GPU based parallel optimization for real time panoramic video stitching

Abstract

Panoramic video is a sort of video recorded at the same point of view to record the full scene. With the development of video surveillance and the requirement for 3D converged video surveillance in smart cities, CPU and GPU are required to possess strong processing abilities to make panoramic video. The traditional panoramic products depend on post processing, which results in high power consumption, low stability and unsatisfying performance in real time. In order to solve these problems,we propose a real-time panoramic video stitching framework.The framework we propose mainly consists of three algorithms, L-ORB image feature extraction algorithm, feature point matching algorithm based on LSH and GPU parallel video stitching algorithm based on CUDA.The experiment results show that the algorithm mentioned can improve the performance in the stages of feature extraction of images stitching and matching, the running speed of which is 11 times than that of the traditional ORB algorithm and 639 times than that of the traditional SIFT algorithm. Based on analyzing the GPU resources occupancy rate of each resolution image stitching, we further propose a stream parallel strategy to maximize the utilization of GPU resources. Compared with the L-ORB algorithm, the efficiency of this strategy is improved by 1.6-2.5 times, and it can make full use of GPU resources. The performance of the system accomplished in the paper is 29.2 times than that of the former embedded one, while the power dissipation is reduced to 10W.

A Novel Sobel Edge Detection Accelerator Based on Reconfigurable Architecture

“…The GPU is selected as the processing unit and the edge detection accelerator is designed. Although the processing capacity is slightly higher than that of CPU and FPGA, the power consumption is higher than that of CPU [24,25]. This further shows that the role of the high-performance CPU or GPU in enhancing the system performance is limited even though they continue to improve their performance or add more multicores, while the reconfigurable accelerator based on FPGA is an ideal choice for accelerating embedded graphics and image processing, which can meet the stringent requirements of power consumption and resources.…”

Research on Postproduction of Film and Television Based on Computer Multimedia Technology

“…e homography matrix not only determines the transformation relationship of points on two images but also directly determines the quality of stitched images. For the same mosaic image, or the image with little change in the position of pixels on the image, the homography matrix is almost the same [14]. From this feature, we can consider starting with the interframe similarity of video pictures and reducing repeated calculation by detecting repeated frame pictures, so as to improve the realtime performance of video splicing.…”

Automated crack evaluation of a high‐rise bridge pier using a ring‐type climbing robot

“…The conventional digital image stitching methods may work well if the target images contain distinctive and dominant features. For example, the target images that have dominant features such as city (Y. Zhang, Lai, & Zhang, 2020), buildings (Liao & Li, 2020), bridges, and mountains (Du et al., 2019) can be readily and successfully stitched using the conventional stitching algorithms. However, because the V R images are obtained at a very close distance from the target concrete surface in this study, dominant features for image stitching are difficult to be found especially from the pristine condition of the target surface.…”