End-to-End Image Compression with Segmentation Guided Dual Coding for Wind Turbines

TL;DR

This paper introduces a novel end-to-end deep learning framework for wind turbine image compression that combines segmentation, lossy, and lossless coding to improve defect detection efficiency.

Contribution

It presents the first integrated learning-based ROI codec that jointly performs segmentation and dual-mode compression, enhancing wind turbine inspection workflows.

Findings

Superior compression performance on wind turbine images.

Efficient parallelized dual-mode compression framework.

Accurate blade segmentation with a CRF-regularized network.

Abstract

Transferring large volumes of high-resolution images during wind turbine inspections introduces a bottleneck in assessing and detecting severe defects. Efficient coding must preserve high fidelity in blade regions while aggressively compressing the background. In this work, we propose an end-to-end deep learning framework that jointly performs segmentation and dual-mode (lossy and lossless) compression. The segmentation module accurately identifies the blade region, after which our region-of-interest (ROI) compressor encodes it at superior quality compared to the rest of the image. Unlike conventional ROI schemes that merely allocate more bits to salient areas, our framework integrates: (i) a robust segmentation network (BU-Netv2+P) with a CRF-regularized loss for precise blade localization, (ii) a hyperprior-based autoencoder optimized for lossy compression, and (iii) an extended bits-back coder with hierarchical models for fully lossless blade reconstruction. Furthermore, our ROI framework removes the sequential dependency in bits-back coding by reusing background-coded bits, enabling parallelized and efficient dual-mode compression. To the best of our knowledge, this is the first fully integrated learning-based ROI codec combining segmentation, lossy, and lossless compression, ensuring that subsequent defect detection is not compromised. Experiments on a large-scale wind turbine dataset demonstrate superior compression performance and efficiency, offering a practical solution for automated inspections.