Abstract
Many works have been proposed on image saliency detection to handle challenging issues including low illumination, cluttered background, low contrast, and so on. Although good performance has been achieved by these algorithms, detection results are still poor based on RGB modality. Inspired by the recent progress of multi-modality fusion, we propose a novel RGB-thermal saliency detection algorithm through learning static-adaptive graphs. Specifically, we first extract superpixels from the two modalities and calculate their affinity matrix. Then, we learn the affinity matrix dynamically and construct a static-adaptive graph. Finally, the saliency maps can be obtained by a two-stage ranking algorithm. Our method is evaluated on RGBT-Saliency Dataset with eleven kinds of challenging subsets. Experimental results show that the proposed method has better generalization performance. The complementary benefits of RGB and thermal images and the more robust feature expression of learning static-adaptive graphs create an effective way to improve the detection effectiveness of image saliency in complex scenes.
Highlights
Image saliency detection aims to quickly capture the most important and useful information from a scene by using the human visual attention mechanism, which can reduce the complexity of subsequent image processing, and has been applied to numerous vision problems including image classification [1], image retrieval [2], image encryption [3,4], video summary [5], and so on
We compared our model with eight methods including BR [40], CA [41], MCI [42], NFI [43], SS-KDE [44], GMR [20], GR [45], and MTMR [26] on the RGBT-Saliency dataset
The image pairs are recorded in bad weather, such as snowy, rainy, hazy, or cloudy weather
Summary
Image saliency detection aims to quickly capture the most important and useful information from a scene by using the human visual attention mechanism, which can reduce the complexity of subsequent image processing, and has been applied to numerous vision problems including image classification [1], image retrieval [2], image encryption [3,4], video summary [5], and so on. Thermal images can work well in low illumination, and have good discrimination when the target and the background have similar colors or shapes RGB-T saliency detection algorithms can obtain better results by handling challenging issues including low illumination, cluttered background, low contrast, and so on. The existing graph-based fusion models only use the static graph The limitation of this kind of method is that it cannot explore the relationship between nodes at the target level and gain better fusion of multi-modality information.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
