Authors:
Michael Korn
;
Daniel Sanders
and
Josef Pauli
Affiliation:
University of Duisburg-Essen, Germany
Keyword(s):
3D Object Detection, Iterative Closest Point (ICP), Point Cloud Registration, Connected Component Labeling (CCL), Depth Images, GPU, CUDA.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Geometry and Modeling
;
Image and Video Analysis
;
Image Registration
;
Image-Based Modeling
;
Pattern Recognition
;
Segmentation and Grouping
;
Software Engineering
Abstract:
Using a depth camera, the KinectFusion with Moving Objects Tracking (KinFu MOT) algorithm permits
tracking the camera poses and building a dense 3D reconstruction of the environment which can also contain
moving objects. The GPU processing pipeline allows this simultaneously and in real-time. During the reconstruction,
yet untraced moving objects are detected and new models are initialized. The original approach to
detect unknown moving objects is not very precise and may include wrong vertices. This paper describes an
improvement of the detection based on connected component labeling (CCL) on the GPU. To achieve this,
three CCL algorithms are compared. Afterwards, the migration into KinFu MOT is described. It incorporates
the 3D structure of the scene and three plausibility criteria refine the detection. In addition, potential
benefits on the CCL runtime of CUDA Dynamic Parallelism and of skipping termination condition checks are
investigated. Finally, the enhancement of the detecti
on performance and the reduction of response time and
computational effort is shown.
(More)