Robust Building Footprint Extraction From Big Multi-Sensor Data Using Deep Competition Network

Computational Intelligence and Neuroscience

Shah-Hosseini

2020

In this study, an essential application of remote sensing using deep learning functionality is presented. Gaofen-1 satellite mission, developed by the China National Space Administration (CNSA) for the civilian high-definition Earth observation satellite program, provides near-real-time observations for geographical mapping, environment surveying, and climate change monitoring. Cloud and cloud shadow segmentation are a crucial element to enable automatic near-real-time processing of Gaofen-1 images, and therefore, their performances must be accurately validated. In this paper, a robust multiscale segmentation method based on deep learning is proposed to improve the efficiency and effectiveness of cloud and cloud shadow segmentation from Gaofen-1 images. The proposed method first implements feature map based on the spectral-spatial features from residual convolutional layers and the cloud/cloud shadow footprints extraction based on a novel loss function to generate the final footprints. The experimental results using Gaofen-1 images demonstrate the more reasonable accuracy and efficient computational cost achievement of the proposed method compared to the cloud and cloud shadow segmentation performance of two existing state-of-the-art methods.

“…In addition, the he_norm method is used for initializing the network. The he_norm method is one of the most appropriate weighting methods in deep learning [ 46 , 47 ].…”

Section: Proposed Methodsmentioning

confidence: 99%

A Deep Learning Method for Near-Real-Time Cloud and Cloud Shadow Segmentation from Gaofen-1 Images

Computational Intelligence and Neuroscience

Shah-Hosseini

2020

“…A major yet unsolved research topic for accurate 2D/3D city model generation is multi-task learning for scene understanding from high-resolution low-cost photogrammetry and remote sensing data sources (Khoshboresh Masouleh and Saradjian, 2019). In remote sensing and photogrammetry, previous benchmarks include four semantic segmentation datasets designed using satellite, airborne, and UAV platforms for urban scene analysis.…”

Section: Motivationmentioning

confidence: 99%

Multi-Task Learning From Fixed-Wing Uav Images for 2d/3d City Modelling

Bayanlou

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

2021

Abstract. Single-task learning in artificial neural networks will be able to learn the model very well, and the benefits brought by transferring knowledge thus become limited. In this regard, when the number of tasks increases (e.g., semantic segmentation, panoptic segmentation, monocular depth estimation, and 3D point cloud), duplicate information may exist across tasks, and the improvement becomes less significant. Multi-task learning has emerged as a solution to knowledge-transfer issues and is an approach to scene understanding which involves multiple related tasks each with potentially limited training data. Multi-task learning improves generalization by leveraging the domain-specific information contained in the training data of related tasks. In urban management applications such as infrastructure development, traffic monitoring, smart 3D cities, and change detection, automated multi-task data analysis for scene understanding based on the semantic, instance, and panoptic annotation, as well as monocular depth estimation, is required to generate precise urban models. In this study, a common framework for the performance assessment of multi-task learning methods from fixed-wing UAV images for 2D/3D city modelling is presented.

“…Owing to the advances of deep learning (LeCun et al, 2015) and the new datasets released in computer vision, remote sensing, and photogrammetry (Khoshboresh Masouleh and Saradjian, 2019), new insights have been presented in the field of building change detection for bi-temporal data (Chen and Shi, 2020;Hou et al, 2020;Khoshboresh Masouleh and Shah-Hosseini, 2019). Although some efforts have been devoted to the development of deep learning approaches, little attention has been devoted to deep few-shot learning for change detection.…”

Section: Figure 1 Example Bi-temporal Data From the Levir-cd Dataset For Building Change Detectionmentioning

confidence: 99%

“…Uncertainty modelling is a crucial step in the evaluation of the robustness for deep and few-shot learning models in remote sensing, especially when applied in risk-sensitive areas, such as building change detection (Cipolla et al, 2018;Khoshboresh Masouleh and Saradjian, 2019;Li and Alstrøm, 2020). Knowing the confidence with which we can trust the building change detection is important for decision-making in remote sensing .…”

Section: Uncertainty Modellingmentioning

confidence: 99%

“…Current urban and rural space growth rates and obvious effects of building construction on different applications, such as building damage assessments, building change detection, population estimation, and urban planning continuous monitoring of building footprints are becoming ever more significant (Hardin et al, 2007;Hegazy and Kaloop, 2015;Masouleh and Shah-Hosseini, 2018). The interest in developing building change detection methods from bi-temporal optical images with a different platform (e.g., UAV, Airborne, and Spaceborne) is rapidly increasing due to larger land-covers, and lower costs of remote sensing data (Bayanlou and Khoshboresh-Masouleh, 2020;Khoshboresh Masouleh and Saradjian, 2019;Khoshboresh-Masouleh and Hasanlou, 2020). Despite rapid advances in computer vision and remote sensing, change detection is a major challenge in mapping.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Few-Shot Learning for Bi-Temporal Building Change Detection

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

Shah-Hosseini

2021

Abstract. In real-world applications (e.g., change detection), annotating images is very expensive. To build effective deep learning models in these applications, deep few-shot learning methods have been developed and prove to be a robust approach in small training data. The study of building change detection from high spatial resolution satellite observations is important to research in remote sensing, photogrammetry, and computer vision nowadays, which can be widely used in a variety of real-world applications, such as map generation and updating. As manual high-resolution image interpretation is expensive and time-consuming, building change detection methods are of high interest. The interest in developing building change detection approaches from optical remote sensing images is rapidly increasing due to larger coverages, and lower costs of optical images. In this study, we focus on building change detection analysis on a small set of building changes from different regions that sit in several cities. In this paper, a new deep few-shot learning method is proposed for building change detection using Monte Carlo dropout and remote sensing observations. The setup is based on a small dataset, including bitemporal optical images labelled for building change detection.