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

Road moving target detection method based on trajectory prediction

A moving target and target detection technology, applied in the field of moving target detection, can solve the problem of high missed detection rate, and achieve the effect of reducing the missed detection rate, small structure, and good continuity

Inactive Publication Date: 2020-06-26
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned shortcomings in the prior art, the trajectory prediction-based road moving object detection method provided by the present invention solves the problem in the prior art that the detection rate of the detector is high when the moving objects are occluded from each other.

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
  • Road moving target detection method based on trajectory prediction
  • Road moving target detection method based on trajectory prediction
  • Road moving target detection method based on trajectory prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059]The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0060] Such as figure 1 As shown, a road moving target detection method based on trajectory prediction includes the following steps:

[0061] S1. Obtain the video stream of the road moving target through the vehicle camera, and process it to obtain the corresponding image frame;

[0062] S2. Input the image frame into the trained target detection network to obtain the corresponding target detection frame;

[0063] S3. Perf...

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 road moving target detection method based on trajectory prediction. The improved YOLOv3-Tiny network is used for carrying out a vehicle pedestrian detection task of a vehicle-mounted video, has the advantages of small structure and few network parameters, and is very suitable for carrying out rapid and high-precision detection on an image under the condition that the vehicle-mounted hardware level is limited; a Kalman filtering tracking algorithm is used to predict the position of a detection frame, and then a Hungary algorithm data association strategy is used to combine the detection algorithm and the tracking algorithm, so that the continuity of motion between frames of vehicles and pedestrians can be well utilized, and the omission ratio of a target is reduced.

Description

technical field [0001] The invention belongs to the technical field of moving target detection, and in particular relates to a trajectory prediction-based road moving target detection method. Background technique [0002] With the development of automatic driving technology, accurate and timely detection of road vehicles and pedestrians has become a basic requirement for the realization of automatic driving assistance systems. The implementation methods for vehicle and pedestrian detection can be mainly divided into winner-based detection schemes and image-based detection schemes. Among them, hardware-based detection mostly uses vehicle-mounted sensing systems to sense the road environment, such as arranging multiple millimeter-level radars around the vehicle for information collection. Although this type of solution can collect road information very well, it greatly improves the production of vehicles. The cost is not conducive to the large-scale promotion of autonomous dr...

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): G06T7/277G06T7/246G06K9/62G06N3/04G06N3/08
CPCG06T7/277G06T7/246G06N3/082G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30256G06N3/045G06F18/23213
Inventor 吴正华缪忻怡李欣芮欀玉双
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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