Abstract

Speckle dots have the advantage of easy projection, which makes them good candidate features of structured light (SL) cameras, such as Kinect v1. However, they generally yield poor accuracy due to block matching. To improve their accuracy, this paper proposes a dot-coded SL, the coding information of which is added into dot distribution. Some of the dots are arranged regularly to provide easy-to-locate corner features, while others are specially designed to form different shapes of unique identification. A Gaussian-cross module and a simplified ResNet have been proposed to conduct robust decoding. Various experiments are performed to verify the accuracy and robustness of our framework.

© 2020 Optical Society of America

Accurate infrared structured light sensing system for dynamic 3D acquisition

Yuping Ye, Hongguang Chang, Zhan Song, and Juan Zhao
Appl. Opt. 59(17) E80-E88 (2020)

3D shape, deformation, and vibration measurements using infrared Kinect sensors and digital image correlation

Hieu Nguyen, Zhaoyang Wang, Patrick Jones, and Bing Zhao
Appl. Opt. 56(32) 9030-9037 (2017)

3D reconstruction of objects with occlusion and surface reflection using a dual monocular structured light system

Kejing He, Congying Sui, Congyi Lyu, Zerui Wang, and Yunhui Liu
Appl. Opt. 59(29) 9259-9271 (2020)

Fast 3D reconstruction via event-based structured light with spatio-temporal coding

Jiacheng Fu, Yueyi Zhang, Yue Li, Jiacheng Li, and Zhiwei Xiong
Opt. Express 31(26) 44588-44602 (2023)

MIMONet: Structured-light 3D shape reconstruction by a multi-input multi-output network

Hieu Nguyen, Khanh L. Ly, Thanh Nguyen, Yuzheng Wang, and Zhaoyang Wang
Appl. Opt. 60(17) 5134-5144 (2021)