Journal Title : International Journal of Modern Trends in Engineering and Science
Volume 03 Issue 07 2016
ISSN no: 2348-3121
Page no: 95-99
Abstract – In this paper, a novel method is proposed to detect the number of cars in an UAV images. The primary step for car counting starts with screening, which separates the interested area in the images. The primary step followed by key points extraction by using an SIFT algorithm, which are highly distinctive. In addition to that, for suppressing the background in images, Foreground detection method is proposed, which will exhibits a promising car counting accuracy. Finally key points can be grouped by using an merging algorithm. The promising results indicate the effectiveness of our proposed framework, with higher accuracy.
Keywords— Unmanned Aerial Vehicle (UAV), Support Vector Machine(SVM), Scale Invariant Feature Transform (SIFT) , Car Keypoint Merging
- Thomas Moranduzzo and Farid Melgani, “Automatic Car Counting Method for Unmanned Aerial Vehicle Images” ieee transactions on geoscience and remote sensing, vol. 52, no. 3, march 2014.
- Thomas Moranduzzo, and Farid Melgani,”Detecting Cars in UAV Images With a Catalog-Based Approach” ieee transactions on geoscience and remote sensing, vol. 52, no. 10, october 2014.
- ‘Scale invariant feature transorms(SIFT) by David Lowe’ presented by Jason Clemons gives an clarity knowledge about the matching problem and Feature Characteristics
- “Vehicle Detection and Classification from Satellite Images Based On Gaussian Mixture Model” International Journal of Engineering Research and General Science Volume 3, Issue 2, Part 2, March-April, 2015 .
- “Car Detection and Counting Method by using Data Mining / Warehousing” 2014 International Journal of Advance Research in Computer Science and Management Studies Research Article Volume 2, Issue 7, July 2014.