Locating 3D Object Proposals: A Depth-Based Online Approach

TL;DR

This paper introduces a real-time online method for generating accurate 3D object proposals from RGB-D video sequences, leveraging depth and multi-view information to improve over existing techniques.

Contribution

A novel online approach that uses depth data and multi-view registration to produce precise 3D object proposals in near real-time.

Findings

Significantly more accurate than current state-of-the-art methods.

Operates in less than a second on standard hardware.

Suitable for integration into SLAM systems for quick 3D localization.

Abstract

2D object proposals, quickly detected regions in an image that likely contain an object of interest, are an effective approach for improving the computational efficiency and accuracy of object detection in color images. In this work, we propose a novel online method that generates 3D object proposals in a RGB-D video sequence. Our main observation is that depth images provide important information about the geometry of the scene. Diverging from the traditional goal of 2D object proposals to provide a high recall (lots of 2D bounding boxes near potential objects), we aim for precise 3D proposals. We leverage on depth information per frame and multi-view scene information to obtain accurate 3D object proposals. Using efficient but robust registration enables us to combine multiple frames of a scene in near real time and generate 3D bounding boxes for potential 3D regions of interest. Using standard metrics, such as Precision-Recall curves and F-measure, we show that the proposed approach is significantly more accurate than the current state-of-the-art techniques. Our online approach can be integrated into SLAM based video processing for quick 3D object localization. Our method takes less than a second in MATLAB on the UW-RGBD scene dataset on a single thread CPU and thus, has potential to be used in low-power chips in Unmanned Aerial Vehicles (UAVs), quadcopters, and drones.