FD: A feature difference based image clutter metric for targeting performance

Xu, Dejiang; Shi, Zelin

doi:10.1016/j.infrared.2012.08.001

Cited by 11 publications

(14 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Error analysis and correlation tests are adopted to assess clutter metrics between the prediction targeting performances based on clutter metrics and 62 observers' psychophysical experimental results including detection probability, false alarm probability and search time. The evaluated clutter metrics include the recently proposed target structural similarity metric (TSSIM) [23] denoted by C S S , feature difference metric (FD) [49] denoted byC F D , and the proposed DSIM metric denoted byC DS I M . The adopted performance assessment measures contain root mean square (RMS) error denoted by, Pearson Linear correlation coefficient denoted by r p , Spearman's rank correlation coefficient denoted by r s , and Kendall's rank correlation coefficient denoted by r k between the 62 observers' psychophysical experimental results and the targeting prediction performance as (40)(41)(42).…”

Section: Experimental Verification and Results Analysismentioning

confidence: 99%

“…Therefore, clutter can be defined as the parts within a scene that distract observers' attention and affect targeting performances. To be generalized, the so-called background clutter is defined as the remaining parts within a scene by removing the target and system noise, which is also adopted in this paper like the existed clutter metrics [1], [3], [9]- [12], [15]- [23], [49].…”

Section: Definition Of Image Clutter Metricmentioning

confidence: 99%

“…Accuracy and complexity seems to be a contradictory unity . p a m y t i r a l i m i s s i d e c n a n i m u l ) c ( e g a m i r e t t u l c ) b ( e g a m i t e g r a t ) [49], we choose two times to reduce the effect of the block size [31]. (a) and (b) are the target and clutter images of the twentieth image in Search_2 dataset [26], [27], respectively.…”

Section: A Human Vision Perceptual Dissimilarity Measure (Vpdm) Betwmentioning

confidence: 99%

“…In the man-in-the-loop target acquisition system, the existed image clutter metrics [1], [3], [9]- [12], [15]- [23], [49] did Z. Shi is with Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 100081, China (e-mail: zlshi@sia.cn).…”

Section: Introductionmentioning

confidence: 99%

“…Recently, a FD metric [49] is proposed based on the sensitivity of the HVS to image features. The low-level image features are divided into two complementary features that are a phase congruency feature and a directional contrast feature, and then two M-relative distances [50], [51] are introduced to calculate the feature difference between the target and clutter images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

DSIM: A DisSIMilarity-Based Image Clutter Metric for Targeting Performance

Shi

2013

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Previous image clutter metrics were proposed on the thought that clutter was just a perceptual effect, while we identify clutter as both perceptual and cognitive effects. Under this identification, we give a new definition of image clutter metric by analyzing the research results in the fields of visual psychology and psychophysics. According to the definition, we further put forward a DisSIMilarity (DSIM) based image clutter metric, which can also be taken as a kind of HVS-based signal-to-clutter ratio. The earlier image clutter metrics produced limited success in predicting targeting performance mainly since they did not consider brain cognitive characteristics. We develop a brain cognitive dissimilarity measure (BCDM) as a quantitative estimate of the selection weights which are allocated by brain attentional mechanism to affect visual selection processes. A human vision perceptual dissimilarity measure (VPDM), fully embodying vision perceptual properties, is first established between the target and clutter images, and then we utilize the BCDM between the two images as selection weights to pool the VPDM to be a clutter metric, which can be called DSIM metric. The metric is tested in Search_2 dataset provided by TNO Human Factors Research Institute of Netherlands. Error analysis and correlation tests demonstrate that the DSIM metric makes a more significant improvement than previously proposed metrics in predicting 62 observers' targeting performances including detection probability, false alarm probability and search time.

show abstract