Title: Depth information acquisition and image measurement algorithm using microarray camera

Authors: Jiancheng Zou; Peizhou Yan; Zhengzheng Li

Addresses: Beijing Key Laboratory of Urban Road Traffic Intelligent Control Technology, North China University of Technology, Beijing, 100043, China ' Beijing Key Laboratory of Urban Road Traffic Intelligent Control Technology, North China University of Technology, Beijing, 100043, China ' Beijing Key Laboratory of Urban Road Traffic Intelligent Control Technology, North China University of Technology, Beijing, 100043, China

Abstract: The traditional algorithm for obtaining the depth information of an image is a binocular stereo vision algorithm. Meanwhile, the multi-eye stereo vision system can obtain more scene information. Based on the 3 × 3 array lens, we obtained the depth information of static and dynamic scenes and applied the depth map to image measurement. First, the single calibration of 9 sub-lenses and the stereo calibration of each lens with the central lens are carried out. Second, a corresponding energy cost function is established to construct a Markov random field. Then, the graph-cutting algorithm is applied to minimise the energy function, select the optimal matching value, and then to get the matching graph with depth information. Finally, the measurement of the target in the scene is obtained based on the depth map. The experimental results show that the proposed method can get more accurate depth information than monocular and binocular cameras.

Keywords: microarray camera; Markov random field; graph cut; depth information; image measurement.

DOI: 10.1504/IJAACS.2023.134112

International Journal of Autonomous and Adaptive Communications Systems, 2023 Vol.16 No.5, pp.419 - 435

Received: 01 Jun 2021
Accepted: 27 Aug 2021
Published online: 11 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article