No abstract

Abstract. Many machine vision applications deal with depth estimation in a scene. Disparity map recovery from a stereo image pair has been extensively studied by the computer vision community. Previous methods are mainly restricted to software based techniques on general-purpose architectures, presenting relatively high execution time due to the computationally complex algorithms involved. In this paper a new hardware module suitable for real-time disparity map computation module is realized. This enables a hardware based occlusion-aware parallel-pipelined design, implemented on a single FPGA device with a typical operating frequency of 511 MHz. It provides accurate disparity map computation at a rate of 768 frames per second, given a stereo image pair with a disparity range of 80 pixels and 640x480 pixel spatial resolution. The proposed method allows a fast disparity map computational module to be built, enabling a suitable module for real-time stereo vision applications.

No abstract

The demographic change situation in Germany, as well as in other leading industrial nations, leads to an overload of the family and institutionalized nursing care system structure. For this reason, novel solutions must be developed, in order to guarantee fully independent living of the elderly people, and an efficient assistance or nursing, in diverse living environments. The research project LISA has investigated the possibilities to embed mechatronic, assistive functions and services into compact wall "terminal" elements thereby enabling autonomous and independent living upon performing Activities of Daily Living (ADLs) by means of generated structured environments and robotic micro-rooms (RmRs). In this article, a classification of the approach in the broader context of research, as well as a statement of methodical and structured multi-phase development are described. The conceptual and development phases and the technical details using selected assistive functions of the entire system are presented. The article explains the methodical approach throughout the four phases of development and focuses on essential field trials with collected user feedback.

No abstract