Using BP Network for Occlusion Boundary Detection Based on Depth Image
ZHANG Shi-hui1,2,GENG Yong1,ZHANG Xiao-wei1
1. School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066004,China
2. The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province,Qinhuangdao, Hebei 066004,China
Abstract：Aiming at the occlusion phenomena existing in visual object, an occlusion boundary detection approach is proposed based on machine learning for depth image. Firstly, a novel occlusion related feature named the longest projected line segment is presented according to the depth and spatial information in depth image. Secondly, a nonlinear normalization method is designed to normalize the occlusion related features. Finally, the problem of occlusion boundary detection is taken as a classification problem, meanwhile, the back propagation(BP) neural network is utilized to detect the occlusion boundary and then the detection result is visualized. Compared with existing methods, the proposed approach is more accurate and the generalization performance is better.
［1］Silva L, Bellon O R P, Boyer K L. Multiview range image registration using the surface interpenetration mea-sure ［J］. Image & Vision Computing, 2007, 25 (1): 114-125.
［2］Szirmay-Kalos L, Umenhoffer T, Toth B, et al. Volu-metric Ambient Occlusion for Real-Time Rendering and Games ［J］. IEEE Computer Graphics & Applications, 2010, 30 (1): 70-79.
［3］Yi O. Multi-scale Human Detection Based on Window Gradient Potential Energy with Partial Occlusion Handling ［J］. Journal of Electronics & Information Technology, 2012, 34 (4): 858-864.
［4］Yang M, Zhang L, Shiu S C K, et al. Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary ［J］. Pattern Recognition, 2013, 46 (7): 1865-1878.
［5］邵伟,彭鹏,周阿维,等.工件表面低对比度缺陷快速准确识别方法［J］. 计量学报, 2019, 40 (5): 793-797.
Shao W, Peng P, Zhou A W, et al.Fast and Accurate Recognition of Low-contrast Defects Workpiece Surface［J］. Acta Metrologica Sinica, 2019, 40 (5): 793-797.
［6］Zhao Q, Yang Z, Tao H. Differential Earth Movers Distance with Its Applications to Visual Tracking ［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2010, 32 (2): 274-287.
［7］Yang M, Cao X, Dai Q. Multiview video depth estima-tion with spatial-temporal consistency ［C］//British Machine Vision Conference, Aberystwyth, UK, 2010, 1-11.
［8］He X, Yuille A. Occlusion boundary detection using pseudo-depth ［C］// Proceedings of the European Confer-ence on Computer Vision, Heidelberg, Germany, 2010, 539-552.
［9］Yang J, Wang J, Liu L, et al. RIFO: Restoring images with fence occlusions ［C］// IEEE International Work-shop on Multimedia Signal Processing, Xiamen, China, 2015, 1-6.
［10］Lee S J, Park K R, Kim J. A SfM-based 3D face recons-truction method robust to self-occlusion by using a shape conversion matrix ［J］. Pattern Recognition, 2011, 44 (7): 1470-1486.
［11］Hoiem D, Stein A N, Efros A A, et al. Recovering Occlusion Boundaries from an Image ［J］. International Journal of Computer Vision, 2011, 91 (3): 328-346.
［12］张世辉, 张煜婕, 孔令富. 一种基于深度图像的自遮挡检测方法 ［J］. 小型微型计算机系统, 2010, 31 (5): 964-968.
Zhang S H, Zhang Y J, Kong L F. A Self-occlusion Detection Approach Based on Depth Image ［J］. Journal of Chinese Computer Systems, 2010,31 (5): 964-968.
［13］张世辉, 杨青青, 何欢. 利用无监督聚类实现深度图像的遮挡边界检测 ［J］. 小型微型计算机系统, 2017, 38 (11): 2567-2572.
Zhang S H, Yang Q Q, He H. Occlusion Boundary Detection for Depth Image Utilizing Unsupervised Clust-ering ［J］. Journal of Chinese Computer Systems, 2017,38 (11): 2567-2572.
［14］张世辉, 庞云冲. 基于集成学习思想的深度图像遮挡边界检测方法 ［J］. 计量学报, 2014, 35 (6): 569-573.
Zhang S H , Pang Y C. Occlusion Boundary Detection Method for Depth Image Based on Ensemble Learning ［J］. Acta Metrologica Sinica, 2014, 35 (6): 569-573.
［15］张世辉, 张钰程, 张红桥,等.基于图的半监督学习的遮挡边界检测方法 ［J］. 计量学报, 2016, 37 (6): 576-581.
Zhang S H, Zhang Y C, Zhang H Q, et al. Occlusion Boundary Detection Using Graph-Based Semi-Supervised Learning ［J］. Acta Metrologica Sinica, 2016, 37 (6): 576-581.
［16］张世辉, 刘建新, 孔令富. 基于深度图像利用随机森林实现遮挡检测 ［J］. 光学学报, 2014, 34 (9): 0915003: 1-12.
Zhang S H, Liu J X, Kong L F. Using Random Forest for Occlusion Detection Based on Depth Image ［J］. Acta Optica Sinica, 2014, 34 (9): 0915003: 1-12.
［17］Zhang S H, Liu J X. A Self-Occlusion Detection App-roach Based on Depth Image Using SVM ［J］. Interna-tional Journal of Advanced Robotic Systems, 2012, 9 (6): 1-12.
2020, Vol. 41 
