Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art

David Hall, Pietro Perona; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 5482-5491

Abstract


A video dataset that is designed to study fine-grained categorisation of pedestrians is introduced. Pedestrians were recorded ``in-the-wild'' from a moving vehicle. Annotations include bounding boxes, tracks, 14 keypoints with occlusion information and the fine-grained categories of age (5 classes), sex (2 classes), weight (3 classes) and clothing style (4 classes). There are a total of 27,454 bounding box and pose labels across 4222 tracks. This dataset is designed to train and test algorithms for fine-grained categorisation of people; it is also useful for benchmarking tracking, detection and pose estimation of pedestrians. State-of-the-art algorithms for fine-grained classification and pose estimation were tested using the dataset and the results are reported as a useful performance baseline.

Related Material


[pdf]
[bibtex]
@InProceedings{Hall_2015_CVPR,
author = {Hall, David and Perona, Pietro},
title = {Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}