All Projects → Yuki-11 → CSSR

Yuki-11 / CSSR

Licence: MIT license
Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution (CSSR) was accepted to international conference on MVA2021 (oral), and selected for the Best Practical Paper Award.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to CSSR

DeepCrack
DeepCrack: A Deep Hierarchical Feature Learning Architecture for Crack Segmentation, Neurocomputing.
Stars: ✭ 130 (+160%)
Mutual labels:  crack-detection, crack-segmentation
Crack-segmentation
This repo contains customized deep learning models for segmenting cracks.
Stars: ✭ 35 (-30%)
Mutual labels:  crack-detection, crack-segmentation
MCIS wsss
Code for ECCV 2020 paper (oral): Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Stars: ✭ 151 (+202%)
Mutual labels:  semantic-segmentation
pysemseg
Semantic Segmentation Models in Pytorch
Stars: ✭ 31 (-38%)
Mutual labels:  semantic-segmentation
Jalali-Lab-Implementation-of-RAISR
Implementation of RAISR (Rapid and Accurate Image Super Resolution) algorithm in Python 3.x by Jalali Laboratory at UCLA. The implementation presented here achieved performance results that are comparable to that presented in Google's research paper (with less than ± 0.1 dB in PSNR). Just-in-time (JIT) compilation employing JIT numba is used to …
Stars: ✭ 118 (+136%)
Mutual labels:  super-resolution
etos-deepcut
Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr . a tool to do automatically object segmentation from extreme points.
Stars: ✭ 24 (-52%)
Mutual labels:  semantic-segmentation
DeepCrack
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection
Stars: ✭ 137 (+174%)
Mutual labels:  crack-detection
nobrainer
A framework for developing neural network models for 3D image processing.
Stars: ✭ 123 (+146%)
Mutual labels:  semantic-segmentation
Fashion-Clothing-Parsing
FCN, U-Net models implementation in TensorFlow for fashion clothing parsing
Stars: ✭ 29 (-42%)
Mutual labels:  semantic-segmentation
tf-semantic-segmentation-FCN-VGG16
Semantic segmentation for classifying road. "Fully Convolutional Networks for Semantic Segmentation (2015)" implemented using TF
Stars: ✭ 30 (-40%)
Mutual labels:  semantic-segmentation
Xtreme-Vision
A High Level Python Library to empower students, developers to build applications and systems enabled with computer vision capabilities.
Stars: ✭ 77 (+54%)
Mutual labels:  semantic-segmentation
Magpie
将任何窗口放大至全屏
Stars: ✭ 4,478 (+8856%)
Mutual labels:  super-resolution
K-Net
[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation
Stars: ✭ 434 (+768%)
Mutual labels:  semantic-segmentation
ScasNet
Semantic Labeling in VHR Images via A Self-Cascaded CNN (ISPRS JPRS, IF=6.942)
Stars: ✭ 24 (-52%)
Mutual labels:  semantic-segmentation
multiclass-semantic-segmentation
Experiments with UNET/FPN models and cityscapes/kitti datasets [Pytorch]
Stars: ✭ 96 (+92%)
Mutual labels:  semantic-segmentation
SEC-tensorflow
a tensorflow version for SEC approach in the paper "seed, expand and constrain: three principles for weakly-supervised image segmentation".
Stars: ✭ 35 (-30%)
Mutual labels:  semantic-segmentation
Semantic Segmentation
Semantic Segmentation using Fully Convolutional Neural Network.
Stars: ✭ 60 (+20%)
Mutual labels:  semantic-segmentation
RGBD-semantic-segmentation
A paper list of RGBD semantic segmentation (processing)
Stars: ✭ 264 (+428%)
Mutual labels:  semantic-segmentation
ssgan
Semi Supervised Semantic Segmentation Using Generative Adversarial Network ; Pytorch
Stars: ✭ 25 (-50%)
Mutual labels:  semantic-segmentation
ESPCN-PyTorch
A PyTorch implementation of ESPCN based on CVPR 2016 paper Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network.
Stars: ✭ 33 (-34%)
Mutual labels:  super-resolution

Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution (CSSR)

Paper | Data


Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution
Yuki Kondo*1, Norimichi Ukita*1
*1Toyota Technological Institute (TTI-J)
in MVA 2021 (Oral Presentation, Best Practical Paper Award)

Our Framework

News

What's this?

We have proposed a method for high-resolution crack segmentation for low-resolution images. This approach enables automatic detection of cracks even when the image resolution of the crack area is reduced due to an environment in which the area where cracks may occur must be photographed from a distance (e.g., An environment in which a drone that targets a high-altitude chimney wall must take a distance in order to fly safely.). The proposed method is composed of the following two approaches.

  1. Deep learning based super resolution to increase the resolution of low-resolution images. This super-resolution image enables delicate crack segmentation. In addition, we proposed CSSR (Crack Segmentation with Super Resolution) using end-to-end joint learning to optimize the super-resolution for the crack segmentation process.

  2. In order to optimize the deep learning model for segmentation, we proposed a loss function Boundary Combo loss that simultaneously optimizes the global and local structures of cracks. This loss function enables both detection of thin and difficult-to-detect cracks and detection of fine crack boundaries.

The experimental results show that the proposed method is superior to the conventional method, and quantitatively*1 and qualitatively, the segmentation is as precise as when using high-resolution images.

*1; In terms of IoU, the proposed method achieves 97.3% of the IoU of the high-resolution image input.

Dependencies

  • Python >= 3.6
  • PyTorch >= 1.8
  • numpy >= 1.19

Usage

  1. Clone the repository:

    git clone https://github.com/Yuki-11/CSSR.git
  2. Download khanhha dataset:

    cd $CSSR_ROOT
    mkdir datasets
    cd datasets
    curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1xrOqv0-3uMHjZyEUrerOYiYXW_E8SUMP" > /dev/null
    CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"  
    curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1xrOqv0-3uMHjZyEUrerOYiYXW_E8SUMP" -o temp_dataset.zip
    unzip temp_dataset.zip
    rm temp_dataset.zip
  3. Download trained models:

    cd $CSSR_ROOT
    mkdir output

    You can download trained models here. Then, place the unzipped directory of the models you want to use under <$CSSR_ROOT/output/>.

  4. Install packages:

    cd $CSSR_ROOT
    pip install -r requirement.txt
  5. Training:

    cd $CSSR_ROOT
    python train.py --config_file <CONFIG FILE>

    If you want to resume learning, you can do it with the following command.

    cd $CSSR_ROOT
    python train.py --config_file output/<OUTPUT DIRECTORY (OUTPUT_DIR at config.yaml)>/config.yaml --resume_iter <Saved iteration number>
  6. Test:

    cd $CSSR_ROOT
    python test.py output/<OUTPUT DIRECTORY (OUTPUT_DIR at config.yaml)> <iteration number> 

Citations

If you find this work useful, please consider citing it.

@inproceedings{CSSR2021,
  title={Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution},
  author={Kondo, Yuki and Ukita, Norimichi},
  booktitle={International Conference on Machine Vision Applications (MVA)},
  year={2021}
}

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].