Title: Image saliency and co-saliency detection by low-rank multiscale fusion

Authors: Rui Huang; Wei Feng; Jizhou Sun; Yaobin Zou

Addresses: College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China; Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang 443003, China ' College of Intelligence and Computing, School of Computer Science and Technology, Tianjin University, Tianjin, 300350, China; Key Research Center for Surface Monitoring and Analysis of Cultural Relics, State Administration of Cultural Heritage, China ' College of Intelligence and Computing, School of Computer Science and Technology, Tianjin University, Tianjin, 300350, China; Key Research Center for Surface Monitoring and Analysis of Cultural Relics, State Administration of Cultural Heritage, China ' Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang 443003, China

Abstract: Saliency and co-saliency detection aim to distinguish conspicuous foreground objects from single and multiple images, thus are essential in many multimedia and vision applications. To achieve balanced efficiency and accuracy, most recent successful saliency detectors are based on superpixels. However, saliency detection with single-scale superpixel segmentation may fail in capturing intrinsic salient objects of complex natural scenes with small-scale high-contrast backgrounds. To tackle this problem, we present a simple strategy using multiscale superpixels to jointly detect salient object via low-rank optimisation. Specifically, we first build a multiscale superpixel pyramid and derive the corresponding saliency map by multimodal saliency features and priors at each single scale. Then, we use joint low-rank analysis of multiscale saliency maps to obtain a more reliable and adaptively-fused saliency map, which properly takes all scales saliency into account. We further propose a GMM generative co-saliency prior to enable the above approach to detect co-salient objects from multiple images. Extensive experiments on benchmark datasets validate the effectiveness and superiority of the proposed saliency and co-saliency detector over state-of-the-arts.

Keywords: saliency; co-saliency; co-saliency prior; Gaussian mixture model; GMM; joint low-rank analysis; multiscale.

DOI: 10.1504/IJHPSA.2019.104942

International Journal of High Performance Systems Architecture, 2019 Vol.8 No.4, pp.225 - 237

Received: 16 Feb 2019
Accepted: 19 Mar 2019
Published online: 07 Feb 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article