WDA-Net

PyTorch implementation of "Weak Appearance Aware Pipeline Leak Detection based on CNN-Transformer Hybrid Architecture".

Highlights:

1.We propose a visual pipeline leak detection system with a novel segmentation network, namely WDA-Net, that can work with subtle pipeline leaks in real-time and various illumination conditions.

2. We design a novel encoder achieved with the CNN-Transformer hybrid architecture to capture more semantic features of the defects, and a lightweight decoder to fuse the feature maps and gradually recover spatial details. Our method has the most significant improvement effect on extracting features with weak appearance performance.

2. Our WDA-Net achieves state-of-the-art performance on the PLD dataset.

3. we proposed a new dataset named PLD for pipeline leakage semantic segmentation .

Benchmark and model zoo

Model	Dataset	img_size	mIoU	Download
WDA-Net	PLD	512x512	70.04	model
WDA-Net	NEU-Seg	192x192	84.55	model

The PLD test set is available at [DataSet].

Installation

The code was tested on SUSE Linux, with Anaconda Python 3.8 and PyTorch v1.10.0. NVIDIA GPUs are needed for both training and testing. After installing Anaconda:

a. Create a conda virtual environment and activate it.

conda create -n WDA-Net python=3.8 -y
conda activate WDA-Net

b. Install PyTorch and torchvision following the official instructions. Here we use PyTorch 1.10.0 and CUDA 11.1. You may also switch to other version by specifying the version number.

conda install pytorch=1.10.0 torchvision -c pytorch

c. Install MMCV-full 1.5.0 following the official instructions.

pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{torch_version}/index.html

d. Install MMSegmentation.

pip install mmsegmentation 

or

pip install git+https://github.com/open-mmlab/mmsegmentation.git 

Train a model

Train with a single GPU

sh tools/dist_train.sh ${CONFIG_FILE} 1 [optional arguments]

Train with multiple GPUs

sh tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM} [optional arguments]

eval a model

sh tools/dist_test.sh ${CONFIG_FILE} 1 [optional arguments]