RGB-T saliency detection benchmark: Dataset, baselines, analysis and a novel approach

Abstract

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.