利用視覺目標遮擋和輪廓信息確定下一最佳觀測方位
doi: 10.11999/JEIT150190 cstr: 32379.14.JEIT150190
-
2.
(燕山大學(xué)信息科學(xué)與工程學(xué)院 秦皇島 066004) ②(河北省計算機虛擬技術(shù)與系統(tǒng)集成重點實驗室 秦皇島 066004)
基金項目:
國家自然科學(xué)基金(61379065)和河北省自然科學(xué)基金 (F2014203119)
Determining Next Best View Using Occlusion and Contour Information of Visual Object
-
2.
(School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China)
Funds:
The National Natural Science Foundation of China (61379065)
-
摘要: 下一最佳觀測方位的確定是視覺領(lǐng)域一個比較困難的問題。該文提出一種基于視覺目標深度圖像利用遮擋和輪廓信息確定下一最佳觀測方位的方法。該方法首先對當(dāng)前觀測方位下獲取的視覺目標深度圖像進行遮擋檢測。其次根據(jù)深度圖像遮擋檢測結(jié)果和視覺目標輪廓構(gòu)建未知區(qū)域，并采用類三角剖分方式對各未知區(qū)域進行建模。然后根據(jù)建模所得的各小三角形的中點、法向量、面積等信息構(gòu)造目標函數(shù)。最后通過對目標函數(shù)的優(yōu)化求解得到下一最佳觀測方位。實驗結(jié)果表明所提方法可行且有效。Abstract: Determining cameras next best view is a difficult issue in visual field. A next best view approach based on depth image of visual object is proposed by using occlusion and contour information in this paper. Firstly, the occlusion detection is accomplished for the depth image of visual object in current view. Secondly, the unknown regions are constructed according to the occlusion detection result of the depth image and the contour of the visual object, and then the unknown regions are modeled with triangulation-like. Thirdly, the midpoint, normal vector and area of each small triangle and other information are utilized to establish the objective function. Finally, the next best view is obtained by optimizing objective function. Experimental results demonstrate that the approach is feasible and effective.
-
Key words:
- Depth image /
- Occlusion /
- Contour /
- Unknown regions /
- Triangulation-like /
- Next best view
-
Bottino A and Laurentini A. What is next an interactive next best view approach[J]. Pattern Recognition, 2006, 39(1): 126-132. Pintilie G D and Stuerzlinger W. An evaluation of interactive and automated next best view methods in 3D scanning[J]. Computer-Aided Design and Applications, 2013, 10(2): 279-291. 曾明勇, 吳澤民, 田暢, 等. 基于外觀統(tǒng)計特征融合的人體目標再識別[J]. 電子與信息學(xué)報, 2014, 36(8): 1844-1851. Zeng Ming-yong, Wu Ze-min, Tian Chang, et al.. Fusing appearance statistical features for person re-identification[J]. Journal of Electronics Information Technology, 2014, 36(8): 1844-1851. 李烈辰, 李道京. 基于壓縮感知的連續(xù)場景稀疏陣列SAR三維成像[J]. 電子與信息學(xué)報, 2014, 36(9): 2166-2172. Li Lie-Chen and Li Dao-jing. Sparse array SAR 3D imaging for continuous scene based on compressed sensing[J]. Journal of Electronics Information Technology, 2014, 36(9): 2166-2172. Trummer M, Munkelt C, and Denzler J. Online next-best-view planning for accuracy optimization using an extended E-criterion[C]. Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey, 2010: 1642-1645. Haner S and Heyden A. Covariance propagation and next best view planning for 3D reconstruction[C]. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy, 2012: 545-556. Connolly C. The determination of next best views[C]. Proceedings of the IEEE International Conference on Robotics and Automation, Missouri, USA, 1985: 432-435. Maver J and Bajcsy R. Occlusion as a guide for planning the next view[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(5): 417-432. Banta J E, Wong L M, Dumont C, et al.. A next-best-view system for autonomous 3-D object reconstruction[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, 2000, 30(5): 589-598. Li Y F and Liu Z G. Information entropy-based viewpoint planning for 3-D object reconstruction[J]. IEEE Transactions on Robotics, 2005, 21(3): 324-337. Vasquez-Gomez J I, Sucar L E, and Murrieta-Cid R. Hierarchical ray tracing for fast volumetric next-best-view planning[C]. Proceedings of the International Conference on Computer and Robot Vision, Regina, SK, Canada, 2013: 181-187. Potthast C and Sukhatme G. A probabilistic framework for next best view estimation in a cluttered environment[J]. Journal of Visual Communication and Image Representation, 2014, 25(1): 148-164. 張世輝, 劉建新, 孔令富. 基于深度圖像利用隨機森林實現(xiàn)遮擋檢測[J]. 光學(xué)學(xué)報, 2014, 34(9): 0915003: 1-12. Zhang Shi-hui, Liu Jian-xin, and Kong Ling-fu. Using random forest for occlusion detection based on depth image[J]. Acta Optica Sinica, 2014, 34(9): 0915003: 1-12. Curtis F and Overton M. A sequential quadratic programming algorithm for nonconvex, nonsmooth constrained optimization[J]. SIAM Journal on Optimization, 2012, 22(2): 474-500. Hetzel G, Leibe B, Levi P, et al.. 3D object recognition from range images using local feature histograms[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2001: II394-II399. -
計量
- 文章訪問數(shù): 1341
- HTML全文瀏覽量: 149
- PDF下載量: 586
- 被引次數(shù): 0
下載:
