In this work we compare the performance of seven popular feature detection algorithms on a synthetic sonar image dataset. The dataset consists of a single mine-like object (MLO) superimposed on three different backgrounds: grass, sand ripple, and sand. We explore the performance of Harris, Shi-Tomasi, SIFT, SURF, STAR, FAST, and ORB on each of these backgrounds, and all the backgrounds at once by training an SVM classifier. Performance is evaluated with ROC curves by comparing the number of correctly identified features belonging to objects (True Positives) and the number of incorrectly identified features belonging to background noise (False Positives).
|Title of host publication||OCEANS 2018 MTS/IEEE Charleston, OCEAN 2018|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|State||Published - 7 Jan 2019|
|Event||OCEANS 2018 MTS/IEEE Charleston, OCEANS 2018 - Charleston, United States|
Duration: 22 Oct 2018 → 25 Oct 2018
|Name||OCEANS 2018 MTS/IEEE Charleston, OCEAN 2018|
|Conference||OCEANS 2018 MTS/IEEE Charleston, OCEANS 2018|
|Period||22/10/18 → 25/10/18|
Bibliographical notePublisher Copyright:
© 2018 IEEE.
- Feature detection
- Visual odometry
ASJC Scopus subject areas
- Renewable Energy, Sustainability and the Environment