GLSC: LSC superpixels at over 130 FPS

• Published in: Journal of real-time image processing Vol. 14; no. 3; pp. 605 - 616
• Main Authors: Ban, Zhihua, Liu, Jianguo, Fouriaux, Jeremy
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2018; Springer Nature B.V
• Subjects: Algorithms; Clustering; Complexity; Computer Graphics; Computer Science; Computer vision; Graphics processing units; Image Processing and Computer Vision; Image resolution; Image retrieval; Multimedia Information Systems; Optical tracking; Pattern Recognition; Signal,Image and Speech Processing; Source code; Special Issue Paper; Trends; CUDA; Superpixel; Image segmentation; Real time; GPGPU
• DOI: 10.1007/s11554-016-0652-5
• ISSN: 1861-8200

Superpixel has been successfully applied in various computer vision tasks, and many algorithms have been proposed to generate superpixel map. Recently, a superpixel algorithm called “superpixel segmentation using linear spectral clustering” (LSC) has been proposed, and it performs equally well or better than state-of-the art superpixel segmentation algorithms in terms of several commonly used evaluation metrics in superpixel segmentation. Although LSC is of linear complexity, its original implementation runs in few hundreds of milliseconds for images with resolution of 481 × 321 stated by the authors, which is a limitation for some real-time applications such as visual tracking which may needs, for instance, 30 FPS for standard image resolution (e.g., 480 × 320, 640 × 480, 1280 × 720 and 1920 × 1080). Instead of inventing new algorithms with lower complexity than LSC, we will explore LSC to modify its structure and make it suitable to be implemented by parallel technique. The modified LSC algorithm is implemented in CUDA and tested on several NVIDIA graphics processing unit. Our implementation of the proposed modified LSC algorithm achieves speedups of up to 80× from the original sequential implementation, and the quality, measured by two commonly used evaluation metrics, of our implementation keeps being similar to the original one. The source code will be made publicly available.