A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Saliency, Scale and Image Description
International Journal of Computer Vision
An Affine Invariant Interest Point Detector
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fusing Points and Lines for High Performance Tracking
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A Comparison of Affine Region Detectors
International Journal of Computer Vision
Attention Model Based SIFT Keypoints Filtration for Image Retrieval
ICIS '08 Proceedings of the Seventh IEEE/ACIS International Conference on Computer and Information Science (icis 2008)
SURF: speeded up robust features
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Machine learning for high-speed corner detection
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Images as sets of locally weighted features
Computer Vision and Image Understanding
Proceedings of the Symposium on Eye Tracking Research and Applications
Hi-index | 0.00 |
This paper investigates the coincidence between six interest point detection methods (SIFT, MSER, Harris-Laplace, SURF, FAST & Kadir-Brady Saliency) with two robust "bottom-up" models of visual saliency (Itti and Harel) as well as "task" salient surfaces derived from observer eye-tracking data. Comprehensive statistics for all detectors vs. saliency models are presented in the presence and absence of a visual search task. It is found that SURF interest-points generate the highest coincidence with saliency and the overlap is superior by 15% for the SURF detector compared to other features. The overlap of image features with task saliency is found to be also distributed towards the salient regions. However the introduction of a specific search task creates high ambiguity in knowing how attention is shifted. It is found that the Kadir-Brady interest point is more resilient to this shift but is the least coincident overall.