Accession Number : ADA567167


Title :   Multi-Frame Object Detection


Descriptive Note : Master's thesis


Corporate Author : NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF INFORMATION SCIENCES


Personal Author(s) : Laielli, Michael J


Full Text : http://www.dtic.mil/get-tr-doc/pdf?AD=ADA567167


Report Date : Sep 2012


Pagination or Media Count : 45


Abstract : This thesis describes an object detection system that extracts and combines appearance information over multiple consecutive video frames, inherently gaining and analyzing information related to motion. Objects that exhibit characteristic motion over the course of multiple frames are able to be detected at smaller scales than is achievable using a single-frame detector. Our method builds on the detection work of Viola and Jones, with our extension being the added ability to combine information from multiple frames. Our implementation detects an object in synthetic images at very small scales, down to 3x3 pixels, and has a low false-alarm rate.


Descriptors :   *CLASSIFICATION , *COMPUTER VISION , *FEATURE EXTRACTION , *MOTION , *MOTION PICTURES , *TARGET DETECTION , *VIDEO FRAMES , AUTOMATION , C PROGRAMMING LANGUAGE , COMPUTER PROGRAMS , FALSE ALARMS , INTENSITY , LEARNING MACHINES , PIXELS , THESES , TRAINING , VIDEO IMAGES


Subject Categories : Cybernetics
      Photography
      Miscellaneous Detection and Detectors
      Target Direction, Range and Position Finding


Distribution Statement : APPROVED FOR PUBLIC RELEASE