Multidimensional non-wearable type traffic police gesture identification method and system for driverless vehicles

An unmanned vehicle and gesture recognition technology, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of wearable device command freedom constraints, complex implementation, and difficulty in extracting key gestures in a single frame.

Active Publication Date: 2016-08-24
EAST CHINA NORMAL UNIV
View PDF8 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Actual traffic crossings are usually complex and changeable. The traditional two-dimensional static traffic police gesture detection method is easily affected by changes in lighting, weather and other factors. Difficult, the implementation is more complicated, and the auxiliary use of wearable devices has brought constraints on the freedom of command to the traffic police

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multidimensional non-wearable type traffic police gesture identification method and system for driverless vehicles
  • Multidimensional non-wearable type traffic police gesture identification method and system for driverless vehicles
  • Multidimensional non-wearable type traffic police gesture identification method and system for driverless vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0100] In the method of the present invention, depth sensors are respectively placed in four directions of the crossing to obtain the four-dimensional data source (x, y, z, t) of traffic police gestures, and a three-dimensional Laplace distribution is proposed as a probability distribution to realize feature extraction, and descriptive and discriminative traffic police gesture features, using support vector machine classifiers to identify current traffic police gestures and command orientations, and transmit the current geographic location coordinates, traffic police gesture recognition results, and command directions to wireless stations within a certain range of crossings via wireless broadcasting. People drive the car, which is convenient for the vehicle to accurately make a prediction of the crossing. Specific steps are as follows:

[0101] The first step is to ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a multidimensional non-wearable type traffic police gesture identification method and system for driverless vehicles. The method includes the steps of obtaining traffic police gesture four-dimensional data sources from four depth sensors installed on a road crossing, extracting traffic police gesture characteristics with description and differentiability performance, identifying the current traffic police gesture and instruction orientation in combination with a traffic police gesture characteristic dictionary library, transmitting the current geographic position coordinate, the traffic police gesture identification result, the instruction direction to a driverless vehicle on the road crossing, the vehicle parsing the received information and extracting corresponding traffic police instructions on the driving direction, and entering into an automatic response state according to the instructions. The system comprises a traffic police gesture data acquisition apparatus, a traffic police gesture identification apparatus and a driverless vehicle response apparatus. The identification speed is fast, the method and system do not rely on wearable devices, traffic polices are free to command, the influence of the illumination, weather and complex background can be eliminated, and the robustness is good.

Description

technical field [0001] The invention belongs to the technical field of computer vision and pattern recognition, and in particular relates to a multi-dimensional non-wearable traffic police gesture recognition method and system for unmanned vehicles. Background technique [0002] With the rapid development of Internet technology, driverless cars are gradually becoming a reality. As an important part of the future intelligent transportation system, being able to accurately recognize traffic police gestures and make timely judgments is an important guarantee for the safe driving of unmanned vehicles. [0003] In the prior art, the Chinese invention patent with the application number 201410222122.5 discloses a traffic sign recognition method for unmanned vehicles, which recognizes two-dimensional static traffic signs; the Chinese invention patent with the application number 201510208977.7 discloses an application A fast detection algorithm for traffic lights for driverless cars...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/28G06V2201/09G06F18/2411
Inventor 邱崧凌佩佩蔡茗名钟阳徐伟刘莹莹贾高杰金豫
Owner EAST CHINA NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap