Person Re-identification by Attributes

Abstract

Visually identifying a target individual reliably in a crowded environment observed by a distributed camera network is critical to a variety of tasks in managing business information, border control, and crime prevention. Automatic re-identification of a human candidate from public space CCTV video is challenging due to spatiotemporal visual feature variations and strong visual similarity between different people, compounded by low-resolution and poor quality video data. In this work, we propose a novel method for re-identification that learns a selection and weighting of mid-level semantic attributes to describe people. Specifically, the model learns an attribute-centric, parts-based feature representation. This differs from and complements existing low-level features for re-identification that rely purely on bottom-up statistics for feature selection, which are limited in discriminating and identifying reliably visual appearances of target people appearing in different camera views under certain degrees of occlusion due to crowdedness. Our experiments demonstrate the effectiveness of our approach compared to existing feature representations when applied to benchmarking datasets.

On-the-fly feature importance mining for person re-identification

“…Second, the conventional top-down approach imposes weights on certain feature types that are considered optimal in a universal sense; while the bottom-up approach aims to discover a set of discriminative features and quantify their importance specific to each individual. From another perspective, the notion of bottom-up learning can also be interpreted as a process of unsupervised discovering latent attribute (see Section 3.1), which is largely different from existing top-down supervised attribute learning [16,15] that requires exhaustive humanspecified attributes.…”

Person re-identification with mutual re-ranking

“…Semantic features, human understandable mid-level features, are applied in [13,20] for person re-identification. In [13], semantic features are first detected by applying SVM with texture features (introduced in [25]).…”

“…In [13], semantic features are first detected by applying SVM with texture features (introduced in [25]). The detected midlevel features are then used for re-identification.…”

“…SDALF [6] integrates three kinds of low-level features: weighted color histogram, maximally stable color regions (MSCR), and recurrent high-structured patches (RHSP). Meanwhile, semantic features are used in [13] together with other lowlevel features. Another approach is to learn appropriate metrics for specific data [25].…”

D2C: Deep cumulatively and comparatively learning for human age estimation

“…Our model with this novel CHL is similar to the very successful attribute based models used in many computer vision problems [41,42,43]. Structurally, these attribute based models are two-stage mapping, i.e., they first map the visual features to the attribute space and then map this attribute space to the label space.…”