Late Fusion in Part-based Person Re-identification

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

In person re-identification, the purpose is to match persons across, typically, non-overlapping cameras. This introduces challenges such as occlusion and changes in view and light- ing. In order to overcome these challenges, discriminative features are extracted and used in combination with a su- pervised metric learning algorithm. Most often, feature rep- resentations are created from the entire body, causing noisy features if certain parts are occluded. Therefore, we propose a system which applies the same learning algorithm sepa- rately on feature representations from different body parts and late fuses the outputs, to take advantage of situations in which features from certain body parts are more discrim- inative than other. By evaluation on features at three ab- straction levels, we show that the proposed system increase accuracy by up to 19.87% in the case of high-level features. In addition, we also fuse the features at different abstraction levels to further improve results. Experimental results on VIPeR and CUHK03 show similar performance to state-of- the-art with rank-1 accuracies of 52.72% and 61.50%, respec- tively, while results on the datasets PRID450S and CUHK01 show rank-1 accuracies of 78.36% and 73.40%, respectively, improvements of 11.74% and 7.76% compared to state-of- the-art.
Luk

Detaljer

In person re-identification, the purpose is to match persons across, typically, non-overlapping cameras. This introduces challenges such as occlusion and changes in view and light- ing. In order to overcome these challenges, discriminative features are extracted and used in combination with a su- pervised metric learning algorithm. Most often, feature rep- resentations are created from the entire body, causing noisy features if certain parts are occluded. Therefore, we propose a system which applies the same learning algorithm sepa- rately on feature representations from different body parts and late fuses the outputs, to take advantage of situations in which features from certain body parts are more discrim- inative than other. By evaluation on features at three ab- straction levels, we show that the proposed system increase accuracy by up to 19.87% in the case of high-level features. In addition, we also fuse the features at different abstraction levels to further improve results. Experimental results on VIPeR and CUHK03 show similar performance to state-of- the-art with rank-1 accuracies of 52.72% and 61.50%, respec- tively, while results on the datasets PRID450S and CUHK01 show rank-1 accuracies of 78.36% and 73.40%, respectively, improvements of 11.74% and 7.76% compared to state-of- the-art.
OriginalsprogEngelsk
TitelProceedings of the 9th International Conference on Machine Learning and Computing
ForlagAssociation for Computing Machinery
Publikationsdatojun. 2017
ISBN (Trykt)978-1-4503-4817-1
DOI
StatusUdgivet - jun. 2017
PublikationsartForskning
Peer reviewJa
BegivenhedInternational Conference on Machine Learning and Computing - Singapore, Singapore
Varighed: 24 feb. 2017 → …
Konferencens nummer: 9

Konference

KonferenceInternational Conference on Machine Learning and Computing
Nummer9
LandSingapore
BySingapore
Periode24/02/2017 → …
SerieACM International Conference Proceedings series
ID: 249883302