Detecting moving spheres in 3D point clouds via the 3D velocity Hough Transform

Abstract

We present a new approach to extracting moving spheres from a sequence of 3D point clouds. The new 3D velocity Hough Transform (3DVHT) incorporates motion parameters in addition to structural parameters in an evidence gathering process to accurately detect moving spheres at any given point cloud from the sequence. We demonstrate its capability to detect spheres which are obscured within the sequence of point clouds, which conventional approaches cannot achieve. We apply our algorithm on real and synthetic data and demonstrate the ability of detecting fully occluded spheres by exploiting inter-frame correlation within the 3D point cloud sequence.

3D Moving Object Reconstruction by Temporal Accumulation

“…[16] perform temporal evidence accumulation on stereo image sequences for extraction of specified objects undergoing linear motion. Temporal accumulation was used in [17] within an evidence gathering algorithm which incorporates structural and motion parameters to detect moving spheres in point cloud sequences. A colour-augmented search algorithm is used in [18] to accumulate coloured point clouds from successive time frames for a moving vehicle, to track the vehicle and build 3D a model of it.…”