Determining next best view based on occlusion information of a single depth image

被引：0

作者：

Zhang S.-H. ^{[1
,2
]}

Zhang Y.-C. ^{[1
]}

机构：

[1] School of Information Science and Technology, Yanshan University, Qinhuangdao, 066004, Hebei

[2] Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, Qinhuangdao, 066004, Hebei

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2016年 / 44卷 / 02期

关键词：

Depth image; External surface of occlusion region; Gradient descent method; Next best view; Occlusion information;

D O I：

10.3969/j.issn.0372-2112.2016.02.028

中图分类号：

学科分类号：

摘要：

How to determine camera's next best view based on current information is a challenging problem in visual field. A next best view approach was proposed based on the occlusion information of a single depth image. Firstly, to establish the model for occlusion region external surface, the quadrilateral meshes for occlusion region external surface were obtained according to the occlusion information of a depth image in initial view. Secondly, the model for next best view was constructed by considering both the visible quadrangle and the loss information in next view. Finally, the next best view was achieved by solving the model with gradient descent method. Compared with the existing methods, the proposed approach does not limit the camera position on a fixed surface or need the priori knowledge of visual object. Experimental results demonstrate its feasibility and effectiveness. © 2016, Chinese Institute of Electronics. All right reserved.

引用

页码：445 / 452

页数：7

共 13 条

[1]

Bottino A., Laurentini A., What's NEXT? An interactive next best view approach, Pattern Recognition, 39, 1, pp. 126-132, (2006)

[2]

Haner S., Heyden A., Covariance propagation and next best view planning for 3D reconstruction, Proceedings of the 12th European Conference on Computer Vision, pp. 545-556, (2012)

[3]

Connolly C., The determination of next best views, Proceedings of the IEEE International Conference on Robotics and Automation, pp. 432-435, (1985)

[4]

Maver J., Bajcsy R., Occlusion as a guide for planning the next view, IEEE Transactions on Pattern Analysis and Machine Intelligence, 15, 5, pp. 417-432, (1993)

[5]

Pito R., Solution to the next best view problem for automated surface acquisition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 21, 10, pp. 1016-1030, (1999)

[6]

Banta J.E., Wong L.M., Dumont C., Et al., Next-best-view system for autonomous 3-D object reconstruction, IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, 30, 5, pp. 589-598, (2000)

[7]

Chen S.Y., Li Y.F., Automatic sensor placement for model-based robot vision, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 34, 1, pp. 393-408, (2004)

[8]

Li Y.F., Liu Z.G., Information entropy-based viewpoint planning for 3-D object reconstruction, IEEE Transactions on Robotics, 21, 3, pp. 324-337, (2005)

[9]

Scott W.R., Model-based view planning, Machine Vision and Applications, 20, 1, pp. 47-69, (2009)

[10]

Vasquez-Gomez J.I., Sucar L.E., Murrieta-Cid R., Hierarchical ray tracing for fast volumetric next-best-view planning, Proceedings of the International Conference on Computer and Robot Vision, pp. 181-187, (2013)

← 1 2 →