Outdoor scene understanding using SEVI-BOVW model

A simple and effective novel approach for scene understanding is addressed in this paper. Based on bag of visual words (BOVW) model, explicit semantics associated with the object image was embedded into visual words, and then various types of visual words integrated, and finally the SEVI-BOVW (semantics embedded and vocabulary integrated bag of visual words) model constructed. Mean Shift algorithm was employed to recognize local region image in scene. Compared with image understanding approaches presented in the literature, the proposed approach here can remove a classification or generative model during model training or testing. Objects category recognition can be determined by the number of class-specific semantic visual words, without complex reasoning. The effectiveness of the proposed approach has been demonstrated by the experimental results of scene understanding in a campus.