Scale and rotation invariant color features for weakly-supervised object Learning in 3D space
Scale and rotation invariant color features for weakly-supervised object Learning in 3D space
复制标题
DOI：
10.1109/iccvw.2011.6130300
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Asako Kanezaki;T. Harada;Y. Kuniyoshi
中科院分区：
文献类型：
--
作者：
Asako Kanezaki;T. Harada;Y. Kuniyoshi
提出了一种基于3D颜色纹理特征和基于几何分割的联合学习方法，用于弱标注3D颜色数据集的目标分类和定位。最近，像微软的Kinect这样的新消费类相机不仅能产生彩色图像，还能产生深度图像。这大大降低了目标检测的难度，原因如下：(A)通过检测空间不连续性可以给出合理的候选对象段，以及(B)可以提取对视点变化具有鲁棒性的3D特征。该方法通过评估3D点的表面法线之间的角度差异来列出候选线段，从每个线段提取全局3D特征，并使用附加有3D颜色场景的对象标签的多实例学习来学习对象分类器。实验结果表明，特征的旋转不变性和尺度不变性是解决这一问题的关键。
We propose a joint learning method for object classification and localization using 3D color texture features and geometry-based segmentation from weakly-labeled 3D color datasets. Recently, new consumer cameras such as Microsoft's Kinect produce not only color images but also depth images. These reduce the difficulty of object detection dramatically for the following reasons: (a) reasonable candidates for object segments can be given by detecting spatial discontinuity, and (b) 3D features that are robust to view-point variance can be extracted. The proposed method lists candidate segments by evaluating difference in angle between the surface normals of 3D points, extracts global 3D features from each segment, and learns object classifiers using Multiple Instance Learning with object labels attached to 3D color scenes. Experimental results show that the rotation invariance and scale invariance of features are crucial for solving this problem.