A vehicle key point alignment method based on deep learning

A technology of deep learning and key points, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as poor generalization, inability to extract low-quality vehicle pictures from large angles, and achieve rapid detection and positioning, robustness Strong performance and generalization ability, reducing video memory usage and time-consuming effects

Inactive Publication Date: 2019-04-05
GOSUNCN TECH GRP
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a vehicle key point alignment method based on deep learning to solve the technical problem that the existing technology cannot effectively extract large-angle low-quality vehicle pictures in complex video surveillance scenes, and the generalization is poor

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
  • A vehicle key point alignment method based on deep learning
  • A vehicle key point alignment method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0027] In view of the traditional algorithm architecture used in the existing technology, the strategy of using gradient regression tree point-by-point regression combined with global constraint rules to extract key points of vehicles can only be adapted to the situation where the image is clear, the body is correct and there is no occlusion in the bayonet or electric police scene , it is impossible to effectively extract large-angle low-quality vehicle ...

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 vehicle key point alignment method based on deep learning. Characteristic point regression is carried out on areas such as vehicle windows, vehicle lamps and license plates ofa vehicle by utilizing a strong characteristic extraction capability of a deep convolutional network. And the vehicle key points are subjected to geometric matrix operation to obtain a vehicle alignment matrix, so that the vehicles are corrected and aligned to the same angle and direction, and the vehicle alignment effect is completed. The vehicle key point alignment method is high in feasibilityand high in real-time performance, the extracted key points can effectively represent the overall situation and detail information of the vehicle, and the aligned vehicle images are beneficial for improving the recognition rate of a subsequent classification recognition algorithm.

Description

technical field [0001] The invention belongs to the technical field of computer vision processing, in particular to a vehicle key point alignment method based on deep learning. Background technique [0002] With the development of artificial intelligence and computer vision technology, vehicle recognition technology has been widely used in many image detection and public security systems, such as bayonet system, electronic police system, intelligent transportation and automatic driving and other fields. However, due to the complex outdoor lighting environment and the reality of vehicles traveling in multiple angles and directions, vehicle recognition technology is prone to misidentification. What needs to be solved urgently is to improve the accuracy of vehicle recognition. Therefore, preprocessing and correcting vehicle images to provide better vehicle images for algorithm recognition is a feasible way to improve the recognition rate. [0003] There is currently only one p...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/52G06V10/44G06V2201/08G06V20/625G06F18/214
Inventor 毛亮薛昆南朱婷婷黄仝宇汪刚宋一兵侯玉清刘双广
Owner GOSUNCN TECH GRP
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