Abstract | ||
---|---|---|
Saliency detection technology has been greatly developed and applied in recent years. However, the performance of current methods is not satisfactory in complex scenes. One of the reasons is that the performance improvement is often carried out through utilizing complicated mathematical models and involving multiple features rather than classifying the scene complexity and respectively detecting saliency. To break this unified detection schema for generating better results, we propose a method of scene classification-oriented saliency detection via the modularized prescription in this paper. Different scenes are described by a scene complexity expression model, and they are analyzed and discriminately detected by different pipelines. This process seems like that doctors can tailor the treatment prescriptions when they meet different symptoms. Moreover, two SVM-based classifiers are trained for scene classification and sky region identification, and the proposed sky region discrimination and erase model can be used to efficiently decrease the saliency interference by the high luminance of the background sky regions. Experimental results demonstrate the effectiveness and superiority of the proposed method in both higher precision and better smoothness, especially for detecting in structure complex scenes. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/s00371-018-1475-0 | The Visual Computer |
Keywords | Field | DocType |
Saliency detection, Scene classification, Modularized prescription, Scene complexity expression, Support Vector Machine (SVM) | Computer vision,Computer science,Salience (neuroscience),Support vector machine,Sky,Artificial intelligence,Interference (wave propagation),Mathematical model,Smoothness,Luminance,Performance improvement | Journal |
Volume | Issue | ISSN |
35.0 | 4 | 1432-2315 |
Citations | PageRank | References |
1 | 0.35 | 27 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunlei Yang | 1 | 96 | 10.76 |
Jiexin Pu | 2 | 92 | 19.85 |
Yongsheng Dong | 3 | 230 | 17.59 |
Yong Xu | 4 | 339 | 31.64 |
yanna si | 5 | 1 | 2.04 |
Zhonghua Liu | 6 | 115 | 11.12 |