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.

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 that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints.

In this paper, we describe an algorithm for object recognition that explicitly models and estimated the posterior probability function, P(object/image). We have chosen a functional form of the posterior probability function that captures the joint statistics of local appearance and position on the object as well as the statistics of local appearance in the visual world at large. We use a discrete representation of local appearance consisting of approximately 10/sup 6/ patterns. We compute an estimate of P(object/image) in closed form by counting the frequency of occurrence of these patterns over various sets of training images. We have used this method for detecting human faces from frontal and profile views. The algorithm for frontal views has shown a detection rate of 93.0% with 88 false alarms on a set of 125 images containing 483 faces combining the MIT test set of Sung and Poggio with the CMU test sets of Rowley, Baluja, and Kanade. The algorithm for detection of profile views has also demonstrated promising results.

A new vision-based technique for autonomous driving is described. This approach explicitly addresses and compensates for two forms of uncertainty: uncertainty about changes in road direction and uncertainty in the measurements of the road derived in each image. Autonomous driving has been demonstrated on both local roads and highways at speeds up to 100 km/h. The algorithm has performed well in the presence of non-ideal road conditions including gaps in the lane markers, sharp curves, shadows, cracks in the pavement, and wet roads. It has also performed well in rain, dark, and nighttime driving with headlights.>

Describes a visual processing algorithm that supports autonomous road following. The algorithm requires that lane markings be present and attempts to track the lane markings on both lane boundaries. There are three stages of computation: extracting edges; matching extracted edge points with a geometric model of the road, and updating the geometric road model. All processing is confined to the 2-D image plane. No information about the motion of the vehicle is used. This algorithm has been implemented and tested using video taped road scenes. It performs robustly for both highways and rural roads. The algorithm runs at a sampling rate of 15 Hz and has a worst case latency of 139 milliseconds (ms). The algorithm is implemented under the NASA/NBS Standard Reference Model for Telerobotic Control System Architecture (NASREM) architecture and runs on a dedicated vision processing engine and a VME-based microprocessor system.>