Co-Saliency Detection for RGBD Images Based on Multi-Constraint Feature Matching and Cross Label Pro
Co-Saliency Detection for RGBD Images Based on Multi-Constraint Feature Matching and Cross Label Propagation
Co-saliency detection aims at extracting the common salient regions from an image group containing two or more relevant images. It is a newly emerging topic in computer vision community. Different from the most existing co-saliency methods focusing on RGB images, this paper proposes a novel co-saliency detection model for RGBD images, which utilizes the depth information to enhance identification of co-saliency. First, the intra saliency map for each image is generated by the single image saliency model, while the inter saliency map is calculated based on the multi-constraint feature matching, which represents the constraint relationship among multiple images. Then, the optimization scheme, namely cross label propagation, is used to refine the intra and inter saliency maps in a cross way. Finally, all the original and optimized saliency maps are integrated to generate the final co-saliency result. The proposed method introduces the depth information and multi-constraint feature matching to improve the performance of co-saliency detection. Moreover, the proposed method can effectively exploit any existing single image saliency model to work well in co-saliency scenarios. Experiments on two RGBD co-saliency datasets demonstrate the effectiveness of our proposed model.
Existing co-saliency detection models are focused on RGB image and have achieved satisfactory performances. However, little work has been done on co-saliency detection for RGBD images. Depth information has demonstrated its usefulness for many computer vision tasks, such as recognition, object segmentation, and saliency detection. It reduces the ambiguity with color descriptors and enhances the identification of the object from the complex background. In this paper, the depth information is introduced as a novel cue for the co-saliency detection model.
A novel co-saliency model for RGBD images is proposed, which integrates the depth cue to enhance the identification of co-saliency. The multi-constraint based feature matching method is designed to capture the corresponding relationship and constrain the inter saliency map generation. Additionally, a Cross Label Propagation (CLP) method is proposed to optimize the intra and inter saliency maps in a cross way. The major contributions of the proposed co-saliency detection method are summarized as follows.
To the best of our knowledge, our method is the first model that detects the co-salient objects from RGBD images. The depth information is demonstrated to be served as a useful complement for co-saliency detection.
A multi-constraint feature matching method is introduced to constrain the inter saliency map generation, which is robust to the complex backgrounds.
The CLP scheme is proposed to optimize the co-saliency model in our method.
The proposed method can effectively exploit any existing single image saliency model to work well in cosaliency scenarios.