CN104035752A - Linux intelligent vehicle-mounted system based on vision internet of things - Google Patents

Linux intelligent vehicle-mounted system based on vision internet of things Download PDF

Info

Publication number
CN104035752A
CN104035752A CN201310066253.4A CN201310066253A CN104035752A CN 104035752 A CN104035752 A CN 104035752A CN 201310066253 A CN201310066253 A CN 201310066253A CN 104035752 A CN104035752 A CN 104035752A
Authority
CN
China
Prior art keywords
sensor
things
vision
internet
intelligent vehicle
Prior art date
Application number
CN201310066253.4A
Other languages
Chinese (zh)
Inventor
张佳宇
赵博然
董国勇
李少军
彭力
冯伟
Original Assignee
江南大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 江南大学 filed Critical 江南大学
Priority to CN201310066253.4A priority Critical patent/CN104035752A/en
Publication of CN104035752A publication Critical patent/CN104035752A/en

Links

Abstract

The invention designs a Linux intelligent vehicle-mounted system based on vision internet of things. The intelligent vehicle-mounted system is based on data aggregation and integration in vision internet of things and data consistency techniques, uses sensor image fusion algorithms and multi-vision sensor global calibration methods, can perform image de-noising in the harsh environment, image segmentation of the region of interest, feature information extraction, multi-sensor synchronization and image fusion, forms three-dimensional structures of objects and obtains spatial positions of objects as well as supports multiple audio and video media formats and functions of serving as a DVD (Digital Versatile Disc) media player, a hard disk media player, a GPS (Global Position System) navigation instrument, vehicle-mounted Bluetooth, a vehicle-mounted radio and reversing radar.

Description

A kind of Linux intelligent vehicle-mounted system based on vision Internet of Things

Technical field

A kind of based on convergence, fusion and data consistency technology in vision Internet of Things, use sense sensor Image Fusion and multi-visual sense sensor scaling method, image denoising that can be under bad environment, to interesting image regions cut apart, feature information extraction, multisensor is synchronous and image co-registration, formation object three-dimensional structure and obtain object space position, support multiple audio-video frequency media form and support the intelligent vehicle-mounted system of DVD media play, hard disk media play, GPS navigation, on-vehicle Bluetooth, vehicle-mounted radio, reversing radar function.

Background technology

Vision Internet of Things is by information sensing equipment such as visual sensing label, radio-frequency (RF) identification (RFID), infrared inductor, GPS, laser scanners, by the agreement of agreement, any object is connected with internet, carry out message exchange and communicate by letter, to realize a kind of network to intellectuality identification, location, tracking, monitoring and the management of object.

Global calibration is in the measurement data unification to of each a vision sensor overall world coordinate system, namely determines each vision sensor coordinate system position and the direction of this overall world coordinate system, i.e. rotating vector and translation vector relatively.Three kinds of conventional overall calibration methods: coordinate united law of the same name; Intermediate coordinates united law; The unique method of world coordinates.The basic thought of the unique method of world coordinates is directly to utilize punctuate under world's global coordinate to carry out part to each vision sensor unit of the system in measuring state to demarcate, thus part is demarcated and global calibration is unified arrive together with.Thereby the method has strengthened the simplicity of on-site proving, guaranteed the consistance of demarcation state and measuring state, reduced labour intensity, improved to a certain extent the precision of global calibration.Based on above-mentioned advantage, this problem intends adopting the unique method of world coordinates.Coordinate united law of the same name need to be through twice coordinate system conversion, twice calibration point collection; Intermediate coordinates united law needs three coordinate system conversions, twice calibration point collection; And for once coordinate system conversion of the unique method of world coordinates, a calibration point collection.

Convergence, fusion and data consistency technology in vision Internet of Things, the physical features of perception multimedia messages, numerous with the service feature of heterogeneous information feature and different application scene in vision Internet of Things, how above various features are set up to Internet of Things information coalescence model, it is gordian technique that research multimedia information source and multi-source information converge.Internet of Things data fusion mechanism, the hybrid multisensor data fusion of research based on radio multimedia sensor network is machine-processed, multi-medium data blending theory and multimedia messages synchronization solutions are proposed, set up simulation experiment platform and carry out theory and emulation experiment, optimizing the various models and the mechanism that propose is all key issue urgently to be resolved hurrily.

Summary of the invention

The object of the invention is to propose a kind of Linux intelligent vehicle-mounted system based on vision Internet of Things, it is with low cost, and mounting arrangements is simple, flexible and convenient to use.

For reaching this object, the present invention by the following technical solutions:

(1) multiple vision sensor image interfusion method.This technological synthesis utilizes correlativity spatially of different source images that various sensors obtain and the complementarity in information, to obtain more clear, comprehensive, the accurate iamge description of Same Scene.The level of image co-registration can be divided into: signal level, Pixel-level, feature level, decision level.What this problem was intended adopting is pixel-level image fusion, and for pixel-level image fusion, the fusion method having proposed mainly contains principal component analysis (PCA), EVOLUTIONARY COMPUTATION, artificial neural network, wavelet transformation and fuzzy logic etc.Each algorithm all has the relative merits of oneself.This problem will be based upon laboratory in the past on scientific research basis, and several different methods is applied to, in image co-registration, compare, and analyze the advantage of various algorithms, thereby improve wherein a kind of algorithm, obtain being better than a kind of new image interfusion method of previous methods.

(2) multi-visual sense sensor scaling method.Global calibration is in the measurement data unification to of each a vision sensor overall world coordinate system, namely determines each vision sensor coordinate system position and the direction of this overall world coordinate system, i.e. rotating vector and translation vector relatively.Three kinds of conventional overall calibration methods: coordinate united law of the same name; Intermediate coordinates united law; The unique method of world coordinates.The basic thought of the unique method of world coordinates is directly to utilize punctuate under world's global coordinate to carry out part to each vision sensor unit of the system in measuring state to demarcate, thus part is demarcated and global calibration is unified arrive together with.Thereby the method has strengthened the simplicity of on-site proving, guaranteed the consistance of demarcation state and measuring state, reduced labour intensity, improved to a certain extent the precision of global calibration.Based on above-mentioned advantage, this problem intends adopting the unique method of world coordinates.

(3) convergence, fusion and data consistency technology in vision Internet of Things.The physical features of perception multimedia messages, numerous with the service feature of heterogeneous information feature and different application scene in vision Internet of Things, how above various features are set up to Internet of Things information coalescence model, it is gordian technique that research multimedia information source and multi-source information converge.Internet of Things data fusion mechanism, the hybrid multisensor data fusion of research based on radio multimedia sensor network is machine-processed, multi-medium data blending theory and multimedia messages synchronization solutions are proposed, set up simulation experiment platform and carry out theory and emulation experiment, optimizing the various models and the mechanism that propose is all key issue urgently to be resolved hurrily.

Accompanying drawing explanation

Fig. 1 is overall system design block diagram.

Embodiment

Below in conjunction with accompanying drawing, the present invention will be further described:

Figure 1 shows that this overall system design block diagram mainly contains two parts and forms, a part is by TMS320DM6467CPU and peripheral chip and module composition, mainly realize following functions: high definition TFT6.2 inch LCDs shows, 800x480 resolution, high transmission rate touch screen function; Built-in hard disk multi-media player function; Camera head monitor and recording function; GPS navigation positioning function; Tire temperature tire pressure measuring ability; Bluetooth hand-free function; CMMB digital television function; There is USB2.0 and TF interface function.

Another part consists of MCU, and MCU mainly carries out overall system control, controls, standby low-power consumption etc. as remote control and keystroke handling, radio control, volume chip controls, audio frequency and video passage switch chip controls, system power supply.

In addition, MCU and TMS320DM6467 processor carry out communication by serial ports, MCU sends to TMS320DM6467 processor relevant button and guidance command, receive the message that TMS320DM6467 processor transmits, mode of operation as current in system, the switching state of audio frequency and video passage, size of current volume etc. simultaneously.

Claims (5)

1. the Linux intelligent vehicle-mounted system based on vision Internet of Things, is characterized in that:
Comprise a plurality of video acquisition module, be responsible for respectively the situation in monitoring car;
Used the image processing architecture of many visions Internet of Things;
Multiple vision sensor Image Fusion and multi-visual sense sensor scaling method have been used;
Based on convergence, fusion and data consistency technology in vision Internet of Things;
By comprise video monitoring, DVD media play, hard disk media play, GPS navigation, on-vehicle Bluetooth, vehicle-mounted radio, radar for backing car, etc. functional module.
2. the Linux intelligent vehicle-mounted system based on vision Internet of Things according to claim 1, is characterized in that sensor assembly adopts high accuracy number Temperature Humidity Sensor and dust sensor; Sensor assembly moves special-purpose sensor driver and Sensor Network networking program.
3. the Linux intelligent vehicle-mounted system based on vision Internet of Things according to claim 1, is characterized in that chip S3C6410 is core processor.
4. the Linux intelligent vehicle-mounted system based on vision Internet of Things according to claim 1, adopts Qt exploitation UI interface.
5. the Linux intelligent vehicle-mounted system based on vision Internet of Things according to claim 1, is characterized in that signal data converges, fusion and data consistency technology, sensor image blending algorithm and multi-visual sense sensor scaling method.
CN201310066253.4A 2013-03-04 2013-03-04 Linux intelligent vehicle-mounted system based on vision internet of things CN104035752A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310066253.4A CN104035752A (en) 2013-03-04 2013-03-04 Linux intelligent vehicle-mounted system based on vision internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310066253.4A CN104035752A (en) 2013-03-04 2013-03-04 Linux intelligent vehicle-mounted system based on vision internet of things

Publications (1)

Publication Number Publication Date
CN104035752A true CN104035752A (en) 2014-09-10

Family

ID=51466528

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310066253.4A CN104035752A (en) 2013-03-04 2013-03-04 Linux intelligent vehicle-mounted system based on vision internet of things

Country Status (1)

Country Link
CN (1) CN104035752A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106657745A (en) * 2016-12-30 2017-05-10 北京航空航天大学 Vehicle-mounted data collection system of multi-source GPS data and monocular images
US10235480B2 (en) 2016-06-15 2019-03-19 International Business Machines Corporation Simulation of internet of things environment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100125387A1 (en) * 2008-11-17 2010-05-20 Chung-Ang University Industry-Academy Cooperation Foundation System of integrated telematics service and method of controlling the system
KR20120033146A (en) * 2010-09-29 2012-04-06 현대자동차주식회사 Method for checking location of vehicle using smart phone
CN102651173A (en) * 2012-05-23 2012-08-29 成都亿盟恒信科技有限公司 Beidou satellite monitoring safe driving system based on 3G network
CN102881016A (en) * 2012-09-19 2013-01-16 中科院微电子研究所昆山分所 Vehicle 360-degree surrounding reconstruction method based on internet of vehicles

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100125387A1 (en) * 2008-11-17 2010-05-20 Chung-Ang University Industry-Academy Cooperation Foundation System of integrated telematics service and method of controlling the system
KR20120033146A (en) * 2010-09-29 2012-04-06 현대자동차주식회사 Method for checking location of vehicle using smart phone
CN102651173A (en) * 2012-05-23 2012-08-29 成都亿盟恒信科技有限公司 Beidou satellite monitoring safe driving system based on 3G network
CN102881016A (en) * 2012-09-19 2013-01-16 中科院微电子研究所昆山分所 Vehicle 360-degree surrounding reconstruction method based on internet of vehicles

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
白景斐: "基于RFID的物联网车载终端系统", 《电子设计工程》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10235480B2 (en) 2016-06-15 2019-03-19 International Business Machines Corporation Simulation of internet of things environment
CN106657745A (en) * 2016-12-30 2017-05-10 北京航空航天大学 Vehicle-mounted data collection system of multi-source GPS data and monocular images
CN106657745B (en) * 2016-12-30 2019-07-23 北京航空航天大学 A kind of vehicular collecting system of multi-source GPS data and monocular image

Similar Documents

Publication Publication Date Title
US10529142B2 (en) Capturing and aligning three-dimensional scenes
KR102028720B1 (en) Transparent display apparatus for displaying an information of danger element and method thereof
JP2011128220A (en) Information presenting device, information presenting method, and program
DE112012004773T5 (en) Configurable dashboard display
US10068373B2 (en) Electronic device for providing map information
US9952433B2 (en) Wearable device and method of outputting content thereof
TWI544781B (en) Real-time 3d reconstruction with power efficient depth sensor usage
US8588464B2 (en) Assisting a vision-impaired user with navigation based on a 3D captured image stream
CN105409212B (en) The electronic equipment with depth sense is caught with multi-view image
CN105408938B (en) System for the processing of 2D/3D space characteristics
US9851787B2 (en) Display resource management
KR20110071210A (en) Apparatus and method for mixed reality content operation based on indoor and outdoor context awareness
CA2926861C (en) Fiducial marker patterns, their automatic detection in images, and applications thereof
US8107677B2 (en) Measuring a cohort'S velocity, acceleration and direction using digital video
US20160210786A1 (en) Method of displaying virtual information in a view of a real environment
CN102645666B (en) Method for switching indoor ultra wide band (UWB) location and outdoor global position system (GPS) location
US20140009494A1 (en) Display control device, display control method, and program
US9983592B2 (en) Moving robot, user terminal apparatus and control method thereof
CN105100390A (en) Mobile terminal and method for controlling the mobile terminal
CN105393079A (en) Context-based depth sensor control
CN104238739A (en) Visibility improvement method based on eye tracking and electronic device
US9189068B2 (en) Apparatus and a method for gesture recognition
CN102156481A (en) Intelligent tracking control method and system for unmanned aircraft
CN103353935A (en) 3D dynamic gesture identification method for intelligent home system
US10140771B2 (en) Information processing apparatus for displaying an image such that the image is superimposed on real scenery

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20140910