Video object segmentation (VOS) is a significant yet challenging task in computer vision. In VOS, two challenging problems, including occlusions and distractions, are needed to be handled especially in multi-object videos. However, most existing methods have difficulty in efficiently tackling these two factors. To this end, a new semi-supervised VOS model, called Distance-Guided Mask Propagation Model (DGMPM), is proposed in this paper. Specifically, a novel embedding distance module, which is utilized to generate a soft cue for handling occlusions, is implemented by calculating distance difference between target features and the centers of foreground/background features. This non-parametric module that is based on global contrast between the target and reference features to detect object regions even if occlusions still exist, is less sensitive to the feature scale. The prior knowledge of the previous frame is applied as spatial guidance in the decoder to reduce the effect of distractions. In addition, spatial attention blocks are designed to strengthen the network to focus on the target object and rectify the prediction results. Extensive experiments demonstrate that the proposed DGMPM achieves competitive performance on accuracy and runtime in comparison with state-of-the-art methods.
|Title of host publication||2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Publication status||Published - Jul 2020|
|Event||2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom|
Duration: 19 Jul 2020 → 24 Jul 2020
|Name||Proceedings of the International Joint Conference on Neural Networks|
|Conference||2020 International Joint Conference on Neural Networks, IJCNN 2020|
|Period||19/07/20 → 24/07/20|
Bibliographical noteFunding Information:
This research was supported by National Key R&D Program of China (No. 2017YFC0806000), by National Natural Science Foundation of China (No. 11627802, 51678249), State Key Lab of Subtropical Building Science, South China University of Technology (2018ZB33), and the State Scholarship Fund of China Scholarship Council (201806155022).
© 2020 IEEE.
- Attention Mechanism
- Fully Convolutional Neural Networks
- Spatial Guidance
- Video Object Segmentation