Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Abstract

Automatic road extraction from very-high-resolution remote sensing images has become a popular topic in a wide range of fields. Convolutional neural networks are often used for this purpose. However, many network models do not achieve satisfactory extraction results because of the elongated nature and varying sizes of roads in images. To improve the accuracy of road extraction, this paper proposes a deep learning model based on the structure of Deeplab v3. It incorporates squeeze-and-excitation (SE) module to apply weights to different feature channels, and performs multi-scale upsampling to preserve and fuse shallow and deep information. To solve the problems associated with unbalanced road samples in images, different loss functions and backbone network modules are tested in the model’s training process. Compared with cross entropy, dice loss can improve the performance of the model during training and prediction. The SE module is superior to ResNext and ResNet in improving the integrity of the extracted roads. Experimental results obtained using the Massachusetts Roads Dataset show that the proposed model (Nested SE-Deeplab) improves F1-Score by 2.4% and Intersection over Union by 2.0% compared with FC-DenseNet. The proposed model also achieves better segmentation accuracy in road extraction compared with other mainstream deep-learning models including Deeplab v3, SegNet, and UNet.

Improving Road Surface Area Extraction via Semantic Segmentation with Conditional Generative Learning for Deep Inpainting Operations

“…We concluded that these imperfections were caused by the complex nature of the geospatial object (roads have large curvature changes, different materials used in the pavement, different widths, depending on the importance of the route, and very often have no clearly defined borders) by the presence of occlusions in the scenes, and by the limitation of existing semantic segmentation algorithms. These imperfections and errors are in line with issues raised by other investigations, as similar problems were identified in other works tackling the road extraction task from high-resolution remote sensing images [2], [3], [4], [5], and are very problematic when pursuing a large-scale road extraction operation for automatic mapping purposes. As a consequence, we consider that adding a post-processing operation to improve the initial segmentation predictions is essential for a successful road extraction.…”

Generative Learning for Postprocessing Semantic Segmentation Predictions: A Lightweight Conditional Generative Adversarial Network Based on Pix2pix to Improve the Extraction of Road Surface Areas

“…We also identified higher rates of "false positive labels in areas where the materials used in the road pavement have a similar spectral signature with their surroundings, or areas where geospatial objects with similar features are present (such as dry riverbeds, railroads, or irrigation canals) and higher rates of false negatives in sections where other objects cover large portions of the roads were covered" (page 13 in [8]). Similar problems are still observed in recent works dealing with the road extraction from high-resolution aerial imagery-improving the road extraction task is an active area of research [11][12][13][14].…”

Deep Learning-Based Building Footprint Extraction With Missing Annotations

“…The parameters τ , π y=1 and π y=0 are set to 1, 0.9 and 0.1, respectively. For validation, we compare the proposed loss with other commonly exploited losses for binary segmentation, including: 1) CE [6], [11]; 2) Dice; 3) NR-Dice [20]; 4) CE Dice [21]; 5) ELL [22]; 6) Weighted Dice (WDice); 7) BD Dice [15]; and 8) BD WDice. All the experiments are performed on an NVIDIA Tesla P100 GPU.…”