Inria Aerial Image Labeling Research Articles

Asymmetric Network Combining CNN and Transformer for Building Extraction from Remote Sensing Images.

The accurate extraction of buildings from remote sensing images is crucial in fields such as 3D urban planning, disaster detection, and military reconnaissance. In recent years, models based on Transformer have performed well in global information processing and contextual relationship modeling, but suffer from high computational costs and insufficient ability to capture local information. In contrast, convolutional neural networks (CNNs) are very effective in extracting local features, but have a limited ability to process global information. In this paper, an asymmetric network (CTANet), which combines the advantages of CNN and Transformer, is proposed to achieve efficient extraction of buildings. Specifically, CTANet employs ConvNeXt as an encoder to extract features and combines it with an efficient bilateral hybrid attention transformer (BHAFormer) which is designed as a decoder. The BHAFormer establishes global dependencies from both texture edge features and background information perspectives to extract buildings more accurately while maintaining a low computational cost. Additionally, the multiscale mixed attention mechanism module (MSM-AMM) is introduced to learn the multiscale semantic information and channel representations of the encoder features to reduce noise interference and compensate for the loss of information in the downsampling process. Experimental results show that the proposed model achieves the best F1-score (86.7%, 95.74%, and 90.52%) and IoU (76.52%, 91.84%, and 82.68%) compared to other state-of-the-art methods on the Massachusetts building dataset, the WHU building dataset, and the Inria aerial image labeling dataset.

Semantic Segmentation of Remote Sensing Images Depicting Environmental Hazards in High-Speed Rail Network Based on Large-Model Pre-Classification.

With the rapid development of China's railways, ensuring the safety of the operating environment of high-speed railways faces daunting challenges. In response to safety hazards posed by light and heavy floating objects during the operation of trains, we propose a dual-branch semantic segmentation network with the fusion of large models (SAMUnet). The encoder part of this network uses a dual-branch structure, in which the backbone branch uses a residual network for feature extraction and the large-model branch leverages the results of feature extraction generated by the segment anything model (SAM). Moreover, a decoding attention module is fused with the results of prediction of the SAM in the decoder part to enhance the performance of the network. We conducted experiments on the Inria Aerial Image Labeling (IAIL), Massachusetts, and high-speed railway hazards datasets to verify the effectiveness and applicability of the proposed SAMUnet network in comparison with commonly used semantic segmentation networks. The results demonstrated its superiority in terms of both the accuracies of segmentation and feature extraction. It was able to precisely extract hazards in the environment of high-speed railways to significantly improve the accuracy of semantic segmentation.

Dual Hybrid Attention Mechanism-Based U-Net for Building Segmentation in Remote Sensing Images

High-resolution remote sensing images (HRRSI) have important theoretical and practical value in urban planning. However, current segmentation methods often struggle with issues like blurred edges and loss of detailed information due to the intricate backgrounds and rich semantics in high-resolution remote sensing images. To tackle these challenges, this paper proposes an end-to-end attention-based Convolutional Neural Network (CNN) called Double Hybrid Attention U-Net (DHAU-Net). We designed a new Double Hybrid Attention structure consisting of dual-parallel hybrid attention modules to replace the skip connections in U-Net, which can eliminate redundant information interference and enhances the collection and utilization of important shallow features. Comprehensive experiments on the Massachusetts remote sensing building dataset and the Inria aerial image labeling dataset demonstrate that our proposed method achieves effective pixel-level building segmentation in urban remote sensing images by eliminating redundant information interference and making full use of shallow features, and improves the segmentation performance without significant time costs (approximately 15%). The evaluation metrics reveal significant results, with an accuracy rate of 0.9808, precision reaching 0.9300, an F1 score of 0.9112, a mean intersection over union (mIoU) of 0.9088, and a recall rate of 0.8932.

Dense Connected Edge Feature Enhancement Network for Building Edge Detection from High Resolution Remote Sensing Imagery

Deep-learning-based methods for building-edge-detection have been widely researched and applied in the field of image processing. However, these methods often emphasis the analysis of deep features, which may result in neglecting crucial shallow information representation. Furthermore, abstract features in the deep layers can potentially interfere with the accuracy of edge extraction. To address these challenges, we propose a densely connected edge-detection enhancement network (DCEFE-Net) for building-edge-detection in high-resolution remote sensing images. Firstly, by introducing spatial land channel attention modules, we effectively captured low-level spatial information and high-level semantic information from the input image. Secondly, the proposed edge-aware feature enhancement (EAFE) module emphasis the representation of informative edge features. By alliteratively generating multiple layers of edge-detection maps, it addresses the issue of edge detail loss and enhances edge-detection accuracy. Finally, the dense connectivity blocks strengthen the connections between the convolutional layers, thereby preventing the loss of edge features. Experimental results on the WHU and the Inria Aerial Image Labeling datasets validate the effectiveness of DCEFE-Net, as it consistently produces clear and reliable building-edge results.

Comparative Analysis of Different CNN Models for Building Segmentation from Satellite and UAV Images

Building segmentation has numerous application areas such as urban planning and disaster management. In this study, 12 CNN models (U-Net, FPN, and LinkNet using EfficientNet-B5 backbone, U-Net, SegNet, FCN, and six Residual U-Net models) were generated and used for building segmentation. Inria Aerial Image Labeling Data Set was used to train models, and three data sets (Inria Aerial Image Labeling Data Set, Massachusetts Buildings Data Set, and Syedra Archaeological Site Data Set) were used to evaluate trained models. On the Inria test set, Residual-2 U-Net has the highest F1 and Intersection over Union (IoU) scores with 0.824 and 0.722, respectively. On the Syedra test set, LinkNet-EfficientNet-B5 has F1 and IoU scores of 0.336 and 0.246. On the Massachusetts test set, Residual-4 U-Net has F1 and IoU scores of 0.394 and 0.259. It has been observed that, for all sets, at least two of the top three models used residual connections. Therefore, for this study, residual connections are more successful than conventional convolutional layers.

An Anomaly Detection-Based Domain Adaptation Framework for Cross-Domain Building Extraction from Remote Sensing Images

Deep learning-based building extraction methods have achieved a high accuracy in closed remote sensing datasets. In fact, the distribution bias between the source and target domains can lead to a dramatic decrease in their building extraction effect in the target domain. However, the mainstream domain adaptation methods that specifically address this domain bias problem require the reselection of many unlabeled samples and retraining in other target domains. This is time-consuming and laborious and even impossible at small regions. To address this problem, a novel domain adaptation framework for cross-domain building extraction is proposed from a perspective of anomaly detection. First, the initial extraction results of images in the target domain are obtained by a source domain-based pre-trained model, and then these results are classified into building mixed and non-building layers according to the predicted probability. Second, anomalous objects in the building layer are detected using the isolation forest method. Subsequently, the remaining objects in the building layer and the objects in the non-building layer are used as positive and negative samples, respectively, to reclassify the mixed layer using the random forest classifier. The newly extracted objects are fused with the remaining objects in the building layer as the final result. Four different experiments are performed on different semantic segmentation models and target domains. Some experimental results indicate that our framework can improve cross-domain building extraction compared to the pre-trained model, with an 8.7% improvement in the F1 metric when migrating from the Inria Aerial Image Labeling dataset to the Wuhan University dataset. Furthermore, experimental results show that our framework can be applied to multiple target domains without retraining and can achieve similar results to domain adaptation models based on adversarial learning.

SDSC-UNet: Dual Skip Connection ViT-Based U-Shaped Model for Building Extraction

Benefiting from effective global information interaction, vision-transformers (ViTs) have been widely used in the building extraction task. However, buildings in remote sensing (RS) images usually differ greatly in size. Mainstream ViT-based segmentation models for RS images are based on Swin Transformer, which lacks multi-scale information inside the ViT block. In addition, they only connect the output of the entire ViT encoder block to the decoder, which ignore the similarity information of the attention maps inside the ViT encoder block, and are unable to provide better global dependencies for the decoder. To solve above problems, we introduce a novel Shunted Transformer, which enables the model to capture multi-scale information internally while fully establishing global dependencies, to build a pure ViT-based U-shaped model for building extraction. Furthermore, unlike the previous single-skip-connection structure of U-shaped methods, we build a novel dual skip connection structure inside the model. It simultaneously transmits the attention maps inside the ViT encoder block and its entire output to the decoder, thereby fully mining the information of the ViT encoder block and providing better global information guidance for the decoder. Thus, our model is named Shunted Dual Skip Connection UNet (SDSC-UNet). We also design a feature fusion module called Dual Skip Upsample Fusion Module (DSUFM) to aggregate the information. Our model has yields state-of-the-art (SOTA) performance (83.02%IoU) on the Inria Aerial Image Labeling Dataset. Code will be available.

AFL-Net: Attentional Feature Learning Network for Building Extraction from Remote Sensing Images

Convolutional neural networks (CNNs) perform well in tasks of segmenting buildings from remote sensing images. However, the intraclass heterogeneity of buildings is high in images, while the interclass homogeneity between buildings and other nonbuilding objects is low. This leads to an inaccurate distinction between buildings and complex backgrounds. To overcome this challenge, we propose an Attentional Feature Learning Network (AFL-Net) that can accurately extract buildings from remote sensing images. We designed an attentional multiscale feature fusion (AMFF) module and a shape feature refinement (SFR) module to improve building recognition accuracy in complex environments. The AMFF module adaptively adjusts the weights of multi-scale features through the attention mechanism, which enhances the global perception and ensures the integrity of building segmentation results. The SFR module captures the shape features of the buildings, which enhances the network capability for identifying the area between building edges and surrounding nonbuilding objects and reduces the over-segmentation of buildings. An ablation study was conducted with both qualitative and quantitative analyses, verifying the effectiveness of the AMFF and SFR modules. The proposed AFL-Net achieved 91.37, 82.10, 73.27, and 79.81% intersection over union (IoU) values on the WHU Building Aerial Imagery, Inria Aerial Image Labeling, Massachusetts Buildings, and Building Instances of Typical Cities in China datasets, respectively. Thus, the AFL-Net offers the prospect of application for successful extraction of buildings from remote sensing images.

A Residual-Inception U-Net (RIU-Net) Approach and Comparisons with U-Shaped CNN and Transformer Models for Building Segmentation from High-Resolution Satellite Images.

Building segmentation is crucial for applications extending from map production to urban planning. Nowadays, it is still a challenge due to CNNs’ inability to model global context and Transformers’ high memory need. In this study, 10 CNN and Transformer models were generated, and comparisons were realized. Alongside our proposed Residual-Inception U-Net (RIU-Net), U-Net, Residual U-Net, and Attention Residual U-Net, four CNN architectures (Inception, Inception-ResNet, Xception, and MobileNet) were implemented as encoders to U-Net-based models. Lastly, two Transformer-based approaches (Trans U-Net and Swin U-Net) were also used. Massachusetts Buildings Dataset and Inria Aerial Image Labeling Dataset were used for training and evaluation. On Inria dataset, RIU-Net achieved the highest IoU score, F1 score, and test accuracy, with 0.6736, 0.7868, and 92.23%, respectively. On Massachusetts Small dataset, Attention Residual U-Net achieved the highest IoU and F1 scores, with 0.6218 and 0.7606, and Trans U-Net reached the highest test accuracy, with 94.26%. On Massachusetts Large dataset, Residual U-Net accomplished the highest IoU and F1 scores, with 0.6165 and 0.7565, and Attention Residual U-Net attained the highest test accuracy, with 93.81%. The results showed that RIU-Net was significantly successful on Inria dataset. On Massachusetts datasets, Residual U-Net, Attention Residual U-Net, and Trans U-Net provided successful results.

MSL-Net: An Efficient Network for Building Extraction from Aerial Imagery

There remains several challenges that are encountered in the task of extracting buildings from aerial imagery using convolutional neural networks (CNNs). First, the tremendous complexity of existing building extraction networks impedes their practical application. In addition, it is arduous for networks to sufficiently utilize the various building features in different images. To address these challenges, we propose an efficient network called MSL-Net that focuses on both multiscale building features and multilevel image features. First, we use depthwise separable convolution (DSC) to significantly reduce the network complexity, and then we embed a group normalization (GN) layer in the inverted residual structure to alleviate network performance degradation. Furthermore, we extract multiscale building features through an atrous spatial pyramid pooling (ASPP) module and apply long skip connections to establish long-distance dependence to fuse features at different levels of the given image. Finally, we add a deformable convolution network layer before the pixel classification step to enhance the feature extraction capability of MSL-Net for buildings with irregular shapes. The experimental results obtained on three publicly available datasets demonstrate that our proposed method achieves state-of-the-art accuracy with a faster inference speed than that of competing approaches. Specifically, the proposed MSL-Net achieves 90.4%, 81.1% and 70.9% intersection over union (IoU) values on the WHU Building Aerial Imagery dataset, Inria Aerial Image Labeling dataset and Massachusetts Buildings dataset, respectively, with an inference speed of 101.4 frames per second (FPS) for an input image of size 3 × 512 × 512 on an NVIDIA RTX 3090 GPU. With an excellent tradeoff between accuracy and speed, our proposed MSL-Net may hold great promise for use in building extraction tasks.

Grsnet: gated residual supervision network for pixel-wise building segmentation in remote sensing imagery

ABSTRACT The increasing development of imaging technology has made aerial image analysis one of the most widely used fields in image processing. Building extraction is the basic step in analysing urban structures, detecting construction violations, updating urban geographical divisions, and forecasting natural disasters. In this study, the aim is to automatically segment buildings in high-resolution satellite images using a new hybrid deep learning model, named Gated Residual Supervision Network (GRSNet). GRSNet extends the UNet framework by including three important components, i.e. attention gates (AG), residual units, and deep supervision part, with the main focus on transferring and reusing features. At first, the AG mechanism utilizes channel and spatial fine features to merge them effectively and deep supervision transfers feature details from the depths of the network. Then, residual units retrieve the information at different levels to train the model quickly. Finally, a fully connected classifier recovers features from the input image. GRSNet is evaluated on Massachusetts buildings public dataset and Inria aerial image labeling benchmark. The obtained results show the superiority of the proposed method compared to other deep learning-based state-of-the-art building segmentation methods with an intersection over union (IOU) of 89.86% and an F1-score of 94.53%.

Comparison of residual and dense neural network approaches for building extraction from high-resolution aerial images

Applications including change detection, disaster management, and urban planning require precise building information, and therefore automatic building extraction has become a significant research topic. With the improvements in sensor and satellite technologies, more data has become available, and with the increased computational power, deep learning methods have emerged as successful tools. In this study, U-Net and FPN architectures using four different backbones (ResNet-50, ResNeXt-50, SE-ResNext-50, and DenseNet-121), and an Attention Residual U-Net approach were used for building extraction from high-resolution aerial images. Two publicly available datasets, Inria Aerial Image Labeling Dataset and Massachusetts Buildings Dataset were used to train and test the models. According to the results, Attention Residual U-Net model has the highest F1 score with 0.8154, IoU score with 0.7102, and test accuracy with 94.51% on the Inria dataset. On the Massachusetts dataset, FPN Dense-Net-121 model has the highest F1 score with 0.7565 and IoU score with 0.6188, and Attention Residual U-Net model has the highest test accuracy with 92.43%. It has been observed that, FPN with DenseNet backbone can be a better choice when working with small size datasets. On the other hand, Attention Residual U-Net approach achieved higher success when a sufficiently large dataset is provided.

Comparative research on different backbone architectures of DeepLabV3+ for building segmentation

Rapid urban growth and globalization affect land use in cities, and the need for automatic interpretation of remote sensing images is constantly increasing. Deep neural networks are becoming widespread in high-resolution aerial and satellite image sources in Earth observation missions. Various convolutional neural network (CNN) architectures have been implemented in building extraction, but it is still challenging to distinguish building class from other man-made classes in public datasets. Here, we present comparative research for automatic building extraction on different data sources using DeepLabV3+ architecture with ResNet-18, ResNet-50, Xception, and MobileNetv2 models. The CNNs are implemented on Inria Aerial Image Labeling, Massachusetts Buildings, and Wuhan University Building Extraction Datasets in terms of evaluation metrics and training and testing time consumption. Our implementation of the DeepLabV3 + ResNet-50 model performed F1-score of 97.44% in Massachusetts Building dataset and intersection over union as 80.75% in Inria dataset, higher than at least 3% than the previous studies.

Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints

Building footprint has a significant role in urban design and management but, extracting the building feature is still challenging due to significant variations in scale and shape. Convolution neural networks (CNN) have shown effective results in extracting the high-level and discriminative urban features from high-resolution remote sensing imagery. The traditional CNN architecture has been modified two-scale input based architecture, known as Dual-scale CNN (Du-CNN). However, the repetitive usage of pooling operation leads to a fuzzy boundary of the extracted features. This paper has proposed the MRF-based fusion strategy to take full use of the blurred boundary and define the conditional relationship between classification maps. In the Preliminary stage, we have designed a Du-CNN framework to extract the building feature at different scales. Du-CNN contains a multiple-size asymmetric filter to provide the variation in the receptive field and the depth-wise convolution in the skip connection block for efficient computation. Finally, the classification maps of both CNN sub-architectures are fused using a Modified Markov random field (MMRF). The proposed MMRF technique inherits the properties of Classical MRF with the extension of overlap potential for associating additional terms between the inter-decision layer. The model was tested on Inria Aerial image labeling dataset and Mnih dataset. Experimental result has shown the superior performance of the proposed strategy for extracting the complex building architecture.

AGs-Unet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network.

Building contour extraction from high-resolution remote sensing images is a basic task for the reasonable planning of regional construction. Recently, building segmentation methods based on the U-Net network have become popular as they largely improve the segmentation accuracy by applying ‘skip connection’ to combine high-level and low-level feature information more effectively. Meanwhile, researchers have demonstrated that introducing an attention mechanism into U-Net can enhance local feature expression and improve the performance of building extraction in remote sensing images. In this paper, we intend to explore the effectiveness of the primeval attention gate module and propose the novel Attention Gate Module (AG) based on adjusting the position of ‘Resampler’ in an attention gate to Sigmoid function for a building extraction task, and a novel Attention Gates U network (AGs-Unet) is further proposed based on AG, which can automatically learn different forms of building structures in high-resolution remote sensing images and realize efficient extraction of building contour. AGs-Unet integrates attention gates with a single U-Net network, in which a series of attention gate modules are added into the ‘skip connection’ for suppressing the irrelevant and noisy feature responses in the input image to highlight the dominant features of the buildings in the image. AGs-Unet improves the feature selection of the attention map to enhance the ability of feature learning, as well as paying attention to the feature information of small-scale buildings. We conducted the experiments on the WHU building dataset and the INRIA Aerial Image Labeling dataset, in which the proposed AGs-Unet model is compared with several classic models (such as FCN8s, SegNet, U-Net, and DANet) and two state-of-the-art models (such as PISANet, and ARC-Net). The extraction accuracy of each model is evaluated by using three evaluation indexes, namely, overall accuracy, precision, and intersection over union. Experimental results show that the proposed AGs-Unet model can improve the quality of building extraction from high-resolution remote sensing images effectively in terms of prediction performance and result accuracy.

Multi-channel recurrent attention network for building extraction from high resolution remote sensing images

Building extraction from high-resolution remote sensing images is of great importance for urban planning, disaster assessment, and geography mapping. In recent years, convolutional neural networks have made outstanding achievements in improving the precision of building extraction. However, most existing approaches have some problems, such as insufficient detailed feature extraction and ignorance of the relationship between different features. In this study, we propose a novel multi-channel recurrent attention network (MCANet) for building extraction. Firstly, the multi-scale channel attention mechanism is used to expand the convolution kernel receptive field, making the model can extract rich building region feature information. Secondly, we use the spatial pyramid recurrent block to establish long-range dependencies over space, channel, and layer of different convolutions. Finally, the multi-channel feature fusion block is used to fuse the multi-scale channel features information, and improve the building extraction precision. Experimental results show that the proposed MCANet achieves better results (recall, precision, intersection-over-union, and F1_score on the Inria Aerial Image Labeling Dataset are 89.82%, 94.38%, 87.42%, and 88.25%, respectively), and outperforms the other state-of-the-art approaches.

Building extraction from remote sensing images using deep residual U-Net

ABSTRACT Building extraction is a fundamental area of research in the field of remote sensing. In this paper, we propose an efficient model called residual U-Net (RU-Net) to extract buildings. It combines the advantages of U-Net, residual learning, atrous spatial pyramid pooling, and focal loss. The U-Net model, based on modified residual learning, can reduce the parameters and degradation of the network; atrous spatial pyramid pooling can acquire multiscale features and context information of the sensing images; and focal loss can solve the problem of unbalanced categories in classification. We implemented it on the WHU aerial image dataset and the Inria aerial image labeling dataset. The results of RU-Net were compared with the results of U-Net, FastFCN, DeepLabV3+, Web-Net, and SegNet. Experimental results show that the proposed RU-Net is superior to the others in all aspects of the WHU dataset. For the Inria dataset, most evaluation metrics of RU-Net are better than the others, as well as the sharp, boundary, and multiscale information. Compared with FastFCN and DeepLabV3+, our method increases the efficiency by three to four times.

BOMSC-Net: Boundary Optimization and Multi-Scale Context Awareness Based Building Extraction From High-Resolution Remote Sensing Imagery

Automatic building extraction from high-resolution remote sensing imagery has various applications, such as urban planning and land use management. However, the existing methods for automatic building extraction focus on regional accuracy but not on boundary quality. As a result, these building extraction methods yield discontinuous results due to tree and shadow occlusions and complex building roof materials. In this article, BOMSC-Net, which can consider boundary optimization and multi-scale context awareness, is proposed to address these two problems. BOMSC-Net is an encoder-to-decoder network composed of a basic network, a multi-scale context-aware module (MSCAM), and a direction feature optimization module (DFOM). The basic network learns to predict building segmentation maps through attention gates (AGs) that connect low-level feature jumps to advanced semantics. MSCAM is used as a bridge, which uses graph reasoning blocks (GRBs) to solve intra-class discontinuities. Finally, the DFOM constructs a direction field (DF) and then uses direction information for boundary correction to achieve fine building segmentations. Experiments were conducted on the open Massachusetts building dataset, WHU aerial building dataset, and Inria aerial image labeling dataset. The quantitative and qualitative analyses demonstrate that the proposed BOMSC-Net can help building extraction overcome interruptions caused by shadows and occlusions, extract buildings with different scales and materials, and realize boundary optimization and complete segmentation of buildings.

ASF-Net: Adaptive Screening Feature Network for Building Footprint Extraction From Remote-Sensing Images

Building footprint extraction plays an important role in many remote-sensing (RS) applications such as urban planning and disaster monitoring. Mainly, the exploitation of contextual information in a fixed receptive field is the focus of previous research, which makes it difficult to generically extract buildings that vary greatly in size and shape, especially when isolated large buildings are surrounded by dense small buildings. To improve this problem, we attempt to teach the network to adjust the receptive field and enhance useful feature information adaptively. In this article, we propose a novel adaptive screening feature network (ASF-Net), which can independently screen and enhance effective feature information from two aspects. On the one hand, we propose a deepened space up-sampling block to screen useful information and help establish boundaries. On the other hand, we propose an Adaptive Information Utilization Block (AIUB) to enlarge the receptive field of feature maps and refine the incomplete building footprint. As a result, the more accurate multiscale building footprint is inferred from the enhanced features. Experimental results on the popular aerial image segmentation datasets show that ASF-Net obtains competitive results [80.2% intersection over union (IoU) on the Inria aerial image labeling dataset and 74.2% IoU on the Massachusetts buildings dataset] in comparison with several state-of-the-art models. The TensorFlow implementation is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/jyx0516/ASF-Net</uri> .

Building Extraction from Remote Sensing Images with Sparse Token Transformers

Deep learning methods have achieved considerable progress in remote sensing image building extraction. Most building extraction methods are based on Convolutional Neural Networks (CNN). Recently, vision transformers have provided a better perspective for modeling long-range context in images, but usually suffer from high computational complexity and memory usage. In this paper, we explored the potential of using transformers for efficient building extraction. We design an efficient dual-pathway transformer structure that learns the long-term dependency of tokens in both their spatial and channel dimensions and achieves state-of-the-art accuracy on benchmark building extraction datasets. Since single buildings in remote sensing images usually only occupy a very small part of the image pixels, we represent buildings as a set of “sparse” feature vectors in their feature space by introducing a new module called “sparse token sampler”. With such a design, the computational complexity in transformers can be greatly reduced over an order of magnitude. We refer to our method as Sparse Token Transformers (STT). Experiments conducted on the Wuhan University Aerial Building Dataset (WHU) and the Inria Aerial Image Labeling Dataset (INRIA) suggest the effectiveness and efficiency of our method. Compared with some widely used segmentation methods and some state-of-the-art building extraction methods, STT has achieved the best performance with low time cost.