Transportation Object Detection with Bag of Visual Words Model by PLSA and MLP

Abstract

Visual big data is an essential and significant research topic, due to its diverse applications. In this paper, a new visual detection method for transportation is proposed based on probabilistic latent semantic analysis with visual data. 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 histograms of the visual words of each class; and finally applying the test images as the visual words. A multilayer perceptron (MLP) is used as the classification method in our system. The visual words are extracted by sampling the patches from the current image. A new topology of the neural network for the BoVW model is proposed, and management of the learning rate by reducing at specific iterations is exploited. The Probabilistic latent semantic analysis (PLSA) is compared to the MLP using the Caltech 256 datasets. The classes used include cars, motorbikes, and horses. The results of the experiment show that the MLP outperforms current methods in predicting transportation objects, and properly approximates the transportation detection function with extracted local features. It shows that the proposed method yields about 4.4% higher accuracy than the conventional PLSA for all classes.