Does Thermal Really Always Matter for RGB-T Salient Object Detection?

Cong，Runmin1; Zhang，Kepu1; Zhang，Chen1; Zheng，Feng2; Zhao，Yao1; Huang，Qingming3; Kwong，Sam4

2022

10.1109/TMM.2022.3216476

IEEE TRANSACTIONS ON MULTIMEDIA   影响因子和分区

1520-9210

1941-0077

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing RGB-T SOD models focus on how to perform cross-modality feature fusion, ignoring whether thermal image is really always matter in SOD task. Starting from the definition and nature of this task, this paper rethinks the connotation of thermal modality, and proposes a network named TNet to solve the RGB-T SOD task. In this paper, we introduce a global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities. In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase. On the one hand, we introduce a semantic constraint provider to enrich the semantics of thermal images in the encoding phase, which makes thermal modality more suitable for the SOD task. On the other hand, we introduce a two-stage localization and complementation module in the decoding phase to transfer object localization cue and internal integrity cue in thermal features to the RGB modality. Extensive experiments on three datasets show that the proposed TNet achieves competitive performance compared with 20 state-of-the-art methods. The code and results can be found from the link of https://rmcong.github.io/proj_TNet.html.

Decoding Feature extraction Global illumination estimation Lighting Localization and complementation Location awareness Object detection RGB-T images Salient object detection Semantic constraint provider Semantics Task analysis

EI ; SCI

英语

其他

20224413035930

Computer vision ; Decoding ; Encoding (symbols) ; Feature extraction ; Job analysis ; Lighting ; Object detection ; Object recognition ; Signal encoding

Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Vision:741.2

COMPUTER SCIENCE

2-s2.0-85140716697

Scopus

1.Institute of Information Science, Beijing Jiaotong University, Beijing, China
2.Department of Computer Science and Technology, Southern University of Science and Technology, Shenzhen, China
3.School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China
4.Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China

Cong，Runmin,Zhang，Kepu,Zhang，Chen,et al. Does Thermal Really Always Matter for RGB-T Salient Object Detection?[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2022,PP(99):1-12.

Cong，Runmin.,Zhang，Kepu.,Zhang，Chen.,Zheng，Feng.,Zhao，Yao.,...&Kwong，Sam.(2022).Does Thermal Really Always Matter for RGB-T Salient Object Detection?.IEEE TRANSACTIONS ON MULTIMEDIA,PP(99),1-12.

Cong，Runmin,et al."Does Thermal Really Always Matter for RGB-T Salient Object Detection?".IEEE TRANSACTIONS ON MULTIMEDIA PP.99(2022):1-12.