Salient object detection via global and local cues

Previous saliency detection algorithms used to focus on low level features directly or utilize a bunch of sample images and manually labeled ground truth to train a high level learning model. In this paper, we propose a novel coding-based saliency measure by exploring both global and local cues for...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Pattern recognition Ročník 48; číslo 10; s. 3258 - 3267
Hlavní autori: Tong, Na, Lu, Huchuan, Zhang, Ying, Ruan, Xiang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.10.2015
Predmet:
ISSN:0031-3203, 1873-5142
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Previous saliency detection algorithms used to focus on low level features directly or utilize a bunch of sample images and manually labeled ground truth to train a high level learning model. In this paper, we propose a novel coding-based saliency measure by exploring both global and local cues for saliency computation. Firstly, we construct a bottom-up saliency map by considering global contrast information via low level features. Secondly, by using a locality-constrained linear coding algorithm, a top-down saliency map is formulated based on the reconstruction error. To better exploit the local and global information, we integrate the bottom-up and top-down maps as the final saliency map. Extensive experimental results on three large benchmark datasets demonstrate that the proposed approach outperforms 22 state-of-the-art methods in terms of three popular evaluation measures, i.e., the Precision and Recall curve, Area Under ROC Curve and F-measure value. Furthermore, the proposed coding-based method can be easily applied in other methods for significant improvement. •We present a coding-based algorithm for salient object detection.•Integration of local and global cues makes the saliency maps more accurate, intact.•Bottom-up maps provide foreground and background codebooks for following steps.•Fusion of FC and BC based results makes the saliency results more uniform, robust.•Our coding-based method can be easily applied in other methods for improvement.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2014.12.005