Unlock instant, AI-driven research and patent intelligence for your innovation.

Heterogeneous image pose estimation and registration method, device and medium based on neural network

A neural network and pose estimation technology, applied in the field of image processing, can solve the problem of difficult to achieve pose estimation and registration of heterogeneous images, achieve good interpretability and generalization ability, short time, high accuracy and real-time effects

Active Publication Date: 2022-03-25
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that heterogeneous images are difficult to achieve pose estimation and registration in the prior art, and to provide a method for pose estimation and registration of heterogeneous images based on neural network

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
  • Heterogeneous image pose estimation and registration method, device and medium based on neural network
  • Heterogeneous image pose estimation and registration method, device and medium based on neural network
  • Heterogeneous image pose estimation and registration method, device and medium based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further elaborated and described below with reference to the accompanying drawings and specific embodiments. The technical features of the various embodiments of the present invention can be combined correspondingly on the premise that there is no conflict with each other.

[0029] Heterogeneous sensors are limited by the characteristics of the sensor itself, and the two images obtained by it are heterogeneous images with differences in angle, scale, and viewing angle. Moreover, the sensor is also subject to different forms of interference such as lighting, shadows, and occlusions when acquiring graphics, and these interferences can make pose estimation extremely difficult. For example, O 1 was acquired in the early morning by the drone's bird's-eye camera, while O 2 It is a local elevation map constructed by a ground robot using lidar. These two types of images are heterogeneous images and cannot be directly matched. To address this pro...

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 neural network-based heterogeneous image pose estimation and registration method, which belongs to the field of image processing. The invention optimizes the phase correlation algorithm to be differentiable, embeds it into the end-to-end learning network framework, and constructs a neural network-based heterogeneous image pose estimation method. This method can find the optimal feature extractor for the result of image matching, can get the solution without exhaustive evaluation, and has good interpretability and generalization ability. The test results show that the present invention can accurately realize the accurate pose estimation and registration of heterogeneous pictures, and the required time is relatively short, with high accuracy and real-time performance, which can meet the needs of practical applications and can be applied to robotics positioning etc.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to an image pose estimation and matching method. Background technique [0002] Self-localization is one of the most fundamental problems of mobile robots. After more than ten years of research, it is relatively mature to locate a given observation in the map established by the same sensor. But measurement matching from heterogeneous sensors is still an open problem. Heterogeneous sensors are limited by the characteristics of the sensor itself, and the two images obtained are heterogeneous images with differences in angle, scale, viewing angle, etc.; and the sensor is also subject to different forms of interference such as illumination, shadow, and occlusion when acquiring images. , and these disturbances make pose estimation extremely difficult. Considering the positive progress of researchers in building maps in recent years, we also hope to complete the matching of h...

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 Patents(China)
IPC IPC(8): G06T7/73G06T7/33G06N3/04G06N3/08
CPCG06T7/74G06T7/337G06N3/08G06T2207/20056G06T2207/20081G06T2207/20084G06N3/045G06T7/33G06T2207/10032G06T2207/30244G06T7/32
Inventor 王越陈泽希许学成熊蓉
Owner ZHEJIANG UNIV