High-resolution remote-sensing images cover more feature information, including texture, structure, shape, and other geometric details, while the relationships among target features are more complex. These factors make it more complicated for classical convolutional neural networks to obtain ideal results when performing a feature classification on remote-sensing images. To address this issue, we proposed an attention-based multiscale max-pooling dense network (DMAU-Net), which is based on U-Net for ground object classification. The network is designed with an integrated max-pooling module that incorporates dense connections in the encoder part to enhance the quality of the feature map, and thus improve the feature-extraction capability of the network. Equally, in the decoding, we introduce the Efficient Channel Attention (ECA) module, which can strengthen the effective features and suppress the irrelevant information. To validate the ground object classification performance of the multi-pooling integration network proposed in this paper, we conducted experiments on the Vaihingen and Potsdam datasets provided by the International Society for Photogrammetry and Remote Sensing (ISPRS). We compared DMAU-Net with other mainstream semantic segmentation models. The experimental results show that the DMAU-Net proposed in this paper effectively improves the accuracy of the feature classification of high-resolution remote-sensing images. The feature boundaries obtained by DMAU-Net are clear and regionally complete, enhancing the ability to optimize the edges of features.

Complex traffic scenes are susceptible to the occlusion of moving targets and blurred target images, resulting in incomplete extraction of target trajectories within the field of view (FOV). To address this issue, we proposed a complete trajectory extraction algorithm for moving targets (TraEA) that considers the multi-level semantic features of traffic scenes following the FOV of single-camera surveillance videos. TraEA utilizes semantic information from the multi-level scene structure, such as image pixel features, geometric features, as well as temporal and spatial relationships between targets within each keyframe image. The semantic information helps extract and optimize the complete trajectory of a target, to assemble the target’s moving trajectory with improved integrity. An experiment with real-world traffic videos collected in Beijing, China validated the proposed algorithm and showed that TraEA improved the completeness, accuracy and robustness of target trajectory extraction. Traffic trajectories from the experiment can facilitate traffic supervision by analyzing the moving behaviors of individual targets. While the proposed TraEA algorithm is applicable to extract trajectories from videos in other domains, such as animal movements, potential privacy infringement and abusive applications warrant cautions of ethical considerations.

As a fundamental task in remote sensing interpretation, semantic segmentation of remote sensing images intends to allocate a definite class to each pixel in the image. Fast and efficient semantic segmentation of high-resolution remote sensing images provides helps to capture the real surface covering and plays an essential role in urban planning and dynamic monitoring. However, there are still some limitations in the previous remote sensing image semantic segmentation model for urban scenes, such as the low weight of small target pixels and the tiny target size leading to the unsatisfactory recognition and segmentation results of the model for small target features. Meanwhile, the deeper and broader feature extraction module in the semantic segmentation network usually leads to more redundant parameters, which takes a lot of computation time. Thus, we propose a lightweight semantic segmentation network based on knowledge distillation combined with a multiscale pyramidal pooling mod-ule and attention mechanism named KDMSANet, which enhanced the ability to fuse and focus on shallow features. Then, we trained teacher-student models to obtain lightweight network models through a model pruning and distillation framework. Experiments on Vaihingen and Potsdam datasets demonstrated that the network we designed significantly reduces the number of parameters while ensuring almost constant accuracy. Compared to the pre-compression model, the student model reduced in size by 43.6% the training efficiency was improved by 22.3%, while the accuracy reached 99.30% of the teacher model

Deep learning methods are now frequently adopted for delineating buildings from fine-grained geospatial imagery. Nevertheless, challenges persist due to the diverse colors and shapes of building rooftops, significant variations in spectral characteristics, and complex backgrounds. A primary limitation of existing approaches is their inadequate use of contour information, which is essential for precise localization, often leading to suboptimal boundary definitions. Furthermore, occlusions and the difficulty in effectively integrating multi-scale features hinder the complete extraction of buildings. To tackle these challenges, we introduce a Semantic-Contour Synergy Network designed to simultaneously perform semantic segmentation and contour detection. The contour branch incorporates a Contour Enhancement Module (CEM) to capture fine-grained contour features and facilitates multi-scale interaction with the semantic branch, guiding the network toward more precise localization. To further improve the extraction of large-scale and occluded buildings, we introduce a Multi-Scale Convolutional Fusion Module (MSCFM) which extracts and fuses multi-scale features within each layer. Additionally, the Global-Local Attention Fusion Module (GLAF) adaptively fuses cross-scale features, addressing the limitation of fixed-weight fusion in traditional skip connections when handling buildings of varying scales. Deep supervision is applied to both tasks to preserve fine details in deep features. To validate our approach, we conducted comprehensive experiments on three benchmark datasets: the CrowdAI mapping challenge, Inria aerial image labeling, and Building Instances of Typical Cities in China. The findings confirm the effectiveness of our model, which exhibits noticeably gains in contour delineation and maintains robustness against variations in scale and occlusion.