Pseudo Supervised Solar Panel Mapping based on Deep Convolutional Networks with Label Correction Strategy in Aerial Images

TL;DR

This paper introduces a pseudo supervised deep learning approach with label correction for more accurate solar panel mapping in aerial images, effectively combining weak and strong supervision to reduce annotation costs.

Contribution

It proposes a novel pseudo supervised CNN with a label correction strategy that iteratively refines pseudo labels for improved solar panel detection accuracy.

Findings

Outperforms existing weakly supervised methods in accuracy

Effective in reducing manual annotation effort

Demonstrates robustness through comprehensive evaluations

Abstract

Solar panel mapping has gained a rising interest in renewable energy field with the aid of remote sensing imagery. Significant previous work is based on fully supervised learning with classical classifiers or convolutional neural networks (CNNs), which often require manual annotations of pixel-wise ground-truth to provide accurate supervision. Weakly supervised methods can accept image-wise annotations which can help reduce the cost for pixel-level labelling. Inevitable performance gap, however, exists between weakly and fully supervised methods in mapping accuracy. To address this problem, we propose a pseudo supervised deep convolutional network with label correction strategy (PS-CNNLC) for solar panels mapping. It combines the benefits of both weak and strong supervision to provide accurate solar panel extraction. First, a convolutional neural network is trained with positive and negative samples with image-level labels. It is then used to automatically identify more positive samples from randomly selected unlabeled images. The feature maps of the positive samples are further processed by gradient-weighted class activation mapping to generate initial mapping results, which are taken as initial pseudo labels as they are generally coarse and incomplete. A progressive label correction strategy is designed to refine the initial pseudo labels and train an end-to-end target mapping network iteratively, thereby improving the model reliability. Comprehensive evaluations and ablation study conducted validate the superiority of the proposed PS-CNNLC.