Object Detection Using a Max-Margin Hough Transform
Source: UC Regents
The authors present a discriminative Hough transform based object detector where each local part casts a weighted vote for the possible locations of the object center. They show that the weights can be learned in a max-margin framework which directly optimizes the classification performance. The discriminative training takes into account both the codebook appearance and the spatial distribution of its position with respect to the object center to derive its importance. On various datasets they show that the discriminative training improves the Hough detector.