期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 29, 期 -, 页码 9496-9507出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2020.3028170
关键词
Salient object detection; cross-modal; boundary-aware estimation
资金
- National Natural Science Foundation of China [61672158, 62072110, 61702104, 61972162, 61702194]
- Natural Science Foundation of Fujian Province [2019J02006]
Mobile devices usually mount a depth sensor to resolve ill-posed problems, like salient object detection on cluttered background. The main barrier of exploring RGBD data is to handle the information from two different modalities. To cope with this problem, in this paper, we propose a boundary-aware cross-modal fusion network for RGBD salient object detection. In particular, to enhance the fusion of color and depth features, we present a cross-modal feature sampling module to balance the contribution of the RGB and depth features based on the statistics of their channel values. In addition, in our multi-scale dense fusion network architecture, we not only incorporate edge-sensitive losses to preserve the boundary of the detected salient region, but also refine its structure by merging the estimated saliency maps of different scales. We accomplish the multi-scale saliency map merging using two alternative methods which produce refined saliency maps via per-pixel weighted combination and an encoder-decoder network. Extensive experimental evaluations demonstrate that our proposed framework can achieve the state-of-the-art performance on several public RGBD-based datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据