Scene Recognition Using Multiple Object Classifiers

摘要

Outdoor scene recognition represents a challenging task in computer vision, especially due to the nature of the problem it wants to solve. Many factors can affect the successful recognition of a scene, especially the fact that in one scene one can find a variety of objects. This paper tries to solve the problem of scene recognition by applying a multilayer object detection and recognition framework. We have trained this system using multiple images from our universities campus and this paper presents the results as well as provides a path for future advancement.