Vehicle Identification between Non-Overlapping Cameras without Direct Feature Matching

We propose a novel method for identifying road vehicles between two non-overlapping cameras. The problem is formulated as a same-different classification problem: probability of two vehicle images from two distinct cameras being from the same vehicle or from different vehicles. The key idea is to compute the probability without matching the two vehicle images directly, which is a process vulnerable to drastic appearance and aspect changes. We represent each vehicle image as an embedding amongst representative exemplars of vehicles within the same camera. The embedding is computed as a vector each of whose components is a non-metric distance for a vehicle to an exemplar. The non-metric distances are computed using robust matching of oriented edge images. A set of truthed training examples of same-different vehicle pairings across the two cameras is used to learn a classifier that encodes the probability distributions. A pair of the embeddings representing two vehicles across two camera...

• Type: Conference
• Year: 2005
• Where: ICCV
• Authors: Ying Shan, Harpreet S. Sawhney, Rakesh Kumar
• Keywords: Computer Vision, Distinct Cameras, ICCV 2005, Non-overlapping Cameras, Representative Exemplars, Vehicle Exemplars, Vehicle Images