基于深度图像利用随机森林实现遮挡检测

提出了一种新颖的利用随机森林检测深度图像中遮挡现象的方法。该方法从一幅深度图像中提取每个像素点的遮挡相关特征，利用随机森林分类器检测每个像素点是否为遮挡边界点，得到图像中的遮挡边界。主要贡献在于：提出了一种新的遮挡相关特征深度值离散度特征，同时引入高斯曲率特征，并将它们与现有特征相结合来检测遮挡边界；以特征重要性和特征提取时间为衡量标准，对深度图像中的各遮挡相关特征进行了分析评估，在此基础上，选取平均深度差、最大深度差、平均曲率、高斯曲率和深度值离散度5种特征用于设计遮挡检测分类器；一种新的遮挡检测方法，利用随机森林解决深度图像的遮挡检测问题。实验结果表明，同已有方法相比，所提方法具有较高的准确性和较好的通用性。

Abstract

A novel occlusion detection approach is proposed for depth image by using Random Forest. The occlusion related features of each pixel in the depth image are extracted, and then the Random Forest classifier is used for detecting whether each pixel is an occlusion boundary point or not. All the occlusion boundaries in the input depth image are obtained. This work is distinguished by three contributions. A new occlusion related feature named depth dispersion is proposed and the Gaussian curvature feature is introduced, and both of them are used for occlusion detection by combining with other features. All the occlusion related features in depth image are analyzed and evaluated by using the importance and extraction time as criterion. On this basis, five features such as average depth difference, maximal depth difference, mean curvature, Gaussian curvature and depth dispersion are selected for designing the occlusion detection classifier. A new occlusion detection approach takes the Random Forest to solve occlusion detection problem in depth image. The experimental results show that, compared with the existing methods, the proposed approach has higher accuracy and better generality.

参考文献

[1] S J Lee, K R Park, J Kim. A SfM-based 3D face reconstruction method robust to self-occlusion by using a shape conversion matrix [J]. Pattern Recognition, 2011, 44(7): 1470-1486.

[2] C Schmaltz, B Rosenhahn, T Brox, et al.. Region-based pose tracking with occlusions using 3D models [J]. Machine Vision and Applications, 2012, 23(3): 557-577.

[3] 魏新国, 刘涛, 刘震. 基于平面圆靶标的三维数据拼接[J]. 光学学报, 2013, 33(2): 0215002.

Wei Xinguo, Liu Tao, Liu Zhen. Three-dimensional measurement data registration based on planar circle target [J]. Acta Optica Sinica, 2013, 33(2): 0215002.

[4] A Gupta, A Mittal, L S Davis. Constraint integration for efficient multiview pose estimation with self-occlusions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(3): 493-506.

[5] L Szirmay-Kalos, T Umenhoffer, B Tóth, et al.. Volumetric ambient occlusion for real-time rendering and games [J]. IEEE Computer Graphics and Applications, 2010, 30(1): 70-79.

[6] J J McAuley, T S Caetano. Fast matching of large point sets under occlusions [J]. Pattern Recognition, 2012, 45(1): 563-569.

[7] A Stein, M Hebert. Occlusion boundaries from motion: low-level detection and mid-level reasoning [J]. International Journal of Computer Vision, 2009, 82(3): 325-357.

[8] D Hoiem, A Efros, M Hebert. Recovering occlusion boundaries from an image [J]. International Journal of Computer Vision, 2011, 91(3): 328-346.

[9] A Ayvaci, M Raptis, S Soatto. Sparse occlusion detection with optical flow [J]. International Journal of Computer Vision, 2012, 97(3): 322-338.

[10] Y Liu. Automatic range image registration in the Markov chain [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(1): 12-29.

[11] I Y Jang, J H Cho, K H Lee. 3D human modeling from a single depth image dealing with self-occlusion [J]. Multimedia Tools and Applications, 2012, 58(1): 267-288.

[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 Shihui, Zhang Yujie, Kong Lingfu. Self-occlusion detection approach based on depth image [J]. Journal of Chinese Computer System, 2010, 31(5): 964-968.

[13] 张世辉, 张煜婕, 孔令富. 结合深度图像和最佳分割阈值迭代的自遮挡检测算法[J]. 高技术通讯, 2010, 20(7): 754-757.

Zhang Shihui, Zhang Yujie, Kong Lingfu. Self-occlusion detection algorithm combining depth image and optimal segmentation threshold iteration [J]. Chinese High Technology Letters, 2010, 20(7): 754-757.

[14] S Zhang, F Gao, L Kong. A self-occlusion detection approach based on range image of vision object [J]. ICIC Express Letters, 2011, 5(6): 2041-2046.

[15] S Zhang, J Liu. A self-occlusion detection approach based on depth image using SVM [J]. International Journal of Advanced Robotic Systems, 2012, 9(12): 1-8.

[16] P J Besl, R C Jain. Segmentation through variable-order surface fitting [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988, 10(2): 167-192.

[17] L Breiman. Random forests [J]. Machine Learning, 2001, 45(1): 5-32.

[18] G Hetzel, B Leibe, P Levi, et al.. 3D object recognition from range images using local feature histrograms [C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, 2: II394-II399.

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. Zhang Shihui, Liu Jianxin, Kong Lingfu. Using Random Forest for Occlusion Detection Based on Depth Image[J]. Acta Optica Sinica, 2014, 34(9): 0915003.

基于深度图像利用随机森林实现遮挡检测

关于本站 Cookie 的使用提示

全站搜索

基于深度图像利用随机森林实现遮挡检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索