYCLE FRAMES; CYCLE STEERING DEVICES; RIDER-OPERATED TERMINAL CONTROLS SPECIALLY ADAPTED FOR CYCLES; CYCLE AXLE SUSPENSIONS; CYCLE SIDE-CARS, FORECARS, OR THE LIKE
- B62K11/00—Motorcycles, engine-assisted cycles or motor scooters with one or two wheels
- B62K11/007—Automatic balancing machines with single main ground engaging wheel or coaxial wheels supporting a rider
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Human Computer Interaction (AREA)
- Automation & Control Theory (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Mechanical Engineering (AREA)
- Regulating Braking Force (AREA)
Abstract
The invention discloses a balance car automatic following implementation method and system based on mechanical vision and AI technology, belonging to the technical field of mechanical vision and AI automatic identification, aiming at solving the technical problem of how to realize the identification of a balance car owner, further realizing the automatic following of the balance car to the car owner, lightening the burden of carrying the balance car for ladies and children, and simultaneously improving the safety, and the technical scheme is as follows: the method includes the steps that a GPU offline training platform is carried through a mechanical vision technology, AI automatic identification is achieved, and then a balance car braking system is driven to achieve automatic following of a balance car. The system comprises a video acquisition module, a computing platform, an open-view machine vision platform and a braking module, wherein the video acquisition module acquires the body form and action habit of a vehicle owner in real time and uploads the body form and action habit to the computing platform; the computing platform stores the body type and action habit of the vehicle owner as vehicle owner sample data and operates a spacious machine vision platform; and comparing the sample data of the vehicle owner with the real-time data by the aid of the spacious-vision machine vision platform.
Description
Technical Field
The invention relates to the technical field of mechanical vision and automatic AI identification, in particular to a balance car automatic following implementation method and system based on the mechanical vision and AI technology.
Background
Along with the popularization of internet of things, people's life style has had the change of covering the ground, more and more smart machine enters into people's life, in recent years, a neotype instrument balance car of riding instead of walk takes place, the balance car is for everybody closely to go on a journey, the garden sightseeing, it facilitates to visit activities such as market, but balance car weight is great, can only carry by hand after getting off, to ms, children become the burden on the contrary, there is the safety risk simultaneously, how to realize the discernment to balance car owner, and then realize that the balance car follows the automation of car owner, alleviate the burden of carrying the balance car of ms and children, it is the present urgent technical problem who treats solution to improve the security simultaneously.
Disclosure of Invention
The invention provides a balance car automatic following implementation method and system based on mechanical vision and AI technology, and aims to solve the problems that how to realize the identification of a balance car owner, further realize the automatic following of the balance car to the car owner, reduce the load of carrying the balance car for ladies and children and improve the safety.
The technical task of the invention is realized in the following way, the balance car automatic following realization method based on the mechanical vision and AI technology is characterized in that the method carries a GPU offline training platform through the mechanical vision technology to realize AI automatic identification, and further drives a balance car braking system to realize the automatic following of the balance car; the method comprises the following specific steps:
the video acquisition module acquires vehicle owner sample data, performs sample characteristic extraction on the vehicle owner sample data to obtain and store a sample characteristic value, and continuously updates the sample characteristic value in the subsequent training process;
the method comprises the following steps that a balance car is started in a following mode, a video acquisition module acquires real-time data of a car owner, and characteristic values of the real-time data are extracted to obtain characteristic values of the real-time data;
comparing the real-time data characteristic value with the sample characteristic value, and judging whether the real-time data characteristic value and the sample characteristic value accord with the following conditions:
if not, the video acquisition module acquires real-time data again;
if the brake command is in accordance with the running track, calculating the running track through the calculation platform, and outputting a brake command to the brake module according to the running track;
the braking module controls the balance car to run according to the track, and then the following mode of the balance car is achieved.
Preferably, the computing platform is a master control platform and is used for operating a vision platform of the spacious machine and a braking system of the hole balance car, collecting video information in real time, completing sample comparison and computing the running track of the car owner.
Preferably, the computing platform adopts an kylin ARM8 embedded CPU, and carries an NVIDIA GPU module.
Preferably, the vision acquisition module adopts a loose 720P high-definition digital camera module.
Preferably, the brake module adopts a loose digital brake system.
Preferably, the owner sample data includes body type and action habit of the owner.
A balance car automatic following system based on mechanical vision and AI technology comprises a video acquisition module, a computing platform, an open-view machine vision platform and a brake module, wherein the video acquisition module acquires the body type and action habit of a car owner in real time and uploads the body type and action habit to the computing platform; the computing platform stores the body type and action habit of the vehicle owner as vehicle owner sample data and operates a spacious machine vision platform; the spacious machine vision platform compares car owner sample data with real-time data, and then judges car owner's orbit to issue the braking command and give the braking module, drive braking module is according to the orbit and is patrolled, and then realizes the automation of balance car and follows.
Preferably, the computing platform adopts an kylin ARM8 embedded CPU, and carries an NVIDIA GPU module.
Preferably, the vision acquisition module adopts a loose 720P high-definition digital camera module.
Preferably, the brake module employs a loose digital brake system.
The balance car automatic following implementation method and system based on the mechanical vision and AI technology have the following advantages: according to the invention, a GPU offline training platform is carried by a mechanical vision technology, so that AI automatic identification is realized, namely, the balance car owner identification is realized, and further, a balance car braking system is driven, so that the balance car can automatically follow, the carrying pressure of ladies and children is reduced, and the safety is improved.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart diagram of a balance car automatic following implementation method based on mechanical vision and AI technology;
fig. 2 is a block diagram showing the structure of an automatic following system of a balance car in the machine vision and AI technologies.
Detailed Description
The method and system for realizing automatic following of the balance car based on the mechanical vision and AI technology are described in detail below with reference to the drawings and specific embodiments of the specification.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description. And are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1:
as shown in the attached drawing 1, the balance car automatic following implementation method based on the mechanical vision and the AI technology of the invention is to carry a GPU offline training platform through the mechanical vision technology to realize AI automatic identification, and further drive a balance car braking system to realize the automatic following of the balance car; the method comprises the following specific steps:
s1, the video acquisition module acquires owner sample data, performs sample feature extraction on the owner sample data to obtain and store a sample feature value, and continuously updates the sample feature value in the subsequent training process;
s2, starting a following mode of the balance car, collecting real-time data of a car owner by a video collection module, and extracting characteristic values of the real-time data to obtain characteristic values of the real-time data;
s3, comparing the real-time data characteristic value with the sample characteristic value, and judging whether the real-time data characteristic value and the sample characteristic value meet the following conditions:
if not, jumping to step S1;
if yes, executing step S4;
s4, calculating a running track through the calculation platform, and outputting a braking command to the braking module according to the running track;
and S5, controlling the balance car to run according to the track by the braking module, and further realizing the balance car following mode.
The owner sample data in this embodiment includes the body type and action habit of the owner.
The computing platform is a master control platform in the embodiment and is used for operating a vision platform of a spacious machine and a braking system of the porn balance car, collecting video information in real time, completing sample comparison and computing the running track of a car owner. Wherein, spacious sight machine vision platform, spacious sight be domestic biggest AI training platform especially machine vision field, what this chooseed for use is spacious sight lightweight off-line training platform.
In the embodiment, the computing platform adopts an kylin ARM8 embedded CPU, carries an NVIDIA GPU module, and can also use other platforms with the same specification.
The vision acquisition module in this embodiment adopts loose 720P high definition digital camera module, also can use other with specification products.
In this embodiment, the brake module adopts a loose digital brake system (digital controllable dc brushless motor).
Example 2:
as shown in fig. 2, the balance car automatic following system based on the mechanical vision and AI technology comprises a video acquisition module, a computing platform, an open-view machine vision platform and a braking module, wherein the video acquisition module acquires the body type and action habit of a car owner in real time and uploads the body type and action habit to the computing platform; the computing platform stores the body type and action habit of the vehicle owner as vehicle owner sample data and operates a spacious machine vision platform; the spacious machine vision platform compares car owner sample data with real-time data, and then judges car owner's orbit to issue the braking command and give the braking module, drive braking module is according to the orbit and is patrolled, and then realizes the automation of balance car and follows.
The computing platform adopts an kylin ARM8 embedded CPU, and carries an NVIDIA GPU module. The vision acquisition module adopts a loose 720P high-definition digital camera module. The brake module adopts a loose digital brake system.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A balance car automatic following implementation method based on mechanical vision and AI technology is characterized in that the method is used for carrying a GPU offline training platform through the mechanical vision technology to realize AI automatic identification, and further driving a balance car braking system to realize automatic following of a balance car; the method comprises the following specific steps:
the video acquisition module acquires vehicle owner sample data, performs sample characteristic extraction on the vehicle owner sample data to obtain and store a sample characteristic value, and continuously updates the sample characteristic value in the subsequent training process;
the method comprises the following steps that a balance car is started in a following mode, a video acquisition module acquires real-time data of a car owner, and characteristic values of the real-time data are extracted to obtain characteristic values of the real-time data;
comparing the real-time data characteristic value with the sample characteristic value, and judging whether the real-time data characteristic value and the sample characteristic value accord with the following conditions:
if not, the video acquisition module acquires real-time data again;
if the brake command is in accordance with the running track, calculating the running track through the calculation platform, and outputting a brake command to the brake module according to the running track;
the braking module controls the balance car to run according to the track, and then the following mode of the balance car is achieved.
2. The balance car automatic following implementation method based on the mechanical vision and AI technology as claimed in claim 1, wherein the computing platform is a master control platform for operating a vision platform of a spacious machine and a brake system of a hole balance car, collecting video information in real time, completing sample comparison and computing the running track of a car owner.
3. The method for realizing automatic following of the balance car based on the machine vision and AI technologies as claimed in claim 1, wherein said computing platform employs an Kawaki ARM8 embedded CPU carrying NVIDIA GPU module.
4. The balance car automatic following implementation method based on the mechanical vision and AI technologies as claimed in claim 1, wherein the vision collection module is a loose 720P high definition digital camera module.
5. The method for realizing automatic following of the balance car based on the machine vision and AI technologies as claimed in claim 1, wherein the brake module employs a loose digital brake system.
6. The method for realizing automatic following of the balance car based on the mechanical vision and AI technologies as claimed in any one of claims 1-5, wherein the car owner sample data comprises the body type and action habits of the car owner.
7. A balance car automatic following system based on mechanical vision and AI technology is characterized by comprising a video acquisition module, a computing platform, an open-view machine vision platform and a brake module, wherein the video acquisition module acquires the body type and action habit of a car owner in real time and uploads the body type and action habit to the computing platform; the computing platform stores the body type and action habit of the vehicle owner as vehicle owner sample data and operates a spacious machine vision platform; the spacious machine vision platform compares car owner sample data with real-time data, and then judges car owner's orbit to issue the braking command and give the braking module, drive braking module is according to the orbit and is patrolled, and then realizes the automation of balance car and follows.
8. The machine vision and AI technology based balance car auto-following system of claim 7 wherein said computing platform employs an Kawaki ARM8 embedded CPU, carrying an NVIDIA GPU module.
9. The balance car automatic following system based on the mechanical vision and AI technologies as claimed in claim 7, wherein said vision collection module is implemented using a loose 720P high definition digital camera module.
10. The machine vision and AI technology based balance car automatic following system according to any of the claims 7-9, characterized in that the brake module employs a loose digital brake system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011469211.1A CN112462788A (en) | 2020-12-15 | 2020-12-15 | Balance car automatic following implementation method and system based on mechanical vision and AI technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011469211.1A CN112462788A (en) | 2020-12-15 | 2020-12-15 | Balance car automatic following implementation method and system based on mechanical vision and AI technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112462788A true CN112462788A (en) | 2021-03-09 |
Family
ID=74803978
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011469211.1A Pending CN112462788A (en) | 2020-12-15 | 2020-12-15 | Balance car automatic following implementation method and system based on mechanical vision and AI technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112462788A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036523A (en) * | 2014-06-18 | 2014-09-10 | 哈尔滨工程大学 | Improved mean shift target tracking method based on surf features |
CN104954741A (en) * | 2015-05-29 | 2015-09-30 | 东方浩联(北京)智能科技有限公司 | Tramcar on-load and no-load state detecting method and system based on deep-level self-learning network |
CN105872371A (en) * | 2016-03-31 | 2016-08-17 | 纳恩博(北京)科技有限公司 | Information processing method and electronic device |
CN107992091A (en) * | 2017-10-31 | 2018-05-04 | 深圳市博鑫创科科技有限公司 | A kind of balance car follower method and system based on signal strength |
CN108491828A (en) * | 2018-04-20 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of parking site detecting system and method for the pairwise similarity PVAnet based on level |
CN108664032A (en) * | 2018-06-08 | 2018-10-16 | 东北大学秦皇岛分校 | A kind of automatic control system and method for following carrier based on machine vision |
CN109686031A (en) * | 2018-12-21 | 2019-04-26 | 北京智行者科技有限公司 | Identification follower method based on security protection |
-
2020
- 2020-12-15 CN CN202011469211.1A patent/CN112462788A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036523A (en) * | 2014-06-18 | 2014-09-10 | 哈尔滨工程大学 | Improved mean shift target tracking method based on surf features |
CN104954741A (en) * | 2015-05-29 | 2015-09-30 | 东方浩联(北京)智能科技有限公司 | Tramcar on-load and no-load state detecting method and system based on deep-level self-learning network |
CN105872371A (en) * | 2016-03-31 | 2016-08-17 | 纳恩博(北京)科技有限公司 | Information processing method and electronic device |
CN107992091A (en) * | 2017-10-31 | 2018-05-04 | 深圳市博鑫创科科技有限公司 | A kind of balance car follower method and system based on signal strength |
CN108491828A (en) * | 2018-04-20 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of parking site detecting system and method for the pairwise similarity PVAnet based on level |
CN108664032A (en) * | 2018-06-08 | 2018-10-16 | 东北大学秦皇岛分校 | A kind of automatic control system and method for following carrier based on machine vision |
CN109686031A (en) * | 2018-12-21 | 2019-04-26 | 北京智行者科技有限公司 | Identification follower method based on security protection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN210680559U (en) | Vehicle biological identification entering and starting system on automobile B column | |
CN106184223A (en) | A kind of automatic Pilot control method, device and automobile | |
CN103606246B (en) | A kind of Vehicular intelligent control loop | |
CN105955099A (en) | Driving mode switching method and apparatus for an unmanned vehicle | |
CN106564449A (en) | Intelligent driving customization method and device | |
CN106354130A (en) | Pilotless automobile as well as control method and remote monitoring system thereof | |
CN104002818A (en) | Interaction and automation integrated vehicle-mounted system | |
CN105015544A (en) | Vehicle speed control system and method for full-automatic parking of electric car | |
DE102018200244A1 (en) | Driver assistance system and method for the individual determination of boredom | |
CN107808545A (en) | Intelligent parking lot management system and management method | |
CN206039714U (en) | Electric automobile fills electric pile charging management system | |
CN112070823A (en) | Video identification-based automobile intelligent cabin adjusting method, device and system | |
CN101439653A (en) | System and method for automatically regulating chassis height | |
CN112389451A (en) | Method, device, medium, and vehicle for providing a personalized driving experience | |
CN114537569A (en) | Electric motor car intelligence center control system based on big data | |
CN107117096A (en) | Vehicle mounted multimedia laser display system and automobile | |
CN112854094A (en) | Intelligent pure electric washing and sweeping vehicle control system | |
CN112462788A (en) | Balance car automatic following implementation method and system based on mechanical vision and AI technology | |
CN110481503A (en) | A kind of vehicle personalization custom-built system coming with Face tracking and recognition and its method | |
CN110816325A (en) | Electric vehicle charging control method and system | |
CN110182206A (en) | A kind of pilotless automobile visual identifying system based on dual camera | |
CN108459520B (en) | Automatic display method for vehicle and system thereof | |
CN113085893A (en) | Vehicle control method and device based on image recognition | |
CN204821553U (en) | Speed of a motor vehicle control system of full -automatic in -process of parking of electric automobile | |
CN111399636A (en) | Unmanned vehicle guiding method, system and device based on limb action instruction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |
|
RJ01 | Rejection of invention patent application after publication |