GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method

Abstract

Visual odometry aims to track the incremental motion of an object using the information captured by visual sensors. In this work, we study the point cloud odometry problem, where only the point cloud scans obtained by the LiDAR (Light Detection And Ranging) are used to estimate object's motion trajectory. A lightweight point cloud odometry solution is proposed and named the green point cloud odometry (GPCO) method. GPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans. It consists of three steps. First, a geometry-aware point sampling scheme is used to select discriminant points from the large point cloud. Second, the view is partitioned into four regions surrounding the object, and the PointHop++ method is used to extract point features. Third, point correspondences are established to estimate object motion between two consecutive scans. Experiments on the KITTI dataset are conducted to demonstrate the effectiveness of the GPCO method. It is observed that GPCO outperforms benchmarking deep learning methods in accuracy while it has a significantly smaller model size and less training time.

PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimation

“…As an alternative to deep learning, successive subspace learning (SSL) has been proposed for point cloud processing. Its potential was demonstrated in PointHop [17], PointHop++ [18], SPA [19], R-PointHop [1] and GPCO [20]. The unsupervised feature learning in SSL consists of attribute construction, neighborhood expansion, and dimensionality reduction using the Saab transform.…”

“…Yet, we observe that the 24D attribute vector is sensitive to noise and unable to capture complex local surface patterns for distinction. A modified version that appends point coordinates with eigen features was used for indoor scene registration and odometry [20]. Actually, histogram-based point descriptors such as SHOT (Signature Histogram of Orientations) [4] and FPFH (Fast Point Feature Histogram) [3] have been widely used to describe the local surface geometry.…”