A Spatio-Temporal Isotropic Operator for the Attention-Point Extraction

It is proposed to extract multi-location image features at maxima points of a spatio-temporal attention operator, which indicates locations with high intensity contrast, region homogeneity, shape saliency and temporal change. The scale-adaptive estimation of local change (motion) and its aggregation with the region shape saliency contribute to robust detection of moving objects. Experiments on the accuracy of interest-point detection have proved the operator consistency and its high potential for object detection in image sequences.

[1]  Hemant D. Tagare,et al.  A Maximum-Likelihood Strategy for Directing Attention during Visual Search , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[3]  Tony Lindeberg,et al.  Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention , 1993, International Journal of Computer Vision.

[4]  Harry Wechsler,et al.  Detection and localization of objects in time-varying imagery using attention, representation and memory pyramids , 1996, Pattern Recognit..

[5]  David G. Stork,et al.  Pattern Classification , 1973 .

[6]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[7]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[8]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[10]  Yehezkel Yeshurun,et al.  Context-free attentional operators: The generalized symmetry transform , 1995, International Journal of Computer Vision.

[11]  Ivan Laptev,et al.  On Space-Time Interest Points , 2005, International Journal of Computer Vision.

[12]  Roman M. Palenichka,et al.  Multiscale Isotropic Matched Filtering for Individual Tree Detection in LiDAR Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Tomaso A. Poggio,et al.  Image Representations and Feature Selection for Multimedia Database Search , 2003, IEEE Trans. Knowl. Data Eng..

[14]  Jeff B. Pelz,et al.  Spatio-velocity CSF as a function of retinal velocity using unstabilized stimuli , 2006, Electronic Imaging.

[15]  Petros Maragos,et al.  Pattern Spectrum and Multiscale Shape Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Vito Di Gesù,et al.  A fast recursive algorithm to compute local axial moments , 2001, Signal Process..