Measuring the Temporal Behavior of Real-World Person Re-Identification
This addresses a practical gap for operators of surveillance systems by providing a temporal performance metric, though it is incremental as it builds on existing re-id methods.
The paper tackles the problem of evaluating person re-identification systems in real-world scenarios where galleries update over time, proposing a Rank Persistence Curve (RPC) to measure how long correct matches remain in shortlists, and demonstrates this using a new dataset called RPIfield with 12 cameras and 112 actor paths.
Designing real-world person re-identification (re-id) systems requires attention to operational aspects not typically considered in academic research. Typically, the probe image or image sequence is matched to a gallery set with a fixed candidate list. On the other hand, in real-world applications of re-id, we would search for a person of interest in a gallery set that is continuously populated by new candidates over time. A key question of interest for the operator of such a system is: how long is a correct match to a probe likely to remain in a rank-k shortlist of candidates? In this paper, we propose to distill this information into what we call a Rank Persistence Curve (RPC), which unlike a conventional cumulative match characteristic (CMC) curve helps directly compare the temporal performance of different re-id algorithms. To carefully illustrate the concept, we collected a new multi-shot person re-id dataset called RPIfield. The RPIfield dataset is constructed using a network of 12 cameras with 112 explicitly time-stamped actor paths among about 4000 distractors. We then evaluate the temporal performance of different re-id algorithms using the proposed RPCs using single and pairwise camera videos from RPIfield, and discuss considerations for future research.