A mobile robot image stitching method and device

Abstract

The invention discloses an image stitching method and device. The image stitching method and device are suitable for a binocular vision mobile robot platform, images collected through two eyes of a robot are stitched through an image stitching technology, the view of the robot can be increased, and the robot can better finish locating and environment reestablishment conveniently. The method includes the steps that image sequence feature points are extracted through an SUPF feature to form a feature vector; the feature vector space is searched, and feature matching points are searched; model parameters are estimated and converted robustly through a random sample consensus (RANSAC) algorithm; coordinate conversion is conducted on the images to be matched through a conversion mode, and the coordinate unification of the image sequence is achieved; the conversion relation met by the image sequence brightness space is estimated according to the brightness value of the corresponding matching points to achieve exposure compensation; the image overlapping region pixel value is determined through a pixel label method, and ghost reduction of the stitched images is achieved; image masks are generated according to the optimal label value set, and Laplacian pyramid fusion is conducted on the images.

Description

technical field [0001] The invention belongs to the technical field of robot vision, and in particular relates to an image splicing method and device for a mobile robot. Background technique [0002] The positioning and environment reconstruction of mobile robots is the key technology to realize the robot's autonomous navigation and complete complex intelligent tasks in unknown environments. In practical applications, the monocular vision system is often unable to meet the needs of mobile robot positioning and environment reconstruction due to the influence of its small field of view. , so the binocular vision system is more favored by mobile robots. Using image stitching technology to stitch images collected by the robot's binoculars can increase the robot's field of vision and facilitate the robot's better positioning and environment reconstruction. Taking the "Yutu" lunar rover as an example, the "Yutu" is a special vehicle that travels on the surface of the moon and ins...

AI Technical Summary

Problems solved by technology

Due to the complex working environment of the mobile robot, three problems need to be solved when fusing the images acquired by the camera: first, due to different lighting conditions, the images often have different intensities, resulting in obvious stitching seams in the stitched images; second , it is often difficult to achieve perfect registration in the process of image registration, and wrong registration often leads to blurring of the fused image; thirdly, the existence of moving objects in the image acquisition process leads to ghosting of the fused image

The use of weighted average can easily lead to the loss of image detail information, resulting in blurred stitched images. In addition, when there are moving objects in the overlapping area of ​​the input image, the idea of ​​weighted average will inevitably lead to ghosting in the stitched image; another fusion strategy is The core idea of ​​the optimal stitching seam is to find a stitching seam in the overlapping area of ​​the registration image, and then select different input image information for both sides of the stitching image according to the location of the stitching seam.

Images