Home

Awesome

DMIST-Benchmark

Dense Moving Infrared Small Target Detection

The DMIST benchmark datasets and baseline model implementation of the TGRS 2024 paper Towards Dense Moving Infrared Small Target Detection: New Datasets and Baseline

<img src="/readme/vis.png" width="1000px">

Benchmark Datasets (bounding box-based)

train_annotation_path = '/home/LASNet/DMIST_train.txt'
val_annotation_path = '/home/LASNet/DMIST_60_val.txt'
python utils_coco/coco_to_txt.py
DMIST
├─coco_train.json
├─60_coco_val.json
├─100_coco_val.json
├─images
│   ├─train
│   │   ├─data5
│   │   │   ├─0.bmp
│   │   │   ├─0.txt
│   │   │   ├─ ...
│   │   │   ├─2999.bmp
│   │   │   ├─2999.txt
│   │   │   ├─ ...
│   │   ├─ ...
│   ├─test60
│   │   ├─data6
│   │   │   ├─0.bmp
│   │   │   ├─0.txt
│   │   │   ├─ ...
│   │   │   ├─398.bmp
│   │   │   ├─398.txt
│   │   │   ├─ ...
│   │   ├─ ...
│   ├─test100
│   │   ├─ ...

Prerequisite

Usage of baseline LASNet

Train

<!-- - Note: Please use different `dataloaders` for different datasets. For example, if you want to use IRDST dataset for training, please change the `dataloader` in `train.py` to: `from utils.dataloader_for_IRDST import seqDataset, dataset_collate`. -->
CUDA_VISIBLE_DEVICES=0 python train_DMIST.py

Test

"model_path": '/home/LASNet/logs/model.pth'
#Use DMIST-100 dataset for test.
cocoGt_path         = '/home/public/DMIST/100_coco_val.json'
dataset_img_path    = '/home/public/DMIST/'
python test_DMIST.py

Visulization

# mode = "video" #Predict a sequence
mode = "predict"  #Predict a single-frame image 
python predict.py

Results

<table> <tr> <th>Method</th> <th>Dataset</th> <th>mAP50 (%)</th> <th>Precision (%)</th> <th>Recall (%)</th> <th>F1 (%)</th> <th>Download</th> </tr> <tr> <td align="center">LASNet</td> <td align="center">DMIST-60</td> <td align="center">76.47</td> <td align="center">95.84</td> <td align="center">80.07</td> <td align="center">87.25</td> <td rowspan="3" align="center"> <a href="https://pan.baidu.com/s/1Tq9fyLQF64Ly0xR8VSYW3Q?pwd=y7ki">Baidu</a> (code: y7ki) <br><br> <a href="https://drive.google.com/drive/folders/13CvH9muxs-9fcgeSZJWraw1StWxE3zek?usp=sharing">Google</a> </td> </tr> <tr> <td align="center">LASNet</td> <td align="center">DMIST-100</td> <td align="center">65.70</td> <td align="center">96.52</td> <td align="center">68.68</td> <td align="center">80.25</td> </tr> </table> <img src="/readme/PR1.png" width="500px"> <img src="/readme/PR2.png" width="500px"> <img src="/readme/PR3.png" width="500px">

Contact

If any questions, kindly contact with Shengjia Chen via e-mail: csj_uestc@126.com.

References

  1. S. Chen, L. Ji, J. Zhu, M. Ye and X. Yao, "SSTNet: Sliced Spatio-Temporal Network With Cross-Slice ConvLSTM for Moving Infrared Dim-Small Target Detection," in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-12, 2024, Art no. 5000912, doi: 10.1109/TGRS.2024.3350024.
  2. B. Hui et al., “A dataset for infrared image dim-small aircraft target detection and tracking under ground/air background,” Sci. Data Bank, CSTR 31253.11.sciencedb.902, Oct. 2019.

Citation

If you find this repo useful, please cite our paper.

@ARTICLE{chen2024dmist,
  author={Chen, Shengjia and Ji, Luping and Zhu, Sicheng and Ye, Mao and Ren, Haohao and Sang, Yongsheng},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={Toward Dense Moving Infrared Small Target Detection: New Datasets and Baseline}, 
  year={2024},
  volume={62},
  pages={1-13},
  doi={10.1109/TGRS.2024.3443280}}