An efficient algorithm for the extraction of contours and curvature scale space on SIMD-powered Smart Cameras

Abstract

SIMD (single instruction multiple data) processors have been shown to possess high capability for vector-based image processing due to their massively parallel architecture. However, it is not always easy to map the general-purpose processor implementations of high-level vision algorithms to such processors due to the hardware-imposed characteristics of SIMD processors. In this paper, our focus is on contour extraction algorithms for such processors. We present a novel real-time memory-efficient contour extraction algorithm that is suitable for the SIMD processor used in the WiCa camera developed by NXP. A further goal of this paper is to present a method for extracting the curvature scale space (CSS) on the same SIMD processor. For contour extraction, the detected contour points are first stored as they are detected, and then effectively reordered with low memory overhead. For extracting the CSS, we introduce a high-precision Gaussian filtering scheme using an extended number representation that is particularly suited for the SIMD processor of the camera. We demonstrate both in real time.