Abstract: A method of dispensing a prescribed medication, in pill form, and verifying that the medication dispensed is the prescribed medication. A medication identified from a prescription (P) is dispensed into a container (C). An image of the dispensed pills is taken and processed to obtain a set of characteristic features of the pill. These features include the coloration, shape, size, and any surface features of the pills. These features are then automatically compared with those of all the pills which can be dispensed by a dispensing apparatus (10). If a pill can be uniquely identified as the correct pill, the container of pills is accepted. Otherwise, the container is rejected. If, as a result of the processing, a determination cannot be made, the container is provisionally rejected and is subsequently inspected by a pharmacist to determine if the prescription is correctly filled.

Abstract: A non-imaging traffic sensing system (10) employs three separate detectors (D1-D3) each positioned above a roadway (R) and spatially separated along the roadway. The detectors detect light reflected off the roadway surface. Each detector has its own field of view (FOV) of the roadway surface and a separate footprint (F1-F3) is defined on the surface by intersection of the respective fields of view with the surface. A disturbance passing over the roadway changes the amount of reflected light sensed by the detectors and the detectors generate respective signals indicative of the amount of reflected light they receive. A first pair of the detectors (D1, D3) measure the speed of a passing disturbance. A second pair of the detectors (D1, D2) identify shadows so to eliminate their effects. The footprints defined by the fields of view of the second detector pair generally overlap. A processor (24) processes signals from the first detector pair to determine the speed of the disturbance.

Abstract: A traffic incident detection system (10) includes both the collection and analysis of traffic data and employs a time-indexed traffic anomaly detection algorithm which partitions time into categories of “type of day,” and “time of day”. Using this partition, a fuzzy neuromorphic, unsupervised learning algorithm calibrates fuzzy sets as “normal” and “abnormal” for a plurality of traffic descriptors. Fuzzy composition techniques are used, on a per traffic lane basis, to combine multiple traffic descriptors in order to determine membership in a “normal” or “abnormal” lane status. Each lane status is then combined to determine the overall status of a road segment. Initial training of the algorithm occurs during the first few weeks after a sensor (12) is installed. On-line background training continues thereafter to continually tune and track seasonal changes affecting system performance.