Learning Rich Features from RGB-D Images for Object Detection and Segmentation下载

In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features.We pro- pose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for each pixel in addition to the hor- izontal disparity. We demonstrate that this geocentric embedding works better than using raw depth images for learning feature representations with convolutional neural networks. Our nal object detection system achieves an average precision of 37.3%, which is a 56% relative improve- ment over existing methods. We then focus on the task of instance seg- mentation where we label pixels belonging to object instances found by our detector. For this task, we propose a decision forest approach that classies pixels in the detection window as foreground or background us- ing a family of unary and binary tests that query shape and geocentric pose features. Finally, we use the output from our object detectors in an existing superpixel classication framework for semantic scene segmenta- tion and achieve a 24% relative improvement over current state-of-the-art for the object categories that we study.We believe advances such as those represented in this paper will facilitate the use of perception in elds like robotics.