Salient object detection and segmentation in videos

Abstract : This thesis focuses on the problem of video salient object detection and video object instance segmentation which aim to detect the most attracting objects or assign consistent object IDs to each pixel in a video sequence. One approach, one overview and one extended model are proposed for video salient object detection, and one approach is proposed for video object instance segmentation. For video salient object detection, we propose: (1) one traditional approach to detect the whole salient object via the adjunction of virtual borders. A guided filter is applied on the temporal output to integrate the spatial edge information for a better detection of the salient object edges. A global spatio-temporal saliency map is obtained by combining the spatial saliency map and the temporal saliency map together according to the entropy. (2) An overview of recent developments for deep-learning based methods is provided. It includes the classifications of the state-of-the-art methods and their frameworks, and the experimental comparison of the performances of the state-of-the-art methods. (3) One extended model further improves the performance of the proposed traditional approach by integrating a deep-learning based image salient object detection method For video object instance segmentation, we propose a deep-learning approach in which the warping confidence computation firstly judges the confidence of the mask warped map, then a semantic selection is introduced to optimize the warped map, where the object is re-identified using the semantics labels of the target object. The proposed approaches have been assessed on the published large-scale and challenging datasets. The experimental results show that the proposed approaches outperform the state-of-the-art methods.
Complete list of metadatas

Cited literature [163 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02299316
Contributor : Abes Star <>
Submitted on : Friday, September 27, 2019 - 4:13:08 PM
Last modification on : Sunday, September 29, 2019 - 1:10:50 AM

File

2019ISAR0003_WANG_Qiong.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02299316, version 1

Citation

Qiong Wang. Salient object detection and segmentation in videos. Signal and Image processing. INSA de Rennes, 2019. English. ⟨NNT : 2019ISAR0003⟩. ⟨tel-02299316⟩

Share

Metrics

Record views

55

Files downloads

20