Soft-biometrics evaluation for people re-identification in uncontrolled multi-camera environments

Abstract

A novel method for person identification based on soft-biometrics and oriented to work in real video surveillance environments is proposed in this paper. Thus, an evaluation of relevance's level of several appearance features is carried out with this purpose. First, a bag-of-soft-biometric features related to color, texture, local features, and geometry are extracted from individuals. The relevance of each feature has been deeply analyzed through different proposed methods. Features are ranked and weighted according to their relevance value. Later, each method is evaluated under two different scenarios: mono-camera and multi-camera surveillance images. In order to test the system in a realistic way, it has been evaluated over standard databases in the surveillance community: PETS 2006, PETS 2009, CAVIAR, SAIVT-SoftBio, and CAVIAR4REID. Moreover, a new database was acquired at Adolfo Suarez Madrid-Barajas international airport. This database was acquired under regular conditions and infrastructure of the Barajas airport, no additional camera or special settings were installed for this purpose. An analysis of relevance for each feature acquired in these two scenarios is presented. The results obtained demonstrate the promising potential of the soft-biometric approach. Finally, an optimal system configuration according to each scenario is obtained.

Appearance model update based on online learning and soft‐biometrics traits for people re‐identification in multi‐camera environments

“…As this work, it is focused on the updating process of an appearance model; all the features were computed following the work presented in [34]. These features were selected to work under sub‐optimal resolution and lighting conditions, as it is the rule in a real security camera environment.…”

“…Here, SD means standard deviation and Matrix of Co‐Occurrence (MCO) means co‐occurrence matrix. From these features, a vector is generated to identify each people in the scene or for a more detailed analysis, see [34]. Next, with this set of soft‐biometric features, a model is constructed; that is, the people appearance model is generated and updated over several conditions.…”

Analysing comparative soft biometrics from crowdsourced annotations

“…Further approaches extract global and body soft biometrics from multi-camera environments [28], depth images [25], or most recently, by applying state-of-the-art Convolutional Neural Networks to still images [46,33]. Combining several soft biometrics modalities, especially clothing, has proven important in improving subject recognition rates [3,14] and can be estimated for surveillance tracking and search [9,44].…”