A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Principled Approach to Detecting Surprising Events in Video
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
2006 Special Issue: Modeling attention to salient proto-objects
Neural Networks
Segmentation of Multivariate Mixed Data via Lossy Data Coding and Compression
IEEE Transactions on Pattern Analysis and Machine Intelligence
Stochastic bottom-up fixation prediction and saccade generation
Image and Vision Computing
| Hi-index | 0.00 |
By the guidance of attention, human visual system is able to locate objects of interest in complex scene. In this paper, we propose a novel visual saliency detection method - the conditional saliency for both image and video. Inspired by biological vision, the definition of visual saliency follows a strictly local approach. Given the surrounding area, the saliency is defined as the minimum uncertainty of the local region, namely the minimum conditional entropy, when the perceptional distortion is considered. To simplify the problem, we approximate the conditional entropy by the lossy coding length of multivariate Gaussian data. The final saliency map is accumulated by pixels and further segmented to detect the proto-objects. Experiments are conducted on both image and video. And the results indicate a robust and reliable feature invariance saliency.