A fast and automatic splicing technology of aerial video in search and tracking system

Abstract

The invention brings forward a rapid and automatic mosaic technology of aerial video in a search and tracking system. The technology provided by the invention comprises the following steps: two continuous frames of color images in an aerial video sequence are converted to grayscale images; three-valued processing is carried out on the grayscale images by an image three-valued method, edge feature information images are extracted by an edge detection sobel operator and feature points are extracted by an Harris algorithm; feature point matching is completed by an optical flow pyramid algorithm; optimal homography matrix of the color images is calculated by combining a DLT algorithm and a RANSAC algorithm; panoramic image mosaics is completed after image correction of the color images by correction geometric transition matrix; and dynamic regulation of image three-valued upper and lower thresholds and a threshold of the edge detection sobel operator is carried out during the process of panoramic image mosaics. According to the invention, image mosaic accuracy and robustness are raised.

Description

technical field [0001] The invention belongs to the technical field of automatic image splicing, and in particular relates to a fast automatic splicing technology of aerial video in a search and track system. Background technique [0002] The most critical step in image stitching is to find and match image feature points. Yang Tao et al. (Real-time Registration Algorithm for Aerial Video Based on Scene Complexity and Invariant Features. Acta Electronics, 2010.5, Volume 5, Volume 38) proposed a method of image matching using the combination of Harris corners and SIFT descriptors, ensuring The algorithm has good rotation, scale, brightness invariance and registration accuracy. However, due to the large number of feature points extracted in the early stage, the amount of calculation in the later stage is too large, and the real-time performance of image stitching cannot be truly realized. To solve this problem, it is necessary to optimize the algorithm by simplifying the extr...

AI Technical Summary

Problems solved by technology

This method has a good stitching effect for image sequences with a small number of frames, but as the number of frames in the video sequence increases, the geometric transformation matrix of image stitching will accumulate and magnify errors due to continuous superposition in the early stage; At the same time, due to the jitter of the aircraft and obvious scene changes, the accuracy of image stitching will also decrease, and it will also cause the interruption of the image stitching process.

Images