DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 152-159
- https://doi.org/10.1109/cvpr.2014.27
Abstract
Person re-identification is to match pedestrian images from disjoint camera views detected by pedestrian detectors. Challenges are presented in the form of complex variations of lightings, poses, viewpoints, blurring effects, image resolutions, camera settings, occlusions and background clutter across camera views. In addition, misalignment introduced by the pedestrian detector will affect most existing person re-identification methods that use manually cropped pedestrian images and assume perfect detection. In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter. All the key components are jointly optimized to maximize the strength of each component when cooperating with others. In contrast to existing works that use handcrafted features, our method automatically learns features optimal for the re-identification task from data. The learned filter pairs encode photometric transforms. Its deep architecture makes it possible to model a mixture of complex photometric and geometric transforms. We build the largest benchmark re-id dataset with 13, 164 images of 1, 360 pedestrians. Unlike existing datasets, which only provide manually cropped pedestrian images, our dataset provides automatically detected bounding boxes for evaluation close to practical applications. Our neural network significantly outperforms state-of-the-art methods on this dataset.Keywords
This publication has 36 references indexed in Scilit:
- Deep Learning Face Representation from Predicting 10,000 ClassesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Deep Convolutional Network Cascade for Facial Point DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Pedestrian Detection with Unsupervised Multi-stage Feature LearningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Intelligent multi-camera video surveillance: A reviewPattern Recognition Letters, 2013
- Person Re-Identification by Support Vector RankingPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Learning Discriminative Appearance-Based Models Using Partial Least SquaresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Multi-camera Matching using Bi-Directional Cumulative Brightness Transfer FunctionsPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Shape and Appearance Context ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Inter-camera color calibration by correlation model functionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004