資料集簡介

　　DukeMTMC 資料集是一個大規模標記的多目標多攝像機行人跟蹤資料集。它提供了一個由 8 個同步攝像機記錄的新型大型高清視訊資料集，具有 7,000 多個單攝像機軌跡和超過 2,700 多個獨立人物，DukeMTMC-reID 是 DukeMTMC 資料集的行人重識別子集，並且提供了人工標註的bounding box。

目錄結構

DukeMTMC-reID
　　├── bounding_box_test
　　　　　　　├── 0002_c1_f0044158.jpg
　　　　　　　├── 3761_c6_f0183709.jpg
　　　　　　　├── 7139_c2_f0160815.jpg
　　├── bounding_box_train
　　　　　　　├── 0001_c2_f0046182.jpg
　　　　　　　├── 0008_c3_f0026318.jpg
　　　　　　　├── 7140_c4_f0175988.jpg
　　├── query
　　　　　　　├── 0005_c2_f0046985.jpg
　　　　　　　├── 0023_c4_f0031504.jpg
　　　　　　　├── 7139_c2_f0160575.jpg
　　└── CITATION_DukeMTMC.txt
　　└── CITATION_DukeMTMC-reID.txt
　　└── LICENSE_DukeMTMC.txt
　　└── LICENSE_DukeMTMC-reID.txt
　　└── README.md

目錄介紹

從視訊中每 120 幀取樣一張影象，得到了 36,411 張影象。一共有 1,404 個人出現在大於兩個攝像頭下，有 408 個人 (distractor ID) 只出現在一個攝像頭下。
1） “bounding_box_test”——用於測試集的 702 人，包含 17,661 張影象（隨機取樣，702 ID + 408 distractor ID）
2） “bounding_box_train”——用於訓練集的 702 人，包含 16,522 張影象（隨機取樣）
3） “query”——為測試集中的 702 人在每個攝像頭中隨機選擇一張影象作為 query，共有 2,228 張影象

命名規則

以 0001_c2_f0046182.jpg 為例
1） 0001 表示每個人的標籤編號；
2） c2 表示來自第二個攝像頭(camera2)，共有 8 個攝像頭；
3） f0046182 表示來自第二個攝像頭的第 46182 幀。

Dataset Insights

資料分佈

Figure. The image distribution of DukeMTMC-reID training set. We note that the median of images per ID is 20. But some ID may contain lots of images, which may compromise some algorithms. (For example, ID 5388 contains 426 images.)

Thank Xun for suggestions.

地理位置

測試協議

(Matlab)To evaluate, you need to calculate your gallery and query feature (i.e., 17661x2048 and 2228x2048 matrix) and save them in advance. Then download the codes in this repository. You just need to change the image path and the feature path in the evaluation_res_duke_fast.m and run it to evaluate.

(Python)We also provide an evaluation code in python. You may refer to here.

下載地址

Baseline

We release our baseline training code and pretrained model in [Matconvnet Version] and [Pytorch Version]. You can choose one of the two tools to conduct the experiment. Furthermore, you may try our new Pedestrain Alignment Code which combines person alignment with re-ID.

Or you can directly download the finetuned ResNet-50 baseline feature. You can download it from GoogleDriver or BaiduYun, which includes the feature of training set, query set and gallery set. The DukeMTMC-reID LICENSE is also included.

State-of-the-art

Citation

If you use this dataset, please kindly cite the following two papers:

@inproceedings{zheng2017unlabeled,
  title={Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro},
  author={Zheng, Zhedong and Zheng, Liang and Yang, Yi},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  year={2017}
}
@inproceedings{ristani2016MTMC,
  title = {Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking},
  author = {Ristani, Ergys and Solera, Francesco and Zou, Roger and Cucchiara, Rita and Tomasi, Carlo},
  booktitle = {European Conference on Computer Vision workshop on Benchmarking Multi-Target Tracking},
  year = {2016}
}

參考文獻

• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro. Zheng et al., ICCV 2017
• Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. Ristani et al., ECCVWS 2016