Скачать или смотреть GSoC 2014 - Saliency based Improvements for Tracking Purposes_Final

This video briefly shows the results of my work for GSoC 2014. The principal purpose of this API is to give a unique interface, a unique framework for use and plug sever saliency algorithms, also with very different nature and methodology, but they share the same purpose, organizing algorithms into three main categories:

Static Saliency: algorithms belonging to this category, exploit different image features that allow to detect salient objects in a non dynamic scenarios.

Motion Saliency: algorithms belonging to this category, are particularly focused to detect salient objects over time (hence also over frame), then there is a temporal component sealing cosider that allows to detect “moving” objects as salient, meaning therefore also the more general sense of detection the changes in the scene.

Objectness: Objectness is usually represented as a value which reflects how likely an image window covers an object of any category. Algorithms belonging to this category, avoid making decisions early on, by proposing a small number of category-independent proposals, that are expected to cover all objects in an image. Being able to perceive objects before identifying them is closely related to bottom up visual attention (saliency).

Presently, the following methods have been implemented:

Spectral Residual approach (Hou, Xiaodi, and Liqing Zhang. “Saliency detection: A spectral residual approach.” Computer Vision and Pattern Recognition, 2007. CVPR‘07. IEEE Conference on. IEEE, 2007.) for Static Saliency category.

Binarized normed gradients algorithm (Cheng, Ming-Ming, et al. “BING: Binarized normed gradients for objectness estimation at 300fps.” IEEE CVPR. 2014.) for Objectness category.

Bin Wang Apr 2014 (B. Wang and P. Dudek "A Fast Self-tuning Background Subtraction Algorithm", in proc of IEEE Workshop on Change Detection, 2014) for Motion Saliency category.