GAFFE: A gaze-attentive fixation finding engine

被引:121
作者
Rajashekar, Umesh [1 ]
van der Linde, Ian
Bovik, Alan C. [2 ]
Cormack, Lawrence K. [3 ]
机构
[1] NYU, Lab Computat Vis, New York, NY 10003 USA
[2] Univ Texas Austin, Ctr Perceptual Syst, Dept Elect & Comp Engn, Austin, TX 78712 USA
[3] Univ Texas Austin, Dept Psychol, Ctr Perceptual Syst, Austin, TX 78712 USA
基金
美国国家科学基金会;
关键词
eye tracking; fixation selection; foveation; point-of-gaze;
D O I
10.1109/TIP.2008.917218
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The ability to automatically detect visually interesting regions in images has many practical applications, especially in the design of active machine vision and automatic visual surveillance systems. Analysis of the statistics of image features at observers' gaze can provide insights into the mechanisms of fixation selection in humans. Using a foveated analysis framework, we studied the statistics of four low-level local image features: luminance, contrast, and bandpass outputs of both luminance and contrast, and discovered that image patches around human fixations had, on average, higher values of each of these features than image patches selected at random. Contrast-bandpass showed the greatest difference between human and random fixations, followed by luminance-bandpass, RMS contrast, and luminance. Using these measurements, we present a new algorithm that selects image regions as likely candidates for fixation. These regions are shown to correlate well with fixations recorded from human observers.
引用
收藏
页码:564 / 573
页数:10
相关论文
共 45 条
[1]   PERIPHERAL SPATIAL VISION - LIMITS IMPOSED BY OPTICS, PHOTORECEPTORS, AND RECEPTOR POOLING [J].
BANKS, MS ;
SEKULER, AB ;
ANDERSON, SJ .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1991, 8 (11) :1775-1787
[2]  
Barlow H. B., 1961, Sensory_Communication, P217
[3]   SELECTIVE SUPPRESSION OF THE MAGNOCELLULAR VISUAL PATHWAY DURING SACCADIC EYE-MOVEMENTS [J].
BURR, DC ;
MORRONE, MC ;
ROSS, J .
NATURE, 1994, 371 (6497) :511-513
[4]  
Buswell T. G., 1935, PEOPLE LOOK PICTURES
[5]  
Efron E., 1993, INTRO BOOTSTRAP
[6]  
Ester M., 1996, P 2 INT C KNOWL DISC, P226, DOI DOI 10.5555/3001460.3001507
[7]   A foveated silicon retina for two-dimensional tracking [J].
Etienne-Cummings, R ;
Van der Spiegel, J ;
Mueller, P ;
Zhang, MZ .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 2000, 47 (06) :504-517
[8]   RELATIONS BETWEEN THE STATISTICS OF NATURAL IMAGES AND THE RESPONSE PROPERTIES OF CORTICAL-CELLS [J].
FIELD, DJ .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1987, 4 (12) :2379-2394
[9]   A real-time foveated multiresolution system for low-bandwidth video communication [J].
Geisler, WS ;
Perry, JS .
HUMAN VISION AND ELECTRONIC IMAGING III, 1998, 3299 :294-305
[10]   OBJECT IDENTIFICATION IN CONTEXT - THE VISUAL PROCESSING OF NATURAL SCENES [J].
HENDERSON, JM .
CANADIAN JOURNAL OF PSYCHOLOGY-REVUE CANADIENNE DE PSYCHOLOGIE, 1992, 46 (03) :319-341