Despite significant progress, image saliency detection still remains a challenging task in complex scenes and environments. Integrating multiple different but complementary cues, like RGB and Thermal (RGB-T), may be an effective way for boosting saliency detection performance. The current research in this direction, however, is limited by the lack of a comprehensive benchmark. This work contributes such a RGB-T image dataset, which includes 821 spatially aligned RGB-T image pairs and their ground truth annotations for saliency detection purpose. With this benchmark, we propose a novel approach, graph-based multi-task manifold ranking algorithm, for RGB-T saliency detection. Extensive experiments against the baseline methods on the benchmark dataset demonstrate the effectiveness of the proposed approach.
CITATION STYLE
Wang, G., Li, C., Ma, Y., Zheng, A., Tang, J., & Luo, B. (2018). RGB-T saliency detection benchmark: Dataset, baselines, analysis and a novel approach. In Communications in Computer and Information Science (Vol. 875, pp. 359–369). Springer Verlag. https://doi.org/10.1007/978-981-13-1702-6_36
Mendeley helps you to discover research relevant for your work.