5 October 2017 Small target detection using objectness and saliency
Author Affiliations +
Abstract
We are motived by the need for generic object detection algorithm which achieves high recall for small targets in complex scenes with acceptable computational efficiency. We propose a novel object detection algorithm, which has high localization quality with acceptable computational cost. Firstly, we obtain the objectness map as in BING[1] and use NMS to get the top N points. Then, k-means algorithm is used to cluster them into K classes according to their location. We set the center points of the K classes as seed points. For each seed point, an object potential region is extracted. Finally, a fast salient object detection algorithm[2] is applied to the object potential regions to highlight objectlike pixels, and a series of efficient post-processing operations are proposed to locate the targets. Our method runs at 5 FPS on 1000*1000 images, and significantly outperforms previous methods on small targets in cluttered background.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Naiwen Zhang, Naiwen Zhang, Yang Xiao, Yang Xiao, Zhiwen Fang, Zhiwen Fang, Jian Yang, Jian Yang, Li Wang, Li Wang, Tao Li, Tao Li, } "Small target detection using objectness and saliency", Proc. SPIE 10432, Target and Background Signatures III, 104320Q (5 October 2017); doi: 10.1117/12.2278219; https://doi.org/10.1117/12.2278219
PROCEEDINGS
9 PAGES


SHARE
Back to Top