Large-Scale Vehicle Detection in Challenging Urban Surveillance Environments
Rogerio Feris, James Petterson, Behjat Siddiquie, Lisa Brown and Sharath Pankanti
In: WACV, 5-6 Jan 2011, Kona, Hawaii.
We present a novel approach for vehicle detection in urban surveillance videos, capable of handling unstructured and crowded environments with large occlusions, different vehicle shapes, and environmental conditions such as lighting changes, rain, shadows, and reﬂections. This is achieved with virtually no manual labeling efforts. The system runs quite efﬁciently at an average of 66Hz on a conventional laptop computer. Our proposed approach relies on three key contributions: 1) a co-training scheme where data is automatically captured based on motion and shape cues and used to train a detector based on appearance information; 2) an occlusion handling technique based on synthetically generated training samples obtained through Poisson image reconstruction from image gradients; 3) massively parallel feature selection over multiple feature planes which allows the ﬁnal detector to be more accurate and more efﬁcient. We perform a comprehensive quantitative analysis to validate our approach, showing its usefulness in realistic urban surveillance settings.