Accurate multi-scale object detection in remote sensing images poses a challenge due to the complexity of transferring deep features to shallow features among multi-scale objects. Therefore, this study developed a multi-feature fusion and attention network (MFANet) based on YOLOX. By reparameterizing the backbone, fusing multi-branch convolution and attention mechanisms, and optimizing the loss function, the MFANet strengthened the feature extraction of objects at different sizes and increased the detection accuracy. The ablation experiment was carried out on the NWPU VHR-10 dataset. Our results showed that the overall performance of the improved network was around 2.94% higher than the average performance of every single module. Based on the comparison experiments, the improved MFANet demonstrated a high mean average precision of 98.78% for 9 classes of objects in the NWPU VHR-10 10-class detection dataset and 94.91% for 11 classes in the DIOR 20-class detection dataset. Overall, MFANet achieved an mAP of 96.63% and 87.88% acting on the NWPU VHR-10 and DIOR datasets, respectively. This method can promote the development of multi-scale object detection in remote sensing images and has the potential to serve and expand intelligent system research in related fields such as object tracking, semantic segmentation, and scene understanding.

The comprehensive use of high-resolution remote sensing (HRS) images and deep learning (DL) methods can be used to further accurate urban green space (UGS) mapping. However, in the process of UGS segmentation, most of the current DL methods focus on the improvement of the model structure and ignore the spectral information of HRS images. In this paper, a multiscale attention feature aggregation network (MAFANet) incorporating feature engineering was proposed to achieve segmentation of UGS from HRS images (GaoFen-2, GF-2). By constructing a new decoder block, a bilateral feature extraction module, and a multiscale pooling attention module, MAFANet enhanced the edge feature extraction of UGS and improved segmentation accuracy. By incorporating feature engineering, including false color image and the Normalized Difference Vegetation Index (NDVI), MAFANet further distinguished UGS boundaries. The UGS labeled datasets, i.e., UGS-1 and UGS-2, were built using GF-2. Meanwhile, comparison experiments with other DL methods are conducted on UGS-1 and UGS-2 to test the robustness of the MAFANet network. We found the mean Intersection over Union (MIOU) of the MAFANet network on the UGS-1 and UGS-2 datasets was 72.15% and 74.64%, respectively; outperforming other existing DL methods. In addition, by incorporating false color image in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.64%; by incorporating vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.09%; and by incorporating false color image and the vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.73%. Our experimental results demonstrated that the proposed MAFANet incorporating feature engineering (false color image and NDVI) outperforms the state-of-the-art (SOTA) methods in UGS segmentation, and the false color image feature is better than the vegetation index (NDVI) for enhancing green space information representation. This study provided a practical solution for UGS segmentation and promoted UGS mapping.

High-spatial-resolution urban buildings play a crucial role in urban planning, emergency response, and disaster management. However, challenges such as missing building contours due to occlusion problems (occlusion between buildings of different heights and buildings obscured by trees), uneven contour extraction due to mixing of building edges with other feature elements (roads, vehicles, and trees), and slow training speed in high-resolution image data hinder efficient and accurate building extraction. To address these issues, we propose a semantic segmentation model composed of a lightweight backbone, coordinate attention module, and pooling fusion module, which achieves lightweight building extraction and adaptive recovery of spatial contours. Comparative experiments were conducted on datasets featuring typical urban building instances in China and the Mapchallenge dataset, comparing our method with several classical and mainstream semantic segmentation algorithms. The results demonstrate the effectiveness of our approach, achieving excellent mean intersection over union (mIoU) and frames per second (FPS) scores on both datasets (China dataset: 85.11% and 110.67 FPS; Mapchallenge dataset: 90.27% and 117.68 FPS). Quantitative evaluations indicate that our model not only significantly improves computational speed but also ensures high accuracy in the extraction of urban buildings from high-resolution imagery. Specifically, on a typical urban building dataset from China, our model shows an accuracy improvement of 0.64% and a speed increase of 70.03 FPS compared to the baseline model. On the Mapchallenge dataset, our model achieves an accuracy improvement of 0.54% and a speed increase of 42.39 FPS compared to the baseline model. Our research indicates that lightweight networks show significant potential in urban building extraction tasks. In the future, the segmentation accuracy and prediction speed can be further balanced on the basis of adjusting the deep learning model or introducing remote sensing indices, which can be applied to research scenarios such as greenfield extraction or multi-class target extraction.