Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform

@article{Guo2008SpatiotemporalSD,
  title={Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform},
  author={Chenlei Guo and Qi Ma and Liming Zhang},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2008},
  pages={1-8}
}
Salient areas in natural scenes are generally regarded as the candidates of attention focus in human eyes, which is the key stage in object detection. In computer vision, many models have been proposed to simulate the behavior of eyes such as SaliencyToolBox (STB), neuromorphic vision toolkit (NVT) and etc., but they demand high computational cost and their remarkable results mostly rely on the choice of parameters. Recently a simple and fast approach based on Fourier transform called spectral… Expand
A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression
TLDR
Extensive tests of videos, natural images, and psychological patterns show that the proposed PQFT model is more effective in saliency detection and can predict eye fixations better than other state-of-the-art models in previous literature. Expand
Saliency based on human visual sensitivity and phase spectrum of the quaternion Fourier transform
  • O. Buzatu, A. Savin
  • Computer Science
  • International Symposium on Signals, Circuits and Systems ISSCS2013
  • 2013
TLDR
Adding amplitude spectrum information, based on the contrast sensitivity of the HVS, combined with the phase spectrum of the quaternion Fourier transform (QFT), a human gaze prediction model is proposed. Expand
Quaternion-Based Spectral Saliency Detection for Eye Fixation Prediction
TLDR
This work systematically integrate and evaluates quaternion DCT- and FFT-based spectral saliency detection, weighted quaternions color space components, and the use of multiple resolutions, and proposes the useof the eigenaxes and eigenangles for spectral Saliency models that are based on the quaternION Fourier transform. Expand
Saliency Detection by Adaptive Channel Fusion
TLDR
This letter proposes a frequency domain based framework, which exploits HFT-based saliency algorithm and finds a way to weigh the importance of different channels in saliency detection across space, and shows that the proposed method outperforms nine outstanding eye fixation prediction models on four most commonly-used datasets. Expand
A novel approach for saliency detection based on multiscale phase spectrum
  • D. Singh, S. Meher
  • Computer Science
  • 2012 International Conference on Communication, Information & Computing Technology (ICCICT)
  • 2012
TLDR
Four state-of-art of salient object detection techniques are analyzed along with the ground truth and compared against the proposed method for experimental evaluation, showing better results than other methods. Expand
EXPLOITING QUATERNION RARE ORIENTATIONS FOR IMAGE SALIENCY DETECTION
Saliency detection has become lately a valuable tool for many image processing applications. Yet, methodology variations of existing algorithms still permit performances improvement. In this paper aExpand
Scale-Invariant Amplitude Spectrum Modulation for Visual Saliency Detection
  • D. Chen, H. Chu
  • Mathematics, Medicine
  • IEEE Transactions on Neural Networks and Learning Systems
  • 2012
TLDR
Simulation results suggest that the proposed model is more accurate in predicting human eye fixation and is more robust against different types of stimulus when compared with competing models. Expand
2D mel-cepstrum based saliency detection
TLDR
A 2D mel-cepstrum based spectral residual saliency detection model (MCSR) is proposed to provide perceptually meaningful and more informative saliency map with less redundancy and without down-sampling as in saliency residual approach. Expand
Spatio-Temporal Saliency Perception via Hypercomplex Frequency Spectral Contrast
TLDR
The proposed HSC algorithm represents the features in the HSV color space and features of motion by a hypercomplex number, and the spatio-temporal salient objects are efficiently detected by hypercomplex Fourier spectral contrast in parallel. Expand
Motion saliency detection using a temporal fourier transform
TLDR
This paper proposes a new type of motion saliency detection method, Temporal Fourier Transform, for fast motion Saliency detection, which achieves both good accuracy and fast computation. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 15 REFERENCES
Saliency Detection: A Spectral Residual Approach
TLDR
A simple method for the visual saliency detection is presented, independent of features, categories, or other forms of prior knowledge of the objects, and a fast method to construct the corresponding saliency map in spatial domain is proposed. Expand
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
TLDR
A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented, which breaks down the complex problem of scene understanding by rapidly selecting conspicuous locations to be analyzed in detail. Expand
Integrated learning of saliency, complex features, and object detectors from cluttered scenes
  • D. Gao, N. Vasconcelos
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
Experimental evidence is given in support of the arguments that different levels of feature complexity are optimal for different object classes, and that optimal features range from parts to templates, depending on the variability of the object class. Expand
Learning to Detect a Salient Object
  • Tie Liu, Zejian Yuan, +4 authors H. Shum
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
TLDR
A set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, are proposed to describe a salient object locally, regionally, and globally. Expand
Seeing, sensing, and scrutinizing
TLDR
This argument centers around the proposal that focused attention is needed for the explicit perception of change, and it is proposed that perception involves a virtual representation, where object representations do not accumulate, but are formed as needed. Expand
Modeling attention to salient proto-objects
TLDR
It is demonstrated that the suggested model can enable a model of object recognition in cortex to expand from recognizing individual objects in isolation to sequentially recognizing all objects in a more complex scene. Expand
Attentional Selection for Object Recognition - A Gentle Way
TLDR
A combined model for spatial attention and object recognition in which the recognition system monitors the entire visual field, but attentional modulation by as little as 20% at a high level is sufficient to recognize multiple objects. Expand
Guided Search 2.0 A revised model of visual search
  • J. Wolfe
  • Psychology, Medicine
  • Psychonomic bulletin & review
  • 1994
TLDR
This paper reviews the visual search literature and presents a model of human search behavior, a revision of the guided search 2.0 model in which virtually all aspects of the model have been made more explicit and/or revised in light of new data. Expand
Hypercomplex Fourier Transforms of Color Images
  • T. Ell, S. Sangwine
  • Mathematics, Computer Science
  • IEEE Transactions on Image Processing
  • 2007
TLDR
Hypercomplex numbers, specifically quaternions, are used to define a Fourier transform applicable to color images, and the properties of the transform are developed, and it is shown that the transform may be computed using two standard complex fast Fourier transforms. Expand
A feature-integration theory of attention
TLDR
A new hypothesis about the role of focused attention is proposed, which offers a new set of criteria for distinguishing separable from integral features and a new rationale for predicting which tasks will show attention limits and which will not. Expand
...
1
2
...