Visual Distinctiveness Detection of Pedestrian based on Statistically Weighting PLSA for Intelligent Systems

초록

Intelligent Systems for autonomous vehicles including drone, robot vision, and video surveillance, need to distinguish pedestrian from other object. Pedestrian detection is an essential and significant research topic due to its diverse applications. In this paper, a new visual distinctiveness detection method for pedestrian is proposed based on the statistically weighting probabilistic latent semantic analysis. We detect the distinctiveness by integrating three steps as follows: first representing the co-ocurrence matrix of images, which were vectorized using the bag of visual words (BoVW) framework; then calculating the weights through the histograms of visual words of each class; and finally applying the weights to the test images as the distinctiveness of visual words. The probabilistic latent semantic analysis (PLSA) was used as classification method in our system. We extracted the weighted visual words by sampling the patches from the current image. The proposed method was compared to the PLSA using the Caltech 256 datasets. The classes used include pedestrians, cars, motorbikes, airplanes and horses. The results of the experiment show that the proposed method outperforms current methods in predicting pedestrians and transportation objects.

키워드