PrincetonComputer SciencePIXL GroupPublications → [Song et al. 2014] Local Access
Sliding Shapes for 3D Object Detection in Depth Images

European Conference on Computer Vision (ECCV) oral presentation, September 2014

Shuran Song, Jianxiong Xiao
Abstract

The depth information of RGB-D sensors has greatly simplified some common challenges in computer vision and enabled breakthroughs for several tasks. In this paper, we propose to use depth maps for object detection and design a 3D detector to overcome the major difficulties for recognition, namely the variations of texture, illumination, shape, viewpoint, clutter, occlusion, selfocclusion and sensor noises. We take a collection of 3D CAD models and render each CAD model from hundreds of viewpoints to obtain synthetic depth maps. For each depth rendering, we extract features from the 3D point cloud and train an Exemplar-SVM classifier. During testing and hard-negative mining, we slide a 3D detection window in 3D space. Experiment results show that our 3D detector significantly outperforms the state-of-the-art algorithms for both RGB and RGBD images, and achieves about x1.7 improvement on average precision compared to DPM and R-CNN. All source code and data are available online.
Citation

Shuran Song and Jianxiong Xiao.
"Sliding Shapes for 3D Object Detection in Depth Images."
European Conference on Computer Vision (ECCV) oral presentation, September 2014.

BibTeX

@inproceedings{Song:2014:SSF,
   author = "Shuran Song and Jianxiong Xiao",
   title = "Sliding Shapes for {3D} Object Detection in Depth Images",
   booktitle = "European Conference on Computer Vision (ECCV) oral presentation",
   year = "2014",
   month = sep
}