Attributes-Based Re-identification
نویسندگان
چکیده
Automated person re-identification using only visual information from public-space CCTV video is challenging for many reasons, such as poor resolution or challenges involved in dealing with camera calibration. More critical still, the majority of clothing worn in public spaces tends to be non-discriminative and therefore of limited disambiguation value. Most re-identification techniques developed so far have relied on low-level visual-feature matching approaches that aim to return matching gallery detections earlier in the ranked list of results. However, for many applications an initial probe image may not be available, or a low-level feature representation may not be sufficiently invariant to viewing condition changes as well as being discriminative for reidentification. In this chapter, we show how midlevel “semantic attributes” can be computed for person description. We further show how this attribute-based description can be used in synergy with low-level feature descriptions to improve re-identification accuracy when an attribute-centric distance measure is employed. Moreover, we discuss a “zero-shot” scenario in which a visual probe is unavailable but re-identification can still be performed with user-provided semantic attribute description. Ryan Layne Queen Mary University of London e-mail: [email protected] Timothy M. Hospedales Queen Mary University of London e-mail: [email protected] Shaogang Gong Queen Mary University of London e-mail: [email protected]
منابع مشابه
On the Exploration of Joint Attribute Learning for Person Re-identification
This paper presents an algorithm for jointly learning a set of mid-level attributes from an image ensemble by locating clusters of dependent attributes. Human describable attributes are an active research topic due to their ability to transfer between domains, human understanding, and improvement to identification performance. Joint learning may allow for enhanced attribute classification when ...
متن کاملRe-Identification and Synthetic Data Generators: A Case Study
Synthetic generators are increasingly used to replace sensitive data with artificial data preserving to a predetermined extent the utility of the original data. When using synthetic data generators, re-identification analysis is usually disregarded on the grounds that, the released data being artificial, no real re-identification is possible. While this may be reasonable if synthetic generation...
متن کاملCompromising Privacy with Trail Re-Identification: The REIDIT Algorithms
Re-identification is the process of relating unique and specific entities to seemingly anonymous data, and as such, is an attack on the privacy of a data collection. This work introduces a new reidentification attack, termed the trail problem, for data distributed over multiple locations. Through the use of data trails an adversary can independently reconstruct the trails of locations that iden...
متن کاملPerson Re-Identification By Saliency Learning
Human eyes can identify person identities based on small salient regions, i.e. person saliency is distinctive and reliable. Saliency relates to matching regions with attributes that make a person distinctive and are useful in finding the same person across camera views. Person re-identification with saliency learning can be applied in human tracking, surveillance , retrieval etc.
متن کاملRe-id: Hunting Attributes in the Wild
Person re-identification is a crucial capability underpinning many applications of public-space video surveillance. Recent studies have shown the value of learning semantic attributes as a discriminative representation for re-identification. However, existing attribute representations do not generalise across camera deployments. Thus, this strategy currently requires the prohibitive effort of a...
متن کامل