Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery

By Masoud MahdianPari, Bahram Salehi, Mohammad Rezaee, Fariba Mohammadimanesh, Yun Zhang. Remote Sensing, 2018

387 citations recorded by the source corpus.

Despite recent advances of deep Convolutional Neural Networks (CNNs) in various computer vision tasks, their potential for classification of multispectral remote sensing images has not been thoroughly explored. In particular, the applications of deep CNNs using optical remote sensing data have focused on the classification of very high-resolution aerial and satellite data, owing to the similarity of these data to the large datasets in computer vision. Accordingly, this study presents a detailed investigation of state-of-the-art deep learning tools for classification of complex wetland classes using multispectral RapidEye optical imagery. Specifically, we examine the capacity of seven well-known deep convnets, namely DenseNet121, InceptionV3, VGG16, VGG19, Xception, ResNet50, and InceptionResNetV2, for wetland mapping in Canada. In addition, the classification results obtained from deep CNNs are compared with those based on conventional machine learning tools, including Random Forest and Support Vector Machine, to further evaluate the efficiency of the former to classify wetlands. The results illustrate that the full-training of convnets using five spectral bands outperforms the other strategies for all convnets. InceptionResNetV2, ResNet50, and Xception are distinguished as the top three convnets, providing state-of-the-art classification accuracies of 96.17%, 94.81%, and 93.57%, respectively. The classification accuracies obtained using Support Vector Machine (SVM) and Random Forest (RF) are 74.89% and 76.08%, respectively, considerably inferior relative to CNNs. Importantly, InceptionResNetV2 is consistently found to be superior compared to all other convnets, suggesting the integration of Inception and ResNet modules is an efficient architecture for classifying complex remote sensing scenes such as wetlands.

Subfields: Ecology, Global and Planetary Change, Media Technology

View Paper: https://www.semanticscholar.org/paper/55ae79ca10937e3921003b4f1172467ae0be9065

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Global and Planetary Change

In Media Technology

Citations in the corpus

Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, background): “classes [22], [45], and the accuracy of the final product [44], [46]–[48].”
Deep learning in environmental remote sensing: Achievements and challenges (2020, background): “Several well-known deep models are examined for complex land cover mapping (Mahdianpari et al., 2018).”
Remote Sensing Image Scene Classification Using CNN-CapsNet (2019, methodology): “As for CNN, two representative CNN models (VGG‐16 and Inception‐V3) fully trained on the ImageNet dataset are used as initial feature map extractors, considering their popularity in the remote sensing field [25,27,28,35,53,56,59].”
Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection (2019, background): “The height of their orbits is 680 km, and the swath width is 77 km with a 5-day revisit time period [47].”
Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network (2019, background): “Remote sensing images can be categorized by their spatial, spectral, and temporal resolutions [1], and has been generally researched for many areas such as land-cover mapping [2], water monitoring [3], and anomaly detection [4].”