Abstract
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.
Highlights
Urbanization displays a massively increasing global trend
Our results indicated that the investigated methods performed fairly in this task, returning a pixel accuracy between 96.18% (DeepLabV3+) and 95.56% (DDCN), an average accuracy between 96.07% (DeepLabV3+) and 95.56% (DDCN), a F1-score between
We evaluated five state-of-the-art Convolutional Neural Networks for the semantic segmentation of urban forests using airborne high spatial-resolution RGB images
Summary
Urbanization displays a massively increasing global trend. According to data of the UN [1], more than half of the world’s population habit urban areas, and by 2050, it is projected to 68% of the world’s population to be urban. One of the essential aspects of a city is the vegetation; they provide the residents of the city with several environmental and social services, in this way supporting the development and improving inhabitants quality of life [2,3,4,5,6]. Urban growth is usually associated with forest remnants suppression leading to ecosystem stress and biodiversity losses [13]. Vegetation suppression is mainly correlated to the urban process of growth and often results in impervious areas and brings other negative impacts for the environment, such as urban biodiversity loss and changes in the hydrodynamics of the cities [14]. Mapping urban forests are essential in order to propose strategies that optimize citizen’s quality of life, city hydrodynamics, and biodiversity by preserving and improving this valuable ecosystem [2,15]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have