Pedestrian intension detection method and system

A detection method and detection system technology, applied in the field of target tracking and target behavior analysis, can solve the problems of waste of road resources, pedestrian inconvenience, unreasonable utilization of road resources, etc., and achieve the effect of improving traffic efficiency

Active Publication Date: 2017-09-29
深圳市鸿逸达科技有限公司
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1. The traffic flow during peak hours is different from that in normal times, but the switching frequency of traffic lights is the same, resulting in unreasonable utilization of road resources
[0005] 2. If no pedestrians need to cross the road, if the traffic lights are switc

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
  • Pedestrian intension detection method and system
  • Pedestrian intension detection method and system
  • Pedestrian intension detection method and system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 approach

[0023] like figure 1 Shown, the principle of an embodiment of the present invention is:

[0024] In D1, a distance sensor is set to collect environmental perception data (that is, distance data) in the observation area.

[0025] In D2, the monitoring area is divided into multiple sub-areas (such as grid points), and the fluidity of the target in each sub-area is analyzed. The fluidity includes: the change trend of the target potential field (or flow, density).

[0026] More specifically, step D2 includes:

[0027] D2-1. Based on the point cloud data collected on the sub-region (such as the grid point), calculate the potential field of the sub-region (such as the grid point), such as the density map and the posterior probability distribution.

[0028] A common method is, similar to the Mean-shift method, using a kernel function to calculate (see Comaniciu, D., & Meer, P. (1999), Distribution free decomposition of multivariatedata. Pattern analysis & applications, 2(1), 22 -3...

no. 2 approach

[0047] like figure 2 As shown, the second embodiment of the present invention is an improvement on the first embodiment.

[0048] In D1, a plurality of distance sensors are deployed at the intersection where the signal lights are located to collect environmental perception data (ie distance data) in the observation area. This is the same as the first embodiment.

[0049] The distance sensor can perform line scan, multi-line scan and / or area scan. It is generally recommended to use a single-line scanning laser distance sensor, and a multi-line scanning distance sensor or an area scanning distance sensor can also be used. The distance sensor is arranged at a fixed position, and the scanning plane of the distance sensor is parallel to the ground. Generally, the distance sensor is set at a height of 20-80 cm from the ground, so as to be able to scan the area of ​​the legs and feet of pedestrians and the tire area of ​​bicycles and electric vehicles.

[0050] The distance sens...

no. 3 approach

[0080] According to another aspect of the present invention, an intelligent pedestrian recognition system is proposed, including: one or more distance sensors, arranged at intersections where signal lights are located, for collecting target shape data.

[0081] The system of the present invention also includes a processor.

[0082] The processor can be configured to execute the steps described in the first embodiment.

[0083] According to another aspect of the present invention, a computer-readable carrier is proposed, the carrier records a computer-based operating program, and when the program is executed, the steps described in the first embodiment can be realized.

[0084] The intelligent pedestrian identification method and system of the present invention can intelligently identify pedestrians and vehicles. In addition to being applied to the control of traffic lights, it can also be applied to the following scenarios:

[0085] 1. Perimeter intrusion warning for schools,...

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 provides a pedestrian intention detection method and system. The pedestrian intention detection method comprises the steps of D1, setting a distance sensor to acquire environment sensing data in an observation region; D2, dividing the monitoring region into a plurality of sub-regions, and analyzing the mobility of a target in each sub-region; and D3, judging a behavioral intention of the target in the monitoring region through analysis for the mobility in the sub-regions. The invention provides a method for performing analysis on the mobility of a target in a region and judging the behavioral intention of the target, and the method can be applied to intelligent traffic light control.

Description

technical field [0001] The present invention relates to target tracking and target behavior analysis technology, and more specifically, to a method and system for intelligent pedestrian intention detection. Background technique [0002] At intersections where pedestrians pass, traffic lights are generally used for traffic control, and the traffic lights are alternately lit at a fixed frequency. There are also some intersections with pedestrian crossing buttons, which can manually turn on the green light to pass. In addition, at some larger intersections, there are special right-turn lanes. There are no traffic lights in these lanes, and pedestrian traffic depends entirely on the personal qualities of the car owners. [0003] Then, there are the following problems: [0004] 1. The traffic flow during peak hours is different from that in normal times, but the switching frequency of traffic lights is the same, resulting in unreasonable utilization of road resources. [0005]...

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
IPC IPC(8): G08G1/07
CPCG08G1/07
Inventor 邵肖伟许永伟
Owner 深圳市鸿逸达科技有限公司
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