This paper focuses on learning complex polyline generalization. First, the requirements for sampled images to ensure the effective learning of complex polyline generalization are analysed. To meet these requirements, new methods for segmenting complex polylines and sampling images are proposed. Second, using the proposed segmentation and sampling method, a use case for the learning of complex polyline generalization using the generative adversarial network model, Pix2Pix, is developed. Third, this use case is applied experimentally for the complex generalization of coastline data from a scale of 1:50,000 to 1:250,000. Additionally, contrast experiments are conducted to compare the proposed segmentation and sampling method with object-based and traditional fixed-size methods. Experimental results show that the images generated using the proposed method are superior to the other two methods in the learning and application of complex polyline generalization. The results generalized for the developed use case are globally reasonable and suitably accurate.

The present paper presents techniques for polyline simplification based on an artificial neural network within the constraints of generalization knowledge. The proposed method measures polyline shape characteristics that influence polyline simplification using abstracted descriptors and then introduces these descriptors into the artificial neural network as input properties. In total, 18 descriptors categorized into three types are presented in detail. In a second approach, map simplification principles are abstracted as controllers, imposed after the output layer of the trained artificial neural network to make the polyline simplification comply with these principles. This study worked with three controllers – a basic controller and two knowledge-based controllers. These descriptors and controllers abstracted from generalization knowledge were tested in experiments to determine their efficacy in polyline simplification based on the artificial neural network. The experimental results show that the utilization of abstracted descriptors and controllers can constrain the artificial neural network-based polyline simplification according to polyline shape characteristics and simplification principles.

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.

Detecting buildings, segmenting building footprints, and extracting building edges from high-resolution remote sensing images are vital in applications such as urban planning, change detection, smart cities, and map-making and updating. The tasks of building detection, footprint segmentation, and edge extraction affect each other to a certain extent. However, most previous works have focused on one of these three tasks and have lacked a multitask learning framework that can simultaneously solve the tasks of building detection, footprint segmentation and edge extraction, making it difficult to obtain smooth and complete buildings. This study proposes a novel multiscale and multitask deep learning framework to consider the dependencies among building detection, footprint segmentation, and edge extraction while completing all three tasks. In addition, a multitask feature fusion module is introduced into the deep learning framework to increase the robustness of feature extraction. A multitask loss function is also introduced to balance the training losses among the various tasks to obtain the best training results. Finally, the proposed method is applied to open-source building datasets and large-scale high-resolution remote sensing images and compared with other advanced building extraction methods. To verify the effectiveness of multitask learning, the performance of multitask learning and single-task training is compared in ablation experiments. The experimental results show that the proposed method has certain advantages over other methods and that multitask learning can effectively improve single-task performance.

As one of the key operators of automated map generalization, algorithms for the line simplification have been widely researched in the past decades. Although many of the currently available algorithms have revealed satisfactory simplification performances with certain data types and selected test areas, it still remains a challenging task to solve the problems of (a) how to properly divide a cartographic line when it is too long to be dealt with directly; and (b) how to make adaptable parameterizations for various geo-data in different areas. In order to solve these two problems, a new line-simplification approach based on the Oblique-Dividing-Curve (ODC) method has been proposed in this paper. In this proposed model, one cartographic line is divided into a series of monotonic curves by the ODC method. Then, the curves are categorized into different groups according to their shapes, sizes and other geometric characteristics. The curves in different groups will trigger different strategies as well as the associated criteria for line simplification. Whenever a curve is simplified, the whole simplified cartographic line will be re-divided and the simplification process restarts again, i.e., the proposed simplification approach is iteratively operated until the final simplification result is achieved. Experiment evidence demonstrates that the proposed approach is able to handle the holistic bend-trend of the whole cartographic line during the simplification process and thereby provides considerably improved simplification performance with respect to maintaining the essential shape/salient characteristics and keeping the topological consistency. Moreover, the produced simplification results are not sensitive to the parameterizations of the proposed approach.