Paul Watta

A motion and shape-based pedestrian detection algorithm

In this paper we investigate a vision-based pedestrian detection algorithm which can be used in the design of intelligent vehicle systems. The input to the algorithm is video data obtained from a camera mounted on the vehicle. In the proposed method, a wavelet transform is computed on the video frames, and multistage template matching is used to determine whether or not a pedestrian is present in the frame. Motion detection and localization is used to reduce the computational requirements. Experimental results are presented for several different video sequences. The results show that this method is able to reliably detect pedestrians in cluttered scenes.

A two-level Hamming network for high performance associative memory

This paper presents an analysis of a two-level decoupled Hamming network, which is a high performance discrete-time/discrete-state associative memory model. The two-level Hamming memory generalizes the Hamming memory by providing for local Hamming distance computations in the first level and a voting mechanism in the second level. In this paper, we study the effect of system dimension, window size, and noise on the capacity and error correction capability of the two-level Hamming memory. Simulation results are given for both random images and human face images.

A coupled gradient network approach for static and temporal mixed-integer optimization

Utilizes the ideas of artificial neural networks to propose new solution methods for a class of constrained mixed-integer optimization problems. These new solution methods are more suitable to parallel implementation than the usual sequential methods of mathematical programming. Another attractive feature of the proposed approach is that some global search mechanisms may be easily incorporated into the computation, producing results which are more globally optimal. To formulate the solution method proposed in this paper, a penalty function approach is used to define a coupled gradient-type network with an appropriate architecture, energy function and dynamics such that high-quality solutions may be obtained upon convergence of the dynamics. Finally, it is shown how the coupled gradient net may be extended to handle temporal mixed-integer optimization problems, and simulations are presented which demonstrate the effectiveness of the approach.

Recurrent neural nets as dynamical Boolean systems with application to associative memory

Discrete-time/discrete-state recurrent neural networks are analyzed from a dynamical Boolean systems point of view in order to devise new analytic and design methods for the class of both single and multilayer recurrent artificial neural networks. With the proposed dynamical Boolean systems analysis, we are able to formulate necessary and sufficient conditions for network stability which are more general than the well-known but restrictive conditions for the class of single layer networks: (1) symmetric weight matrix with (2) positive diagonal and (3) asynchronous update. In terms of design, we use a dynamical Boolean systems analysis to construct a high performance associative memory. With this Boolean memory, we can guarantee that all fundamental memories are stored, and also guarantee the size of the basin of attraction for each fundamental memory.

The Hamming associative memory and its relation to the exponential capacity DAM

We analyze the capacity of the Hamming associative memory and explore its relation to the exponential DAM (Chiueh and Goodman, 1991). In particular, it is shown that for a sufficiently large but finite radix, the exponential DAM operates as a Hamming associative memory.

Nonparametric Approaches for Estimating Driver Pose

To better understand driver behavior, the Federal Highway Administration and the National Highway Traffic Safety Administration have collected several thousands of hours of driver video. There is now an immediate need for devising automated procedures for analyzing the video. In this paper, we look at the problem of estimating driver pose given a video of the driver as he or she drives the vehicle. A complete system is proposed to perform feature extraction and classification of each frame. The system uses a Fisherface representation of video frames and a nearest neighbor and neural network classification scheme. Experimental results show that the system can achieve high accuracy and reliable performance.

A Weighted Voting Model of Associative Memory

This paper presents an analysis of a random access memory (RAM)-based associative memory which uses a weighted voting scheme for information retrieval. This weighted voting memory can operate in heteroassociative or autoassociative mode, can store both real-valued and binary-valued patterns and, unlike memory models, is equipped with a rejection mechanism. A theoretical analysis of the performance of the weighted voting memory is given for the case of binary and random memory sets. Performance measures are derived as a function of the model parameters: pattern size, window size, and number of patterns in the memory set. It is shown that the weighted voting model has large capacity and error correction. The results show that the weighted voting model can successfully achieve high-detection and -identification rates and, simultaneously, low-false-acceptance rates

An RCE-based Associative Memory with Application to Human Face Recognition

Many models of neural network-based associative memory have been proposed and studied. However, most of these models do not have a rejection mechanism and hence are not practical for many real-world associative memory problems. For example, in human face recognition, we are given a database of face images and the identity of each image. Given an input image, the task is to associate when appropriate the image with the corresponding name of the person in the database. However, the input image may be that of a stranger. In this case, the system should reject the input. In this paper, we propose a practical associative memory model that has a rejection mechanism. The structure of the model is based on the restricted Coulomb energy (RCE) network. The capacity of the proposed memory is desibed by two measures: the ability of the system to correctly identify known individuals, and the ability of the system to reject individuals who are not in the database. Experimental results are given which show how the performance of the system varies as the size of the database increases up to 1000 individuals.

Combining Gabor features: summing vs. voting in human face recognition

Gabor wavelet-based feature extraction has been emerging as one of the most promising ways to represent human face image data. In this paper, we examine the performance of two types of classifiers that can be used with Gabor features. In the first classifier, the distance between two images is computed by summing the local distances among all the nodes. In the second classifier, a voting strategy is used In addition, we examine two types of shift optimization procedures. The first is the standard elastic graph matching algorithm, and the second is a constrained version of the algorithm. Experimental results indicate that the voting-based classifier with constrained elastic graph matching gives improved results.

Training algorithms for robust face recognition using a template-matching approach

This paper describes a complete face recognition system. The system uses a template matching approach along with a training algorithm for tuning the performance of the system to solve two types of problems simultaneously: 1) correct classification experiments which correctly recognize and identify individuals who are in the database; and 2) false positive experiments which reject individuals who are not part of the database. Experimental results are given which indicate that this training method is capable of consistently producing high correct classification rates and low false positive rates.