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

Vehicle search method based on multiple views

A multi-view, vehicle technology, applied in the field of vehicle retrieval based on multi-view, can solve the problem of infeasibility of detection methods

Active Publication Date: 2015-05-13
WUHAN UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to different viewing angles and the variability of vehicle appearance, the traditional vehicle detection method is infeasible.

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 search method based on multiple views
  • Vehicle search method based on multiple views
  • Vehicle search method based on multiple views

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solution of the present invention will be described in detail below in conjunction with the embodiments and related drawings.

[0033] Due to different viewing angles and the variability of vehicle appearance, traditional vehicle detection methods are infeasible. The local model representation is optimized in two aspects in the present invention. During specific implementation, the orientation division model of the vehicle's potential attitude and the local correspondence between any two orientations can be established in advance.

[0034] In the azimuth division model, it is defined that the azimuth division is performed with the camera frontal shooting point as a reference point, and is divided into a plurality of azimuths on average. Those skilled in the art can designate specific azimuth division methods, such as dividing into 4, 8 or 16 azimuths, etc., which can be flexibly selected according to the accuracy requirements.

[0035] First, the embodim...

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

Provided is a vehicle search method based on multiple views. The method includes that a direction dividing model of potential gestures of vehicles is built, the direction dividing is defined with the front camera shooting point of a camera as a reference point in the direction dividing model, a plurality of directions are divided evenly, a local block of each direction is set in advance, the corresponding relation between the local blocks of two directions is built, a vehicle search base is built, vehicle gesture estimation is conducted on images for vehicle detection and search vehicle pictures in the vehicle search base, the directions of the vehicle gestures are obtained according to a direction dividing model, visual characteristics of the local blocks of the direction are extracted according to the divided vehicle gestures, target vehicles are shown by adopting a local two-dimensional model according to the visual characteristics of the local blocks, visual similarity comparison is conducted according to the corresponding relation of the local blocks of the corresponding relation of the local two-dimensional model to obtain similarity and acquire a vehicle search result.

Description

technical field [0001] The invention relates to a vehicle retrieval technology, in particular to a vehicle retrieval method based on multi-view. Background technique [0002] Vehicle retrieval is mainly manifested as a technology that matches the monitoring video results of the same vehicle from cameras with different perspectives in different locations, in order to find the target vehicle. It has a wide application background in the fields of intelligent transportation system, public security criminal investigation and information security. [0003] As mentioned in the article "On-road vehicle detection: a review" by Zehang Sun and ETreppid, compared with traditional vehicle classification, vehicle retrieval requires finding a specific target vehicle in a series of vehicles with similar appearance, which makes the work easier. Not only that, but also the actual situation, such as the influence of factors such as monitoring environment, weather conditions, and lighting cond...

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): G06K9/00G06K9/62G06T7/20
CPCG06V20/584
Inventor 胡瑞敏熊明福方稳华梁超王晓郑淇陈军
Owner WUHAN UNIV
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