An efficient LBP-based descriptor for real-time object detection

This paper presents a novel method for interest region description which is based on the idea that the appearance of an interest region can be well characterized by the distribution of its local features. We introduce a new texture feature called Grid of Local Binary Patterns (GoLBP) that is a modified version of the well-known Local Binary Pattern (LBP) feature. Experiments show that, the proposed descriptor can be used for the real-time vehicle detection in Vietnam.