Search

Nighttime driving is more dangerous than daytime driving--particularly for senior drivers. Three to four times as many driving-related deaths occur at night than in the daytime. To improve the safety of night driving, automatic pedestrian detection based on infrared images has drawn increased attention because pedestrians tend to stand out more against the background in infrared images than they do in visible light images. Nevertheless, pedestrian detection in infrared images is by no means trivial--many of the known difficulties carry over from visible light images, such as image variability occasioned by pedestrians being in different poses. Typically, several different pedestrian templates have to be used in order to deal with a range of poses. Furthermore, pedestrian detection is difficult because of poor infrared image quality (low resolution, low contrast, few distinguishable feature points, little texture information, etc.) and misleading signals. To address these problems, this paper introduces a shape-independent pedestrian-detection method. Our segmentation algorithm first estimates pedestrians' horizontal locations through projection-based horizontal segmentation and then determines pedestrians' vertical locations through brightness/bodyline-based vertical segmentation. Our classification method defines multidimensional histogram-, inertia-, and contrast-based classification features. The features are shape-independent, complementary to one another, and capture the statistical similarities of image patches containing pedestrians with different poses. Thus, our pedestrian-detection system needs only one pedestrian template--corresponding to a generic walking pose--and avoids brute-force searching for pedestrians throughout whole images, which typically involves brightness-similarity comparisons between candidate image patches and a multiplicity of pedestrian templates. Our pedestrian-detection system is neither based on tracking nor does it depend on camera calibration to determine the relationship between an object's height and its vertical image locations. Thus, it is less restricted in applicability. Even if much work is still needed to bridge the gap between present pedestrian-detection performance and the high reliability required for real-world applications, our pedestrian-detection system is straightforward and provides encouraging results in improving speed, reliability, and simplicity. Index Terms--Autonomous driving, classification, infrared image processing, intelligent transportation system (ITS), intelligent vehicle (IV), night vision, pattern recognition, pedestrian detection, shape independent.

The objective of this paper is to develop a method for estimating the Si[O.sub.2] content of igneous rocks using thermal infrared reflectance spectra, aiming to utilize it in the remote sensing of thermal spectral emission. Silicate minerals, which are the major components of the earth's surface, display their strongest fundamental molecular vibration bands in the thermal infrared region (8-12 [[micro]meter]). The wavelengths of these so-called 'reststrahlen bands' are systematically related to the Si[O.sub.2] content of rocks. Pattern matching (using a back-propagating neural network approach) between simulated remotely sensed data and the Si[O.sub.2] content was performed. This approach was evaluated by comparing the spectrally estimated Si[O.sub.2] content with the chemically determined Si[O.sub.2] content for a separate set of rock samples. The estimated error between the spectrally estimated and chemically determined Si[O.sub.2] contents for most samples was within 7%. Future multiband satellite sensors of the earth's thermal emission will have much higher spectral and spatial resolution than existing ones, and should be able to detect these spectral trends.