UAV-Crack

UAV-based pavement crack segmentation
  • Acquiring pavement distress images with UAVs faces unique challenges compared to ground-based methods due to differences in camera setups, flight parameters, and lighting conditions. These factors cause domain shifts that reduce the generalizability of segmentation models.
    • 图片1
  • A dedicated dataset, UAV-CrackX, was created with 1500 pixel-wise annotated UAV images to support model development.The dataset includes three subsets—UAV-CrackX4, X8, and X16—with 500 images each at 4×, 8×, and 16× zoom levels.
    • 图片2
  • Original high-resolution images (2688 × 1512) were split into 16 patches (672 × 378 pixels) for efficient processing. Reference baseline model: https://github.com/open-mmlab/mmsegmentation/tree/main
Active
Click to enter and fill out the application form Get Dataset
Click to manage your methods or submit results Submit Task

Submission Guidelines

UAV-Crack Benchmark Evaluation - Data Format & Submission Guidelines

UAV-Crack Benchmark Evaluation

1. Evaluation Data Format

After unzipping the dataset you received, you will find the following folder structure:

  • gtFine folder: Contains binary mask images output by your model.
    Pixel value 0 represents normal road surface, 1 represents cracks.
  • train subfolder (inside gtFine): Includes binary images at 3 scales: X4, X8, X16, all with resolution 672×378.
  • leftimg8bit folder: Contains input images (original road images).
  • train subfolder (inside leftimg8bit): Input images at 3 scales: X4, X8, X16, resolution 672×378.
  • val subfolder (inside leftimg8bit): Contains 300 validation images for testing, also 672×378.
  • showgt.py: A visualization script to display binary masks more intuitively (not used in evaluation).

Example of Model Input Image (.jpg):

Input Image Example

Example of Model Output Binary Mask (.png):

Output Binary Mask Example

Example of Visualized Binary Mask using showgt.py:

Visualized Mask Example

Benchmark Metrics Introduction:

  • "mIoU": Mean Intersection over Union
  • "Crack F1": Harmonic mean of Precision and Recall
  • "Crack IoU": Intersection over Union for crack class
  • "Crack Precision": Precision for crack detection
  • "Crack Recall": Recall for crack detection
  • "aAcc": Overall Accuracy (Average Accuracy)

2. Evaluation Result Submission Format

We have selected 300 images from the leftimg8bit/val/ folder for evaluation. You are required to submit your model’s predicted binary crack masks for these images only.

Submission Requirements:

  • 1. The resolution of your predicted binary images must be the same as the input, which is 672×378.
  • 2. The file names of your predicted images must exactly match the input image names (but with .png extension).
  • 3. Note: Input images are in .jpg format, but your output predictions must be in .png format.

How to Submit:

  • Please compress all 300 predicted binary mask images (.png) into a single zip file.
  • The zip file should be named: result.zip

The submitted prediction results should be organized as follows:

result/
├── 937956_DJI_20231015154707_0002_Z.JPG_12_z.png
├── 937956_DJI_20231015154713_0005_Z.JPG_5_z.png
├── 937956_DJI_20231015154717_0007_Z.JPG_7_z.png
└── ...

Important: Do not include any extra files or images in the submission zip. Only include the 300 required predicted mask images. Store 300 mask images in a folder named 'result'. This ensures correct evaluation.

Method Leaderboard

22 Methods 6 Metrics
This leaderboard shows methods that are online and have submitted results. Methods are ranked based on their performance metrics. 
@article{焦雨可,蒋嘉杰，万家乐，momi  
  title = {uper-fcn-res},  
  author = {焦雨可,蒋嘉杰，万家乐，momi},  
  year = {2025}  
}
Method mIoU Higher is better Crack F1 Higher is better Crack IoU Higher is better Crack Precision Higher is better Crack Recall Higher is better aAcc Higher is better
Aero裂鉴队
Last submission: 2025-11-24
80.1000 77.2600 62.9500 78.8100 75.7700 97.3800
照隙镜2.0
Last submission: 2025-11-22
80.0300 77.1200 62.7600 80.2000 74.2700 97.4100
CrackNet-Pro
Last submission: 2025-11-24
79.6500 76.5800 62.0500 80.4200 73.0900 97.3700
Hello,Crack! Open Source
Last submission: 2025-11-24
79.6400 76.7900 62.3200 72.5700 81.5300 97.1000
UAVCRACK-trying1
Last submission: 2025-11-24
79.4100 76.2000 61.5500 81.7200 71.3700 97.3800
RBB
Last submission: 2025-11-22
79.4000 76.2700 61.6400 78.7200 73.9600 97.2900
C1 enhanced
Last submission: 2025-11-23
79.2200 75.9300 61.2000 81.2300 71.2800 97.3400
照隙镜
Last submission: 2025-11-18
79.1800 75.8700 61.1300 81.5500 70.9400 97.3500
UAV-CrackSeg Open Source
Last submission: 2025-11-16
78.7600 75.4400 60.5700 75.0200 75.8700 97.1000
UAV-A-MODEL
Last submission: 2025-11-12
78.4200 74.8800 59.8400 76.9200 72.9500 97.1200
UAV-B-MODEL
Last submission: 2025-11-16
78.3000 74.6800 59.5900 78.1200 71.5300 97.1500
UAV11111
Last submission: 2025-11-18
77.7300 73.8400 58.5300 77.5600 70.4600 97.0700
dfanet
Last submission: 2025-11-18
75.4300 70.2200 54.1100 79.6800 62.7700 96.8700
kun
Last submission: 2025-11-18
74.4300 69.5100 53.2700 60.6200 81.4600 95.8000
破晓-UAV_deep
Last submission: 2025-11-24
74.1100 68.9400 52.6000 61.1100 79.0700 95.8100
熊熊上分队
Last submission: 2025-11-24
72.6400 65.6100 48.8200 79.8800 55.6700 96.5700
Uav-deep
Last submission: 2025-11-24
72.0700 66.6700 50.0000 51.5500 94.3400 94.4600
UAV-Crack1
Last submission: 2025-11-25
59.4200 42.7200 27.1700 36.6400 51.2300 91.9300
pcd
Last submission: 2025-11-23
49.9300 3.3400 1.7000 4.4000 2.6900 98.1700
UC
Last submission: 2025-11-17
48.4600 0.0000 0.0000 0.0000 0.0000 96.9300
U
Last submission: 2025-11-24
48.1300 0.0000 0.0000 0.0000 0.0000 96.2700
Unet_crack
Last submission: 2025-11-25
0.0000 0.0000 0.0000 0.0000 0.0000 0.0000