Joint Detection and Identification Feature Learning for Person Search
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3376-3385
- https://doi.org/10.1109/cvpr.2017.360
Abstract
Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates. However, it is different from real-world scenarios where the annotations of pedestrian bounding boxes are unavailable and the target person needs to be searched from a gallery of whole scene images. To close the gap, we propose a new deep learning framework for person search. Instead of breaking it down into two separate tasks-pedestrian detection and person re-identification, we jointly handle both aspects in a single convolutional neural network. An Online Instance Matching (OIM) loss function is proposed to train the network effectively, which is scalable to datasets with numerous identities. To validate our approach, we collect and annotate a large-scale benchmark dataset for person search. It contains 18,184 images, 8,432 identities, and 96,143 pedestrian bounding boxes. Experiments show that our framework outperforms other separate approaches, and the proposed OIM loss function converges much faster and better than the conventional Softmax loss.Keywords
Other Versions
This publication has 35 references indexed in Scilit:
- Person Search in a Scene by Jointly Modeling People Commonness and Person UniquenessPublished by Association for Computing Machinery (ACM) ,2014
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Fast Feature Pyramids for Object DetectionIeee Transactions On Pattern Analysis and Machine Intelligence, 2014
- Unsupervised Salience Learning for Person Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Intelligent multi-camera video surveillance: A reviewPattern Recognition Letters, 2013
- Person Re-identification by Descriptive and Discriminative ClassificationLecture Notes in Computer Science, 2011
- Associating Groups of PeoplePublished by British Machine Vision Association and Society for Pattern Recognition ,2009
- Keeping Track of Humans: Have I Seen This Person Before?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Person Reidentification Using Spatiotemporal AppearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Inter-camera color calibration by correlation model functionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004