Implementation of a Pedestrian Detection Device based on CENTRIST for an Embedded Environment

Abstract

Abstract. This paper proposes implementation of CENTRIST-based pedestrian detection in embedded environments. Although a considerable number of pedestrian detection algorithms have been proposed, they are not suitable for implementation in embedded environments. In this paper proposes a CENTRIST-based pedestrian detection method which combines census transform and histogram, instead of the HOG method, which is more complicated. An Aldebaran board (300MHz) was used for implemntation of the algorithm in embedded enviornments, and the 512x360 pixel input image was used. The implemented algorithm demonstrated performance of 0.7 frame per second.

An Implementation of SIMT Based Image Signal Processor for Pedestrian Detection

“…The pedestrian recognition algorithm used in the image data has less limitation on the data dependency to be appropriate for parallel processing. Figure 4 shows the parallel processing process of Sobel, Census Transform and Histogram in the CENTRIST based pedestrian recognition algorithms [3,4]. Sobel and Census Transform algorithms basically use 3 x 3 size to perform the convolution operation.…”