Sun Yat-Senuniversity

Qingsong Wang

Tao Lai

Haifeng Huang

Yijun Liu

Cuilin Yu

Haisong Weng

Ke Shi

Provided are a multimodal image matching method and system, terminal device, and storage medium. The method includes: performing self-supervised feature extraction on an optical image and a synthetic aperture radar (SAR) image to obtain a repetitive feature point between the optical image and the SAR image; segmenting the optical image and the SAR image into a first image block sequence based on the repetitive feature point, and performing feature extraction on the first image block sequence through a dual-branch network to obtain feature description vectors of the optical image and the SAR image respectively, where the dual-branch network includes a first branch network for extracting a global feature and a second branch network for extracting a local feature; and performing feature matching on the optical image and the SAR image based on the feature description vectors to obtain a matching point pair between the optical image and the SAR image.

Multimodal image matching method and system, terminal device, and storage medium

A method for determining a seam line of orthoimages, method for generating a mosaic image, device, and medium. The method includes: extracting valid area contours of a master image and a slave image respectively through a crawling search method; calculating difference values of valid pixels within an overlapping area between the master and slave images through a difference function, to obtain a difference map of the valid area; if there are more than two intersection points: calculating a position of a centroid of the overlapping area based on coordinates of each contour point of the intersection contour, determining a rectangular window centered on the centroid in the difference map, searching the rectangular window, and taking a position with a smallest difference value as an optimization end and the intersection points as optimization starts; determining, based on the optimization start and optimization end, a seam line through an A* algorithm.

Method for determining seam line of orthoimages, method for generating mosaic image of orthoimages, device thereof, and medium thereof

A multi-source elevation data fusion method including: inputting acquired optical elevation data into a trained optical elevation error prediction model to output an optical elevation error value and an optical elevation error weight map; inputting acquired radar elevation data into a trained radar elevation error prediction model to output a radar elevation error value and a radar elevation error weight map; correcting the optical elevation data based on the optical elevation error value to obtain optical elevation data to be fused; correcting the radar elevation data based on the radar elevation error value to obtain radar elevation data to be fused; performing weighted fusion on the optical elevation data to be fused and the radar elevation data to be fused based on the optical elevation error weight map and the radar elevation error weight map to obtain fused elevation data. This method efficiently enhances the accuracy of fused elevation data.

Growing community of inventors

Guangdong, China

Qingsong Wang