A statistical method for 3D object detection applied to faces and cars

TLDR

The paper proposes a statistical method for 3D object detection. The method models object and non‑object appearance with a product of histograms over subsets of wavelet coefficients and spatial positions, combining many such histograms to capture diverse visual attributes. The algorithm reliably detects human faces with out‑of‑plane rotation and passenger cars across a wide range of viewpoints.

Abstract

In this paper, we describe a statistical method for 3D object detection. We represent the statistics of both object appearance and "non-object" appearance using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithm that can reliably detect passenger cars over a wide range of viewpoints.