An evidential fusion approach for gender profiling

Abstract

Abstract. CCTV (Closed-Circuit TeleVision) systems are broadly deployed in the present world. To ensure in-time reaction for intelligent surveillance, it is a fundamental task for real-world applications to determine the gender of people of interest. However, normal video algorithms for gender profiling (usually face profiling) have three drawbacks. First, the profiling result is always uncertain. Second, the profiling result is not stable. The degree of certainty usually varies over time, sometimes even to the extent that a male is classified as a female, and vice versa. Third, for a robust profiling result in cases that a person's face is not visible, other features, such as body shape, are required. These algorithms may provide different recognition results -at the very least, they will provide different degrees of certainties. To overcome these problems, in this paper, we introduce an Dempster-Shafer (DS) evidential approach that makes use of profiling results from multiple algorithms over a period of time, in particular, Denoeux's cautious rule is applied for fusing mass functions through time lines. Experiments show that this approach does provide better results than single profiling results and classic fusion results. Furthermore, it is found that if severe mis-classification has occurred at the beginning of the time line, the combination can yield undesirable results. To remedy this weakness, we further propose three extensions to the evidential approach proposed above incorporating notions of time-window, time-attenuation, and time-discounting, respectively. These extensions also applies Denoeux's rule along with time lines and take the DS approach as a special case. Experiments show that these three extensions do provide better results than their predecessor when mis-classifications occur.

Multi-sensor data fusion based on the belief divergence measure of evidences and the belief entropy

“…Dempster-Shafer (D-S) evidence theory, which was firstly proposed by Dempster [23] and was extended by Shafer [24] is an useful uncertainty reasoning approach. D-S evidence theory is flexible and effective in modelling both of the uncertainty and imprecision without prior information, so that it has been applied broadly in all kinds of fields, such as fault diagnosis [39][40][41][42], decision making [43][44][45][46], pattern recognition [47][48][49], risk analysis [50], supplier selection [51], human reliability analysis [52], and so on [53]. Whereas, when fusing the highly conflicting evidences, the system based on the classical D-S evidence theory may result in the counter-intuitive results [54].…”

An evidential Markov decision making model

“…Dempster-Shafer (D-S) evidence theory [48,49] is a powerful tool to handle the uncertainty. It has been widely used in many fields, like risk analysis [52][53][54], controller design [55,56], pattern recognition [57][58][59], fault diagnosis [60][61][62], multiple attribute decision making [63,64] and so on.…”

Weighted Evidence Combination Based on Distance of Evidence and Entropy Function

“…Dempster's combination rule which has some interesting mathematical properties, such as associativity and commutativity, plays an important role in evidence theory [4]. Now the evidence theory is utilized widely in many fields, such as decision making [4][5][6], supplier selection [7,8], reliability analysis [9][10][11], and optimization under uncertain environment [12][13][14]. Due to the complexity in fault diagnosis [15,16], sensor data fusion based on evidence theory in these fields is also heavily studied [17,18].…”