Robert Karlsen

Learn More
This paper presents a moving vehicle detection and tracking system, MVDT, for real-time operation in outdoor scenes. MVDT consists of three major components: road detection, vehicle detection, and vehicle tracking. The road detection algorithm utilizes a plane-fitting feature, the vehicle detection uses both segmented blob and Snakes blob features in a(More)
This paper reports on a Field Experiment carried out by the Human Research and Engineering Directorate at Ft. Benning to evaluate the efficacy of using speech to control an Unmanned Ground Vehicle (UGV) concurrently with a handcontroller. The SPEAR system, developed by Think-A-Move, provides speech-control of UGVs. The system picks up user-speech in the ear(More)
This paper presents a software system for imagebased terrain classification that mimics a human supervisor’s segmentation and classification of training images into “Go” and “NoGo” regions. The system identifies a set of image chips in the training images that span the range of terrain appearance. It then uses these exemplars to segment novel images and(More)
According to 1990 NHTSA statistics. traffic accidents cause $135 billion in damage to the American consumer annually, exclusive of pain and suffering. Approximately 30% of these accidents are related to driver perception problems and 14% occur at intersections. The National Automotive Center (NAC) visual perception laboratory (NAC-VPL) at the US Army Tank(More)
Support Vector Machines (SVMs) have become popular due to their accuracy in classifying sparse data sets. Their computational time can be virtually independent of the size of the feature vector. SVMs have been shown to out perform other learning machines on many data sets. In this paper, we use SVMs to detect a car in a lane of traffic. Digital pictures of(More)
  • 1