William A. Bauson

Legendre and gabor moments for vehicle recognition in forward collision warning

Collision warning remains an active research field due to the increasing complexities of on-road traffic worldwide. Vision-based warning systems are of particular interest because of the extensive information contained in images. This paper proposes the combination of Legendre moments and Gabor features for monocular vision-based vehicle recognition. We focus on vehicle recognition within a region of interest (ROI) in an image by assuming that the ROI has been detected by a radar sensor. Two classifiers including a support vector machine (SVM) and a neural network have been investigated to verify the effectiveness of the features. We have tested the proposed approaches on real-world video sequences acquired under various weather conditions for a wide range of vehicles and non-vehicles at up to 70 meters. The proposed combination of Legendre moments and Gabor features has yielded a correct classification rate of 99.1% and a false alarm rate of 1.9%. We have compared the proposed features with the over-complete Haar wavelets in the literature

An Integrated Approach to Automotive Safety Systems

In this paper, the authors present the concept of using a safety state diagram for establishing an integrated system approach to automotive safety. The paper examines the following advanced concepts: pre-crash sensing, anticipatory crash sensing, X-by-wire systems, advanced safety interiors, integrated vehicle electrical/electronics systems data networks, and telematics.

A monocular vision-based occupant classification approach for smart airbag deployment

Occupant classification is essential to a smart airbag system that can either turn off or deploy in a less harmful way according to the type of the occupants in the front seat. This paper presents a monocular vision-based occupant classification approach to classify the occupants into five categories including empty seats, adults in normal position, adults out of position, front-facing child/infant seats, and rear-facing infant seats. The proposed approach consists of image representation and pattern classification. The image representation step computes Haar wavelets and edge features from the monochrome video frames. A support vector machine (SVM) classifier next determines the occupant category based on the representative features. We have tested our approach on a large variety of indoor and outdoor images acquired under various illumination conditions for occupants with different appearances, sizes and shapes. With a strict occupant exclusive training/testing split, our approach has achieved an average correct classification rate of 97.18% among the five occupant categories.

Challenges of Embedded Computer Vision in Automotive Safety Systems

Vision-based automotive safety systems have received considerable attention over the past decade. Such systems have advantages compared to those based on other types of sensors such as radar, because of the availability of lowcost and high-resolution cameras and abundant information contained in video images. However, various technical challenges exist in such systems. One of the most prominent challenges lies in running sophisticated computer vision algorithms on low-cost embedded systems at frame rate. This chapter discusses these challenges through vehicle detection and classification in a collision warning system.

Spatial Encoding of Structured Light for Ranging With Single Camera

A single camera and dot matrix structured light are used for target range measurement with optical triangulation. The probing beams are spatially encoded in the image plane so that each beam can be uniquely identified without confusion. Such an arrangement allows multiple probing beams in a single image frame to obtain target range profiles. Compared with either a stereovision system or an expensive range scanning system, the approach provided in this paper is more practical, efficient, and cost effective. Principles of spatial encoding, optimized optical configuration, beam labeling and system operation are described. The system is demonstrated with 4x7 probing beams and a VGA CMOS camera.

Enhanced Imager Chip Packaging for Automotive Applications

The development of an automotive qualified packaging technology for CMOS and CCD imager chips is described. A flip-chip-on-flex solution was developed. This package solution was demonstrated using a 1/3 inch optical format imager chip that was designed for use with conventional ceramic leadless chip carrier packaging. Overall package thickness is 1.39mm, with the complete back-side of the silicon substrate exposed and available for chip cooling. The flex is bonded to a glass substrate, which provides the optical access to the imager chip. The use of a transparent underfill material reduces the rate of moisture infiltration and reduces optical reflections within the package structure. The flex may be extended beyond the package to allow surface mounting of additional passive and active components, as well as interconnection to additional circuitry.