TASK1-Crowd Counting

Deep learning based computer vision algorithms have surpassed the human-level performance for many CV tasks, like object recognition and face verification. However, computer vision technology relies on the valid information from the input image and video, and the performance of the algorithm is essentially constrained by the quality of source image/video. Along with the emergence of gigapixel-level image/video, the corresponding computer vision tasks remain unsolved, due to the extremely high-resolution, large-scale, huge-data that induced by the gigapixel camera.

This task is intended to evaluate the ability of algorithms to estimate the crowd density map in a complex scenario. For this task, participants will use our Gigapixel Video Dataset, a new resource with high spatial resolution and wide FOV simultaneously for computer vision challenges.

Dataset Download:

The Gigapixel Video Dataset 0.1alpha will be used for this task. This dataset consists of 65 representative images from the train station and the shanghai marathon sequences. These images are saved in JPEG format with more than 200K heads. Currently, we only release some representative images, and we will release the whole unlabeled video sequence in the future.

Baseline

We provide the results for a baseline proposal method on the test subset.……baseline details……

Citation

When using our datasets in your research, we will be happy if you cite us!
For all of the datasets, please cite:

@inproceedings{yuan2017multiscale,
title={Multiscale gigapixel video: A cross resolution image matching and warping approach},
author={Yuan, Xiaoyun and Fang, Lu and Dai, Qionghai and Brady, David J and Liu, Yebin},
booktitle={Computational Photography (ICCP), 2017 IEEE International Conference on},
pages={1--9},
year={2017},
organization={IEEE}
}