Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An unmanned road obstacle recognition system

An obstacle recognition and unmanned driving technology, which is applied in the field of unmanned road obstacle recognition system, can solve the problem that the real-time and recognition accuracy of obstacle recognition need to be improved, the obstacle recognition accuracy is low, and the driving control effect is poor, etc. problem, to achieve the effect of improving the accuracy of unmanned driving control, accurate lane recognition results, and accurate existing technologies

Active Publication Date: 2022-01-28
SHANGHAI BOONRAY INTELLIGENT TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) Obstacle detection based on prior knowledge: This method preprocesses the image and compares it with the existing prior knowledge to draw a conclusion, so it has the disadvantages of low precision and narrow application
[0005] (2) Obstacle detection based on stereo vision: This method includes binocular stereo vision and trinocular stereo vision. Because it requires multiple cameras, the cost is relatively high, and the algorithm is complex and difficult to calculate.
[0006] Moreover, the existing unmanned driving technology has low accuracy for obstacle recognition under complex road conditions, resulting in poor driving control effect of the current unmanned driving technology in the case of bad road conditions. Real-time and recognition accuracy need to be improved

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
  • An unmanned road obstacle recognition system
  • An unmanned road obstacle recognition system
  • An unmanned road obstacle recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] A specific embodiment of the present invention discloses an unmanned road obstacle recognition system, which includes an image acquisition module, a channel separation module, a channel data storage module, an obstacle recognition module and a driving mode control module connected in sequence. Such as figure 1 The schematic diagram of the system structure of the unmanned road obstacle recognition system is shown, and the specific description is as follows.

[0066] The image collection module includes at least one vehicle-mounted camera for monitoring road conditions in real time, and is used to collect road image information during driving of the unmanned vehicle, and the road image information includes RGB (red, green, blue) color image information.

[0067] The vehicle-mounted camera can be installed in the front logo of the vehicle, on the front air grille, on the position of the fog lights, on the rearview mirror of the cab, above the windshield, or other positions...

Embodiment 2

[0089] On the basis of the previous embodiment, the channel separation module separates the road image information into RGB color channels to obtain mutually independent first channel images, second channel images and third channel images. The workflow of this process , comprising: performing pyramid down-sampling processing on the road image information by the image receiving and separating unit to obtain three-layer sample image features corresponding to the road image information, and the three-layer sample image features are respectively output to the first signal reconstruction unit, The second signal reconstruction unit and the third signal reconstruction unit; convert the sample image features in the three signal reconstruction units, extract and reconstruct the first channel image in the first signal reconstruction unit; reconstruct in the second signal The unit extracts and reconstructs the second channel image; the third signal reconstruction unit extracts and reconst...

Embodiment 3

[0091] On the basis of the previous embodiment, the lane recognition unit performs lane recognition based on the red channel road image, and outputs the lane recognition result. The workflow of this process includes:

[0092] Detecting the road edge points of the red channel road image, using the detected road edge points to fit a road boundary model; adjusting the feature area of ​​the red channel road image according to the road boundary model, and extracting the adjusted feature area The grayscale image of brightness features, detecting the lane line pixels in the brightness feature grayscale image, using the lane line pixels to construct a lane, completing lane recognition, and obtaining a lane recognition result.

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 relates to an unmanned road obstacle recognition system, belonging to the technical field of unmanned driving, comprising: an image acquisition module, used to collect road image information during the driving process of an unmanned vehicle; a channel separation module, electrically connected to the The image acquisition module separates the road image information into color channels to obtain the first, second and third channel images; the channel data storage module is electrically connected to the channel separation module for storing the channel image data; The obstacle identification module is electrically connected to the channel data storage module, and is used to intelligently analyze the channel image to obtain road conditions and obstacle identification results; the driving mode control module is electrically connected to the obstacle identification module, for Based on the road conditions and obstacle recognition results, the driving mode information of the unmanned vehicle is obtained and output. The invention can effectively identify different road conditions and obstacles, and has the advantages of high control accuracy and high real-time performance.

Description

technical field [0001] The invention belongs to the technical field of unmanned driving, and in particular relates to a road obstacle recognition system for unmanned driving. Background technique [0002] Since the birth of unmanned vehicles, the perception of obstacles on the vehicle's driving road has attracted the attention of many scholars and scientific research institutions as a very important research content in the field of unmanned driving, but it is still a very difficult topic. Obstacle detection on the road is an important part in the field of driverless technology. [0003] In recent years, in the field of ITS (Intelligent Transportation System) research at home and abroad, many algorithms and implementation methods have been proposed for obstacle detection methods on the vehicle's driving path, including image-based detection methods, which mainly include: [0004] (1) Obstacle detection based on prior knowledge: This method is to preprocess the image and then...

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 Patents(China)
IPC IPC(8): G06V20/58G06V10/56G06V10/764G06K9/62
CPCG06V20/588G06V20/58G06V10/56G06F18/24
Inventor 胡心怡杨扬
Owner SHANGHAI BOONRAY INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com