GPU accelerated Foreign Object Debris Detection on Airfield Pavement with visual saliency algorithm

2016 International Conference on Communication, Image and Signal Processing

物理学;无线电电子学;计算机科学

Qi, Jun^1 ; Gong, Guoping^1 ; Cao, Xiaoguang^1

Image Processing Center, Beihang University, Beijing, China^1

关键词: Airfield pavement;    Complex background;    Connected component analysis;    Effectiveness and efficiencies;    Foreign object debris;    Image signature;    Original images;    Parallel version;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/787/1/012018/pdf
DOI  :  10.1088/1742-6596/787/1/012018

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

We present a GPU-based implementation of visual saliency algorithm to detect foreign object debris(FOD) on airfield pavement with effectiveness and efficiency. Visual saliency algorithm is introduced in FOD detection for the first time. We improve the image signature algorithm to target at FOD detection in complex background of pavement. First, we make pooling operations in obtaining saliency map to improve recall rate. Then, connected component analysis is applied to filter candidate regions in saliency map to get the final targets in original image. Besides, we map the algorithm to GPU-based kernels and data structures. The parallel version of the algorithm is able to get the results with 23.5 times speedup. Experimental results elucidate that the proposed method is effective to detect FOD real-time.