Sparse Detector Imaging Sensor with Two-Class Silhouette Classification 英文参考文献.docVIP

Sensors 2008, 8, 7996-8015; DOI: 10.3390/s8127996 OPEN ACCESS sensors ISSN 1424-8220 /journal/sensors Article Sparse Detector Imaging Sensor with Two-Class Silhouette Classification David Russomanno *, Srikant Chari and Carl Halford Center for Advanced Sensors, Department of Electrical and Computer Engineering, The University of Memphis, Memphis, TN, U.S.A. 38152; E-Mails: schari@; chalford@ * Author to whom correspondence should be addressed; E-Mail: drussmnn@; Tel.: +1-901-678-2175; Fax: +1-901-678-5469 Received: 4 November 2008; in revised form: 1 December 2008 / Accepted: 4 December 2008 / Published: 8 December 2008 Abstract: This paper presents the design and test of a simple active near-infrared sparse detector imaging sensor. The prototype of the sensor is novel in that it can capture remarkable silhouettes or profiles of a wide-variety of moving objects, including humans, animals, and vehicles using a sparse detector array comprised of only sixteen sensing elements deployed in a vertical configuration. The prototype sensor was built to collect silhouettes for a variety of objects and to evaluate several algorithms for classifying the data obtained from the sensor into two classes: human versus non-human. Initial tests show that the classification of individually sensed objects into two classes can be achieved with accuracy greater than ninety-nine percent (99%) with a subset of the sixteen detectors using a representative dataset consisting of 512 signatures. The prototype also includes a Web- service interface such that the sensor can be tasked in a network-centric environment. The sensor appears to be a low-cost alternative to traditional, high-resolution focal plane array imaging sensors for some applications. After a power optimization study, appropriate packaging, and testing with more extensive datasets, the sensor may be a good candidate for deployment in vast geographic