Share Email Print

Proceedings Paper

Track generation in semi-supervised learning of self-structured algorithm using noisy and sparse, visual, and infrared data
Author(s): Bala Konate; James Graham; Igor Ternovskiy
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, we elaborate on what was done to implement a semi-supervised self-structured learning algorithm using aerial visual and infrared (IR) images. The objective of this paper is to focus on the processed visual and IR images and the impact they had on our testing software package with noisy and sparse areal visual and infrared data. We encountered several issues with the processed test data due to noise, invalid detections from shadow, and two or more detections being mistaken as a single detection (or vice versa). The target detections include vehicles, people, noise and unidentified objects. To overcome these phenomena, we utilized our software package to extract information from detections, such as the exact pixel content, orientation, etc. We were also able to infer information from tracks as we built them, such as direction and speed, which further helped. As a result, our algorithm is capable generating patterns to build longer tracks from detections. The improved algorithm also has the ability to differentiate and classify target detections based on binary feature representations and attributes. We plan to further extend this track generation to include learning via pattern recognition, and complex object building.

Paper Details

Date Published: 15 May 2018
PDF: 9 pages
Proc. SPIE 10630, Cyber Sensing 2018, 106300N (15 May 2018); doi: 10.1117/12.2311611
Show Author Affiliations
Bala Konate, Defense Engineering Corp. (United States)
Air Force Research Lab. (United States)
James Graham, Riverside Research (United States)
Air Force Research Lab. (United States)
Igor Ternovskiy, Air Force Research Lab. (United States)

Published in SPIE Proceedings Vol. 10630:
Cyber Sensing 2018
Igor V. Ternovskiy; Peter Chin, Editor(s)

© SPIE. Terms of Use
Back to Top