Computer Vision Talks at Columbia University

The Optimal Distance Measure for Object Detection

Shyjan Mahamud

CMU, USA

CAVE Lab, 6th Floor CEPSR 

Host: Prof. Shree Nayar 

Abstract 

The reliable detection of an object of interest in an input image with arbitrary background clutter and occlusion has to a large extent remained an elusive goal in computer vision. Traditional model-based approaches are inappropriate for a multi-class object detection task primarily due to difficulties in modeling arbitrary object classes. Instead, we develop a detection framework whose core component is a nearest neighbor search over object parts. The performance of the overall system is critically dependent on the distance measure used in the nearest neighbor search.

A distance measure that minimizes the mis-classification risk for the 1-nearest neighbor search can be shown to be the probability that a pair of input measurements belong to different classes. This pair-wise probability is not in general a metric distance measure. Furthermore, it can out-perform any metric distance, approaching even the Bayes optimal performance.

In practice, we seek a model for the optimal distance measure that combines the discriminative powers of more elementary distance measures associated with a collection of simple feature spaces that are easy and efficient to implement; in our work, we use histograms of various feature types like color, texture and local shape properties. We use a linear logistic model for combining such elementary distance measures. Such a model is supported by observations of actual data for a representative discrimination task. For performing efficient nearest neighbor search over large training sets, the same model was extended to learn optimal hamming distance measures associated with a set of discriminators. This discrete model was combined with the continuous model to yield a hierarchical distance model that is both fast and accurate.

Finally, the nearest neighbor search over object parts was integrated into a whole object detection system and evaluated against both an indoor detection task as well as a face recognition task yielding promising results.