Vehicle surrounding pedestrian danger level prediction method and system

A technology of danger level and pedestrians, which is applied in the traffic control system, prediction, and collision avoidance system of road vehicles, etc., can solve the problems of high calculation cost of pedestrian danger level, limited applicable scenarios, and poor predictability, so as to shorten the prediction time, The effect of improving recognition efficiency and reducing computing cost

Active Publication Date: 2021-03-12
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of high computational cost, poor predictability, strong subjectivity, and limited applicable scenarios in the prior art of pedestrian danger level prediction

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
  • Vehicle surrounding pedestrian danger level prediction method and system
  • Vehicle surrounding pedestrian danger level prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] This embodiment discloses the preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein, the accompanying drawings constitute a part of the application and together with the embodiments of the present invention are used to explain the principles of the present invention and are not intended to limit the scope of the present invention scope.

[0043] Example 1

[0044] Such as figure 1 As shown, this embodiment provides a method for predicting the danger level of pedestrians around the vehicle, including two parts: offline danger level predictor training and online danger level prediction. Such as figure 1 It is a schematic flow chart of the method described in this embodiment.

[0045] Among them, the offline danger level predictor training includes the following steps:

[0046] Step S1101, using the on-board sensor to collect the surrounding environment information from the first perspective ...

Embodiment 2

[0068] Such as figure 2 As shown, this embodiment provides a system for predicting the danger level of pedestrians around the vehicle, which includes an offline danger level predictor training part and an online danger level prediction part.

[0069] Among them, the offline training part includes the online collection module of vehicle peripheral information, the pedestrian characteristic parameter extraction module, the pedestrian trajectory fitting training module, and the pedestrian danger level recognition training module.

[0070] The vehicle surrounding information collection module is used to collect the surrounding environment information from the first perspective of the vehicle.

[0071] Specifically, through an image acquisition device, such as an on-board camera installed at the front windshield of the vehicle, image information around the vehicle is collected; through a lidar installed on the top of the vehicle, 3D point cloud information around the vehicle is co...

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 method and system for predicting the danger level of pedestrians around a vehicle, and belongs to the technical field of intelligent vehicle active safety. Pedestrian trajectory prediction is carried out based on the first view angle data of the vehicle, long-time trajectory prediction is realized by using data-driven sequential network modeling, the calculation cost is reduced, and the prediction duration is shortened; a danger level recognizer based on clustering analysis and a classifier can recognize the danger level of pedestrians according to the characteristicparameters, and uncertainty caused by judging the danger level by manually dividing parameter ranges is avoided; a pedestrian moving track is predicted according to the pedestrian track fitting deviceobtained by training, a pedestrian characteristic parameter set is extractd, the parameter set is input into the pedestrian danger level recognizer obtained by training, and the pedestrian danger level is predicted. According to the invention, understanding of behavior intentions of surrounding pedestrians in the driving process is facilitated, the collision risk of pedestrians and vehicles is estimated, a basis is provided for adjusting a driving strategy, the driving risk is avoided, and the driving safety is improved.

Description

technical field [0001] The invention belongs to the technical field of active safety of intelligent vehicles, and in particular relates to a method and system for predicting the danger level of pedestrians around the vehicle. Background technique [0002] In recent years, pedestrian safety has gained more and more attention in the field of intelligent vehicles. Intelligent vehicles need timely perception and danger prediction of pedestrians on the road to avoid possible collisions. [0003] At present, the detection method of pedestrian danger mainly calculates the collision time or collision area of ​​pedestrians relative to the driving vehicle through the method of complex dynamic fitting, and then manually performs different collision time or collision area by safety system designers. Classification of danger levels to determine the degree of danger of pedestrians. For the calculation of pedestrian collision time or collision area through complex dynamic models, there a...

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): G06K9/00G06K9/62G06N3/04G06T7/20G08B21/18G08G1/16B60W30/095G06Q10/04G06Q10/06
CPCB60W30/095G06T7/20G08B21/182G08G1/166G06T2207/30252G06T2207/30241G06T2207/10028G06V20/56G06N3/045G06F18/23213G06F18/214
Inventor 吕超张哲雨张钊陆军琰徐优志龚建伟
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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