Leveraging colour segmentation for upper-body detection

• We propose a novel approach for upper-body detection in images using multi-class colour segmentation features.
• Using these features and the output of classical shape-based detectors, a two-stage classification scheme is applied.
• Experimental results show a considerable improvement in accuracy on different challenging datasets.

This paper presents an upper-body detection algorithm that extends classical shape-based detectors through the use of additional semantic colour segmentation cues. More precisely, candidate upper-body image patches produced by a base detector are soft-segmented using a multi-class probabilistic colour segmentation algorithm that leverages spatial as well as colour prior distributions for different semantic object regions (skin, hair, clothing, background). These multi-class soft segmentation maps are then classified as true or false upper-bodies. By further fusing the score of this latter classifier with the base detection score, the method shows a performance improvement on three different public datasets and using two different upper-body base detectors, demonstrating the complementarity of the contextual semantic colour segmentation and the base detector.