English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

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