<title>Quantitative metric for comparison of night vision fusion algorithms</title>

Abstract

This paper describes development and testing of a program that provides a quantitative metric for the comparison of night vision fusion algorithms. The user enters into the Metric Program the names of a thennal file, a vision file and the corresponding fused image file. The program assigns a fusion rating to the algorithm based on the following four quantitative tests: information content (Ic), vision retention (vr), thermal retention (tr), and the bar test to detect black segments. In Ic the information content ofthe fused image is compared with a weighted sum of the vision and thermal images. In yr the number of faint lights that the fused image failed to incorporate is counted. In tr the number of pixels from the thennal file included in the fused image is determined. With some fusion algorithms if one of the sensors is blocked, a black segment appears in that area in the fused image, thus losing the information from the unblocked sensor. To test for this the Metric Program creates a thermal file with three horizontal black bars. The program then allows the user to call the executable file of the algorithm under test. Then the user is asked to examine the fused image. if three pitch-black horizontal bars appear on the image, the algorithm fails the test. While the bar test is invariant to the vision/thennal image pair used, the other tests are not. For this reason it is suggested that an algorithm should be tested with 5 or 6 different image pairs and a mean fusion rating calculated. The program is used to evaluate several different algorithms. Day vision fusion algorithms are also tested.

Towards cognitive image fusion

“…However, this usually means time consuming and often expensive experiments involving a large number of human subjects. In recent years, a number of computational image fusion quality assessment metrics have therefore been proposed [2,3,[5][6][7][12][13][14]36,42,44,46,49,[52][53][54][55]. Although some of these metrics agree with human visual perception to some extent, most of them cannot predict observer performance for different input imagery and scenarios.…”

Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments

“…To address such concerns would require the formulation and construction of efficient and robust domainbased measures of fusion performance and fusion effectiveness -but the development of pertinent metrics with respect to hydrological modelling is still awaited. This area of research has in fact received limited attention, relative to its overall importance, although some attempts at quantitative estimation of the fusion benefit (or lack thereof) can be found in other domains of scientific investigation (Dasarathy and Townsend, 1999;Xydeas and Petrovic, 2000;Ulug and McCullough, 2000). There has also been an attempt to represent the effectiveness of the fusion process itself -as opposed to the effectiveness of the fusion operation in terms of a correct answer.…”

Evaluation of Image Fusion Performance with Visible Differences

“…So far, only a limited number of relatively application dependent objective image fusion performance metrics has been published in the literature [3,4,9,10,12]. Target signature consistency as an evaluation criterion for detection/recognition applications is proposed in [10].…”