Sparse Depth Odometry: 3D keypoint based pose estimation from dense depth data

This paper presents Sparse Depth Odometry (SDO) to incrementally estimate the 3D pose of a depth camera in indoor environments. SDO relies on 3D keypoints extracted on dense depth data and hence can be used to augment the RGB-D camera based visual odometry methods that fail in places where there is no proper illumination. In SDO, our main contribution is the design of the keypoint detection module, which plays a vital role as it condenses the input point cloud to a few keypoints. SDO differs from existing depth alone methods as it does not use the popular signed distance function and can run online, even without a GPU. A new keypoint detection module is proposed via keypoint selection, and is based on extensive theoretical and experimental evaluation. The proposed keypoint detection module comprises of two existing keypoint detectors, namely SURE [1] and NARF [2]. It offers reliable keypoints that describe the scene more comprehensively, compared to others. Finally, an extensive performance evaluation of SDO on benchmark datasets with the proposed keypoint detection module is presented and compared with the state-of-the-art.

Authors

• Sai Manoj Prakhya
• Bingbing Liu
• Weisi Lin
• Usman Qayyum

Keywords

• Detectors
• Three-dimensional displays
• Estimation
• Cameras
• Visualization
• Covariance matrices
• Computational modeling
• Density Data
• Depth Data
• Pose Estimation
• 3D Keypoints
• Sparse Depth
• Point Cloud
• Visual Methods
• Indoor Environments
• Extensive Evaluation
• Depth Camera
• Camera Pose
• Keypoint Detection
• Input Point Cloud
• Visual Odometry
• Signed Distance Function
• Extensive Experimental Evaluation
• Covariance Matrix
• Visual Analysis
• Singular Value Decomposition
• Uneven Surface
• RGB Images
• Iterative Closest Point
• Depth Information
• Sparse Method
• Random Sample Consensus
• Depth Images
• Spindle Shape
• Loop Closure
• Translation Error
• RGB Information