The purpose of this research is to investigate novel object detection and localization algorithms for autonomous robots. The average of overlaps and the percentage of positive detections are calculated to compare the accuracy between the Scale Invariant Feature Transform and the Speeded-Up Robust Features. Dense features are used as additional features to increase the precision in detection. Features are clustered into visual words to form a histogram. Images are trained based on the histogram and their corresponding labels with Support Vector Machine. The bounding box with the highest output from the Support Vector Machine represents the location of a target class.
July 27, 2016
The right to download or print any of the pages of this thesis (Material) is granted by the copyright owner only for personal or classroom use. The author retains all proprietary rights, including copyright ownership. Any reproduction or editing or other use of this Material by any means requires the express written permission of the copyright owner. Except as provided above, or any use beyond what is allowed by fair use (Title 17 Section 107 U.S.C.), you may not reproduce, republish, post, transmit or distribute any Material from this web site in any physical or digital form without the permission of the copyright owner of the Material. Inquiries regarding any further use of these materials should be addressed to Administration, Jernigan Library, Texas A&M University-Kingsville, 700 University Blvd. Kingsville, Texas 78363-8202, (361)593-3416.