A mobile robot image stitching method and device

Abstract

The invention discloses an image splicing method and device, which are suitable for binocular vision mobile robot platforms. The image splicing technology is used to splice images collected by the robot's binoculars, which can increase the robot's field of view and facilitate the robot to better complete positioning and environment. reconstruction. The method of the present invention includes: using SURF features to extract image sequence feature points to form feature vectors; searching the feature vector space to find feature matching points; using random sampling consistency algorithm (RANSAC) to robustly estimate transformation model parameters; using the transformation model to match The coordinate transformation of the quasi-image is carried out to realize the unification of the coordinates of the image sequence; according to the brightness value of the corresponding matching point, the transformation relationship that the brightness space of the image sequence satisfies is estimated to achieve exposure compensation; the pixel label method is used to determine the pixel value of the image overlapping area to achieve Splicing images to remove ghosts; generate image masks based on the optimal set of label values, and perform Laplacian pyramid fusion 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