Search

Robust and reliable vehicle detection from images acquired by a moving vehicle is an important problem with numerous applications including driver assistance systems and self-guided vehicles. Our focus in this paper is on improving the performance of on-road vehicle detection by employing a set of Gabor filters specifically optimized for the task of vehicle detection. This is essentially a kind of feature selection, a critical issue when designing any pattern classification system. Specifically, we propose a systematic and general evolutionary Gabor filter optimization (EGFO) approach for optimizing the parameters of a set of Gabor filters in the context of vehicle detection. The objective is to build a set of filters that are capable of responding stronger to features present in vehicles than to nonvehicles, therefore improving class discrimination. The EGFO approach unifies filter design with filter selection by integrating genetic algorithms (GAs) with an incremental clustering approach. Filter design is performed using GAs, a global optimization approach that encodes the Gabor filter parameters in a chromosome and uses genetic operators to optimize them. Filter selection is performed by grouping filters having similar characteristics in the parameter space using an incremental clustering approach. This step eliminates redundant filters, yielding a more compact optimized set of filters. The resulting filters have been evaluated using an application-oriented fitness criterion based on support vector machines. We have tested the proposed framework on real data collected in Dearborn, MI, in summer and fall 2001, using Ford's proprietary low-light camera.

Past work on object detection has emphasized the issues of feature extraction and classification, however, relatively less attention has been given to the critical issue of feature selection. The main trend in feature extraction has been representing the data in a lower dimensional space, for example, using principal component analysis (PCA). Without using an effective scheme to select an appropriate set of features in this space, however, these methods rely mostly on powerful classification algorithms to deal with redundant and irrelevant features. In this paper, we argue that feature selection is an important problem in object detection and demonstrate that genetic algorithms (GAs) provide a simple, general, and powerful framework for selecting good subsets of features, leading to improved detection rates. As a case study, we have considered PCA for feature extraction and support vector machines (SVMs) for classification. The goal is searching the PCA space using GAs to select a subset of eigenvectors encoding important information about the target concept of interest. This is in contrast to traditional methods selecting some percentage of the top eigenvectors to represent the target concept, independently of the classification task. We have tested the proposed framework on two challenging applications: vehicle detection and face detection. Our experimental results illustrate significant performance improvements in both cases.

Target detection and tracking represent two fundamental steps in automatic video-based surveillance systems where the goal is to provide intelligent recognition capabilities by analyzing target behavior. This paper presents a framework for video-based surveillance where detection and tracking are addressed simultaneously in a unified framework (i.e., detection results trigger tracking, and tracking re-enforces detections)to improve detection results. In contrast to methods that apply target detection and tracking sequentially and independently from each other (i.e., "detect-then-track"), we feed the results of tracking back to the detection stage to adaptively optimize the threshold used in the detection stage and improve system robustness (i.e., "detect-and-track"). Specifically, the initial locations and representations of the targets are extracted by background subtraction. To model the background, we employ Support Vector Regression (SVR) along with an on-line learning scheme to update it efficiently over time. Target detection is performed by thresholding the outputs of the SVR model. Tracking uses shape projection histograms to iteratively localize the targets and achieve a high shape matching confidence level. Feeding back the results of tracking to the detection stage restricts the range of threshold values, suppress false alarms due to noise, and allows to continuously detect small targets as well as targets undergoing projection distortions. We have validated the proposed framework by detecting vehicles and pedestrians in traffic scenes using both visible and thermal video sequences. Experimental results and comparisons with framebased detection and kernel-based tracking methods illustrate the robustness of our approach.

Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments, and possible collision with other vehicles has attracted a lot of attention lately. In these systems, robust and reliable vehicle detection is a critical step. This paper presents a review of recent vision-based on-road vehicle detection systems. Our focus is on systems where the camera is mounted on the vehicle rather than being fixed such as in traffic/driveway monitoring systems. First, we discuss the problem of on-road vehicle detection using optical sensors followed by a brief review of intelligent vehicle research worldwide. Then, we discuss active and passive sensors to set the stage for vision-based vehicle detection. Methods aiming to quickly hypothesize the location of vehicles in an image as well as to verify the hypothesized locations are reviewed next. Integrating detection with tracking is also reviewed to illustrate the benefits of exploiting temporal continuity for vehicle detection. Finally, we present a critical overview of the methods discussed, we assess their potential for future deployment, and we present directions for future research.

Robust and reliable detection of overtaking vehicles is an important component of any on-board driver assistance system. Optical flow, with the abundant motion information present in image sequences, has been studied extensively for vehicle detection. However, using dense optical ?ow for vehicle detection is sensitive to shocks and vibrations of the mobile camera; image outliers caused by illumination changes; and high computational complexity. To improve vehicle detection performance and reduce computational complexity, we propose an efficient and robust methodology for overtaking vehicle detection based on homogeneous sparse optical flow and eigenspace modeling. Specifically, our method models the background into dynamic and quasi-static regions. Instead of using dense optical flow to model the dynamic parts of the background, we employ homogeneous sparse optical flow, which makes detection more robust to camera shocks and vibrations. Moreover, to make detection robust to illumination changes, we employ a blockbased eigenspace approach to represent quasi-static regions in the background. A region-based hysteresis-thresholding approach, augmented by a localized spatial segmentation procedure, attains a good tradeoff between true detections and false positives. The proposed methodology has been evaluated using challenging traf?c scenes illustrating good performance.

As one of the most promising applications of computer vision, vision-based vehicle detection for driver assistance has received considerable attention over the last 15 years. There are at least three reasons for the blooming research in this field: first, the startling losses both in human lives and finance caused by vehicle accidents; second, the availability of feasible technologies accumulated within the last 30 years of computer vision research; and third, the exponential growth of processor speed has paved the way for running computation-intensive video-processing algorithms even on a low-end PC in realtime. This paper provides a critical survey of recent vision-based on-road vehicle detection systems appeared in the literature (i.e., the cameras are mounted on the vehicle rather than being static such as in traffic/driveway monitoring systems).

Despite the considerable amount of research work on the application of Gabor filters in pattern classification, their design and selection have been mostly done on a trial and error basis. Existing techniques are either only suitable for a small number of filters or less problem-oriented. A systematic and general evolutionary Gabor filter optimization (EGFO) approach that yields a more optimal, problem-specific, set of filters is proposed in this study. The EGFO approach unifies filter design with filter selection by integrating genetic algorithms (GAs) with an incremental clustering approach. Specifically, filter design is performed using GAs, a global optimization approach that encodes the parameters of the Gabor filters in a chromosome and uses genetic operators to optimize them. Filter selection is performed by grouping together filters having similar characteristics (i.e., similar parameters) using incremental clustering in the parameter space. Each group of filters is represented by a single filter whose parameters correspond to the average parameters of the filters in the group. This step eliminates redundant filters, leading to a compact, optimized set of filters. The average filters are evaluated using an application-oriented fitness criterion based on support vector machines (SVMs). To demonstrate the effectiveness of the proposed framework, we have considered the challenging problem of vehicle detection from gray-scale images. Our experimental results illustrate that the set of Gabor filters, specifically optimized for the problem of vehicle detection, yield better performance than using traditional filter banks.

A methodology has been developed that aids drivers by suggesting a safer following distance, through the use of sensors, and optionally, vehicle to vehicle communication. Given the restricted case where there is no option to swerve into another lane, a Matlab Simulink model varies vehicle dynamics, driver reaction delay, following distance, and initial speeds when a lead vehicle suddenly decelerates. Based upon the likelihood of collision, neural networks suggest a best following distance, and the benefits of reducing reaction delay with adaptive agents are quantified.

Feature subset selection has received considerable attention in the machine learning literature, however, it has not been fully explored or exploited in the computer vision area. In this paper, we consider the problem of object detection using genetic algorithms (GA) for feature subset selection. We argue that feature selection is an important problem in object detection, and demonstrate that GA provide a simple, general, and powerful framework for selecting good sets of features, leading to lower detection error rates. As a case study, we have chosen to perform feature extraction using the popular method of principal component analysis (PCA) and classification using support vector machines (SVM). We have tested this framework on. two difficult and practical object detection problems: vehicle detection and face detection. Experimental results demonstrate significant performance improvements in both cases.

The focus of this work is on the problem of feature selection and classification for on-road vehicle detection. In particular, we propose using quantized Haar wavelet features and Support Vector Machines (SVMs) for rear-view vehicle detection. Wavelet features are particularly attractive for vehicle detection because they form a compact representation, encode edge information, capture information from multiple scales, and can be computed efficiently. Traditionally, methods using wavelet features for classification truncate the coefficients by keeping only the ones with largest magnitude. We believe that the actual values of the wavelet coefficients are not very important for vehicle detection. In fact, the coefficient magnitudes indicate local oriented intensity differences, information that cold be very different even for the same vehicle under different lighting conditions. Therefore, we argue and demonstrate experimentally that the actual coefficient values are less important compared to the simple presence or absence of those coefficients. Specifically, we propose quantizing large negative coefficients to -1, large positive coefficients to 1, and setting the rest coefficients to 0. The quantized coefficients seem to encode important information about the general shape and structure of vehicles, while ignoring fine details and allowing for sufficient inter-class variability. Experimental results and comparisons using real data demonstrate the superiority of the proposed approach which has achieved an average accuracy of 93.94% on completely novel test images.

This paper presents an in-vehicle real-time monocular precrash vehicle detection system. The system acquires grey level images through a forward facing low light camera and achieves an average detection rate of 10Hz. The vehicle detection algorithm consists of two main steps: multi-scale driven hypothesis generation and appearance-based hypothesis verification. In the multi-scale hypothesis generation step, possible image locations where vehicles might be present are hypothesized. This step uses multi-scale techniques to speed up detection but also to improve system robustness by making system performance less sensitive to the choice of certain parameters. Appearance-base hypothesis verification verifies those hypothesis using Haar Wavelet decomposition for feature extraction and Support Vector Machines (SVMs) for classification. The monocular system was tested under different traffic scenarios (e.g., simply structured highway, complex urban street, varying weather conditions), illustrating good performance.

For a given digitized view of a driving scenario, motion clusters are formed, indicating possible moving object threats to the driver. Recurrent neural networks minimize hopping between clusters and predict a cluster's next location. Frequency analysis then categorizes as significant motion, and then as either head-on/away or transverse motion.

On-road vehicle detection is an important problem with application to driver assistance systems and autonomous, self-guided vehicles. The focus of this paper is on the problem of feature extraction and classification for rear-view vehicle detection. Specifically, we propose using Gabor filters for vehicle feature extraction and support vector machines (SVM) for vehicle detection. Gabor filters provide a mechanism for obtaining some degree of invariance to intensity due to global illumination, selectivity in scale, and selectivity in orientation. Basically, they are orientation and scale tunable edge and line detectors. Vehicles do contain strong edges and lines at different orientation and scales, thus, the statistics of these features (e.g., mean, standard deviation, and skewness) could be very powerful for vehicle detection. To provide robustness, these statistics are not extracted from the whole image but rather are collected from several subimages obtained by subdividing the original image into subwindows. These features are then used to train a SVM classifier. Extensive experimentation and comparisons using real data, different features (e.g., based on principal components analysis (PCA)), and different classifiers (e.g., neural networks (NN)) demonstrate the superiority of the proposed approach which has achieved an average accuracy of 94.81% on completely novel test images.

Appearance-based methods represent a promising research direction to the problem of vehicle detection. These methods learn the characteristics of the vehicle class from a set of training images which capture the variability in vehicle appearance. First, training images are represented by a set of features. Then, the decision boundary between the vehicle and nonvehicle classes is computed by modelling the probability distribution of the features In each class or through learning. The purpose of this study is to investigate the effectiveness of two important types of features for vehicle detection based on Haar wavelets and Gabor filters. In both cases, the decision boundary is computed using support vector machines (SVMs). Wavelet features encode edge information. Gabor filters provide a mechanism for obtaining orientation and scale tunable edge and line detectors. Our experimental results and comparisons using real data illustrate the effectiveness of both types of features for vehicle detection, with Gabor features performing the better. The two feature sets yield different misclassification errors which led us to the idea of combining them for improving performance. The combined set of features outperformed each feature set alone on completely novel test images.

In order to compete successfully in the global market place, manufactures must have the ability to produce high-quality, low-cost products that fully satisfy the customer’s needs. Many analytical techniques have been adopted by these manufactures aimed at improving customer and engineering quality. Nonlinear multivariate systems, however, complicate this process making the determination of controlling factors difficult. Often times, improvements in one area of the process or product compromises the performance in other areas. The Design of Experiments (DOE), pioneered by Taguchi, represents a powerful statistical method to help better understand nonlinear systems with the aim to improve quality and performance in engineering. A DOE using Computational Fluid Dynamics (CFD) is developed to better understand the influences of flow forces on valve design and performance. Geometric control factors for the spool valve are determined, enabling optimization and performance improvements.

Optimizing the painting process involves understanding the many nonlinear dynamics that effect paint transfer efficiency (PTE) such as bell applicator design (bell cup and shaping air ring), operating conditions (shaping air flow rate, paint flow rate, electric potential, downdraft, and bell rotation speed), target location, and paint type. PTE optimization results in less experimental testing and improved paint quality. We have modified a numerical simulation to include self-consistent momentum coupling between a continuum and discrete mass particles, as well as the inclusion of a self-consistent electrostatic field. These modifications enable the simulation tool to address several seminal questions concerning PTE. Several simulations have been performed and the influence of self-consistent modeling is addressed in this paper.

The unique software VORCAT (VORtex Computational Algorithm for Turbulence), which is based on a fast parallel vortex method, is employed to perform a time-accurate simulation of the flow in the spool valve of a pressure regulator from an automotive automatic transmission. The spool valve experiences flow forces which affect its axial motion and radial clearance. The vortex method is based on a parallel implementation of the Fast Multipole Method, and includes a hybrid vortex filament/sheet representation of the flow field, a vortex filament creation model that imitates the physical vortex self-replication process, and a hairpin removal and reconnection mechanism to limit the number and scale of vortical structures to those that are dynamically essential. In this paper, velocity and vorticity distribution results are presented for spool valve openings of 1mm and 0.25mm. The predicted velocity results agree well with corresponding experimental measurements, while the predicted vorticity results correlate well with experimental pressure measurements.

Aerodynamic lift force can affect automobile handling characteristics and wind gust can affect vehicle directional stability. Experimental measurements of the drag forces are usually made for fuel economy estimation and hence do not cover large wind angles that are important for vehicle stability studies of wind gust or extreme maneuvers. The Virtual Aerodynamic Wind Tunnel (VAWT) which uses PowerFlow is an ideal numerical tool in the early vehicle design stage to provide the aerodynamic forces from a vehicle model. The numerical technique is also advantageous over experimental measurements because it does not need a hardware prototype and the computer model is relatively easier to set up for design iterations. Since the dynamic effects of aerodynamic forces on a vehicle and its driver are best studied with a driving simulator in a real time environment, the VAWT calculated air drag coefficients are reduced to a mathematical function suitable for the real time driving simulations. Available test measurements are used to ensure the practicability of the mathematical function. A vehicle model is then used to test the aerodynamic model and study the effects of the aerodynamics on the vehicle directional stability.