Learning to rank in person re-identification with metric ensembles

We propose an effective structured learning based ap- proach to the problem of person re-identification which out- performs the current state-of-the-art on most benchmark data sets evaluated. Our framework is built on the ba- sis of multiple low-level hand-crafted and high-level vi- sual features. We then formulate two optimization algo- rithms, which directly optimize evaluation measures com- monly used in person re-identification, also known as the Cumulative Matching Characteristic (CMC) curve. Our new approach is practical to many real-world surveillance applications as the re-identification performance can be concentrated in the range of most practical importance. The combination of these factors leads to a person re- identification system which outperforms most existing al- gorithms. More importantly, we advance state-of-the-art results on person re-identification by improving the rank- 1 recognition rates from 40% to 50% on the iLIDS bench- mark, 16% to 18% on the PRID2011 benchmark, 43% to 46% on the VIPeR benchmark, 34% to 53% on the CUHK01 benchmark and 21% to 62% on the CUHK03 benchmark.Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Henge