Translator Disclaimer
Paper
23 May 2013 Invariant unsupervised segmentation of dismounts in depth images
Author Affiliations +
Abstract
This paper will describe a scene invariant method for the unsupervised segmentation of dismounts in depth images. This method can be broken into two parts: ground plane detection and spatial segmentation. The former is accomplished by using RANSAC (RANdom SAmple Consensus) to identify a ground plane in the scene. After performing contrast enhancement the Image is "sliced" into regions. Each classified region is processed by a Robert's edge detector in order to separate each object. Each output is further processed by a block of shape filters that extract the human form.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nathan S. Butler and Richard L. Tutwiler "Invariant unsupervised segmentation of dismounts in depth images", Proc. SPIE 8745, Signal Processing, Sensor Fusion, and Target Recognition XXII, 87451B (23 May 2013); https://doi.org/10.1117/12.2018187
PROCEEDINGS
14 PAGES


SHARE
Advertisement
Advertisement
Back to Top