Evaluating Feature Importance for Re-identification

Abstract

Person re-identification methods seek robust person matching through combining feature types. Often, these features are assigned implicitly with a single vector of global weights, which are assumed to be universally and equally good for matching all individuals, independent of their different appearances. In this study, we present a comprehensive comparison and evaluation of up-to-date imagery features for person re-identification. We show that certain features play more important roles than others for different people. To that end, we introduce an unsupervised approach to learning a bottom-up measurement of feature importance. This is achieved through first automatically grouping individuals with similar appearance characteristics into different prototypes/clusters. Different features extracted from different individuals are then automatically weighted adaptively driven by their inherent appearance characteristics defined by the associated prototype. We show comparative evaluation on the re-identification effectiveness of the proposed prototype-sensitive feature importance-based method as compared to two generic weight-based global feature importance methods. We conclude by showing that their combination is able to yield more accurate person re-identification.

Multi-Object Tracking with Data Association by a Similarity Identification Model

“…Feature selection has been used to improve the discriminative power of the distance function by evaluating the discriminative importance of different types of features to properly weight them, as it is presented in [214].…”

Behavioral Pedestrian Tracking Using a Camera and LiDAR Sensors on a Moving Vehicle

“…This task is a typical person re-identification problem where a specific person is queried in a database of known identities. Several studies [41,42] have shown that HSV and YCbCr features exhibit superior person re-identification performances over other features, i.e., these features are highly sensitive to the unique visual appearance of each person. Thus, the log-likelihood appearance value for each detection bolddt is computed by comparing the normalized 48 bin HSV color histogram to the HSV histogram of the target.…”

Transferring learning from multi-person tracking to person re-identification

“…These mentioned methods address the learning of a global weighting that reflects the stability of each feature component across two cameras, so they can be grouped under the paradigm of Global Feature Importance (GFI) methods. On contrary, in [33], a Prototype-Sensitive Feature Importance based method is proposed to adaptively weight features according to different clusters of population.…”

“…In [33], a Prototype-Sensitive Feature Importance based method is proposed to adaptively weight features according to different clusters of population. On contrary, [36] present a Global Feature Importance (GFI) approach, addressing the learning of a global weighting, i.e.…”