Multi-viewpoint Silhouette Extraction with 3D Context-aware Error Detection, Correction, and Shadow Suppression

Abstract

This paper presents a novel approach for simultaneous silhouette extraction from multi-viewpoint images. The main contribution of this paper is a new algorithm for 1) 3D context aware error detection and correction of 2D multi-viewpoint silhouette extraction and 2) 3D context aware classification of cast shadow regions. Our method takes both monocular image segmentation and background subtraction of each viewpoint as its inputs, but does not assume they are correct. Inaccurate segmentation and background subtraction are corrected through our iterative method based on inter-viewpoint checking. Some experiments quantitatively demonstrate advantages against previous approaches.

False Image Suppression in Two-Dimensional Shape Estimates of a Walking Human Using Multiple Ultra-Wideband Doppler Radar Interferometers

“…In modern society, there is a wide range of applications for techniques that automatically monitor human movements, such as the prevention of terrorism and home healthcare. At present, many automatic monitoring systems use optical cameras [1], [2]. However, optical cameras cannot accurately identify the distance between the target and the camera, and cannot work in adverse conditions such as dim, smoky, and humid environments.…”

Two-Dimensional Imaging of a Pedestrian Using Multiple Wideband Doppler Interferometers with Clustering-Based Echo Association

“…The automatic monitoring of people has a wide range of applications including home health care and safety monitoring of workers in harsh environments [1], [2]. An ultrawideband (UWB) radar system has remarkable potential for the robust and reliable monitoring of people, because such systems, unlike optical cameras, can work in adverse environments such as dark, dusty and smoky locations with high humidity [3]- [6].…”