Semantic Segmentation of Tree-Canopy in Urban Environment with Pixel-Wise Deep Learning

Remote Sensing

Keiller Nogueira¹  Jefersson Alex dos Santos²  Ana Paula Marques Ramos³  Felipe David Georges Gomes³  Danielle Elis Garcia Furuya³  Diego André Sant’Ana⁴  Lucas Prado Osco⁵  José Marcato Junior⁶  José Augusto Correa Martins⁶  Wesley Nunes Gonçalves⁶  Paulo Tarso Sanches de Oliveira⁶  Veraldo Liesenberg⁷ 

[1] Computing Science and Mathematics Division, University of Stirling, Stirling FK9 4LA, UK;Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte 31270-901, Brazil;Environment and Regional Development Program, University of Western São Paulo, Rodovia Raposo Tavares, km 572, Bairro Limoeiro 19067-175, Brazil;Environmental Science and Sustainability, INOVISÃO Universidade Católica Dom Bosco, Av. Tamandaré, 6000, Campo Grande 79117-900, Brazil;Faculty of Engineering and Architecture and Urbanism, University of Western São Paulo, Rodovia Raposo Tavares, km 572, Bairro Limoeiro 19067-175, Brazil;Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, Brazil;Forest Engineering Department, Santa Catarina State University, Avenida Luiz de Camões 2090, Lages 88520-000, Brazil;

关键词: remote sensing;    image segmentation;    sustainability;    convolutional neural network;    urban environment;   

DOI  :  10.3390/rs13163054

来源: DOAJ

【 摘 要 】

Urban forests are an important part of any city, given that they provide several environmental benefits, such as improving urban drainage, climate regulation, public health, biodiversity, and others. However, tree detection in cities is challenging, given the irregular shape, size, occlusion, and complexity of urban areas. With the advance of environmental technologies, deep learning segmentation mapping methods can map urban forests accurately. We applied a region-based CNN object instance segmentation algorithm for the semantic segmentation of tree canopies in urban environments based on aerial RGB imagery. To the best of our knowledge, no study investigated the performance of deep learning-based methods for segmentation tasks inside the Cerrado biome, specifically for urban tree segmentation. Five state-of-the-art architectures were evaluated, namely: Fully Convolutional Network; U-Net; SegNet; Dynamic Dilated Convolution Network and DeepLabV3+. The experimental analysis showed the effectiveness of these methods reporting results such as pixel accuracy of 96,35%, an average accuracy of 91.25%, F1-score of 91.40%, Kappa of 82.80% and IoU of 73.89%. We also determined the inference time needed per area, and the deep learning methods investigated after the training proved to be suitable to solve this task, providing fast and effective solutions with inference time varying from 0.042 to 0.153 minutes per hectare. We conclude that the semantic segmentation of trees inside urban environments is highly achievable with deep neural networks. This information could be of high importance to decision-making and may contribute to the management of urban systems. It should be also important to mention that the dataset used in this work is available on our website.

【 授权许可】

Unknown