Wang Xinhua, Li Dayu, Zhang Guang
School of Computer Science, Northeast Electric Power University, Jilin 132012, China.
State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China.
Sensors (Basel). 2021 Mar 10;21(6):1944. doi: 10.3390/s21061944.
With the rapid development of the virtual reality industry, one of the bottlenecks is the scarcity of video resources. How to capture high-definition panoramic video with depth information and real-time stereo display has become a key technical problem to be solved. In this paper, the optical optimization design scheme of panoramic imaging based on binocular stereo vision is proposed. Combined with the real-time processing algorithm of multi detector mosaic panoramic stereo imaging image, a panoramic stereo real-time imaging system is developed. Firstly, the optical optimization design scheme of panoramic imaging based on binocular stereo vision is proposed, and the space coordinate calibration platform of ultra-high precision panoramic camera based on theodolite angle compensation function is constructed. The projection matrix of adjacent cameras is obtained by solving the imaging principle of binocular stereo vision. Then, a real-time registration algorithm of multi-detector mosaic image and Lucas-Kanade optical flow method based on image segmentation are proposed to realize stereo matching and depth information estimation of panoramic imaging, and the estimation results are analyzed effectively. Experimental results show that the stereo matching time of panoramic imaging is 30 ms, the registration accuracy is 0.1 pixel, the edge information of depth map is clearer, and it can meet the imaging requirements of different lighting conditions.
随着虚拟现实产业的快速发展,其中一个瓶颈是视频资源的稀缺。如何获取具有深度信息的高清全景视频并进行实时立体显示已成为亟待解决的关键技术问题。本文提出了基于双目立体视觉的全景成像光学优化设计方案。结合多探测器拼接全景立体成像图像的实时处理算法,开发了一种全景立体实时成像系统。首先,提出基于双目立体视觉的全景成像光学优化设计方案,构建基于经纬仪角度补偿功能的超高精度全景相机空间坐标标定平台。通过求解双目立体视觉成像原理得到相邻相机的投影矩阵。然后,提出一种基于图像分割的多探测器拼接图像实时配准算法和Lucas-Kanade光流法,实现全景成像的立体匹配和深度信息估计,并对估计结果进行有效分析。实验结果表明,全景成像的立体匹配时间为30毫秒,配准精度为0.1像素,深度图的边缘信息更清晰,能够满足不同光照条件下的成像要求。