TY - GEN
T1 - A novel stereo vision sensor for fast moving objects
AU - Wu, Suining
AU - Liu, Zhen
AU - Ren, Yiming
AU - Wu, Qun
N1 - Publisher Copyright:
© 2018 ACM.
PY - 2018/4/23
Y1 - 2018/4/23
N2 - In this paper, we propose a novel stereo vision sensor for the automatic 3-D dynamic surface measurement, which is able to simultaneously acquire the 2-D scan image and the 3-D reconstruction results. The proposed system mainly concludes a line scan camera, a frame camera and two line lasers. Due to the application of line lasers, the proposed system is able to work accurate and stable under complex lighting condition. About our system, the view plane of line scan camera and the light plane of line laser are in coincidence. First, the calibration of intrinsic, extrinsic parameters and the light plane coefficients are obtained. Epipolar line is calculated to extract the accurate position of image point corresponding to each pixel of line scan camera. Finally, the 3-D shape is reconstructed according to binocular stereo vision model. The 2-D image and 3-D façade information can be synchronously acquired by scanning over objects. Physical experiments show that the proposed stereo vision sensor can provide robust and accurate results.
AB - In this paper, we propose a novel stereo vision sensor for the automatic 3-D dynamic surface measurement, which is able to simultaneously acquire the 2-D scan image and the 3-D reconstruction results. The proposed system mainly concludes a line scan camera, a frame camera and two line lasers. Due to the application of line lasers, the proposed system is able to work accurate and stable under complex lighting condition. About our system, the view plane of line scan camera and the light plane of line laser are in coincidence. First, the calibration of intrinsic, extrinsic parameters and the light plane coefficients are obtained. Epipolar line is calculated to extract the accurate position of image point corresponding to each pixel of line scan camera. Finally, the 3-D shape is reconstructed according to binocular stereo vision model. The 2-D image and 3-D façade information can be synchronously acquired by scanning over objects. Physical experiments show that the proposed stereo vision sensor can provide robust and accurate results.
KW - 2-D scan image
KW - 3-D surface reconstruction
KW - Dynamic measurement
KW - Stereo vision sensor
UR - https://www.scopus.com/pages/publications/85053677477
U2 - 10.1145/3220511.3220524
DO - 10.1145/3220511.3220524
M3 - 会议稿件
AN - SCOPUS:85053677477
SN - 9781450363815
T3 - ACM International Conference Proceeding Series
SP - 41
EP - 45
BT - ICMVA 2018 - Proceedings of 2018 International Conference on Machine Vision and Applications
PB - Association for Computing Machinery
T2 - 2018 International Conference on Machine Vision and Applications, ICMVA 2018
Y2 - 23 April 2018 through 25 April 2018
ER -