Traditional and convolutional neural network (CNN)-based geographic object-based image analysis (GeOBIA) land-cover classification methods prosper in remote sensing and generate numerous distinguished achievements. However, a bottleneck emerges and hinders further improvements in classification results, due to the insufficiency of information provided by very high-spatial resolution images (VHSRIs). To be specific, the phenomenon of different objects with similar spectrum and the lack of topographic information (heights) are natural drawbacks of VHSRIs. Thus, multisource data steps into people’s sight and shows a promising future. Firstly, for data fusion, this paper proposed a standard normalized digital surface model (StdnDSM) method which was actually a digital elevation model derived from a digital terrain model (DTM) and digital surface model (DSM) to break through the bottleneck by fusing VHSRI and cloud points. It smoothed and improved the fusion of point cloud and VHSRIs and thus performed well in follow-up classification. The fusion data then were utilized to perform multiresolution segmentation (MRS) and worked as training data for the CNN. Moreover, the grey-level co-occurrence matrix (GLCM) was introduced for a stratified MRS. Secondly, for data processing, the stratified MRS was more efficient than unstratified MRS, and its outcome result was theoretically more rational and explainable than traditional global segmentation. Eventually, classes of segmented polygons were determined by majority voting. Compared to pixel-based and traditional object-based classification methods, majority voting strategy has stronger robustness and avoids misclassifications caused by minor misclassified centre points. Experimental analysis results suggested that the proposed method was promising for object-based classification.

Semantic segmentation is a crucial approach for remote sensing interpretation. High-precision semantic segmentation results are obtained at the cost of manually collecting massive pixelwise annotations. Remote sensing imagery contains complex and variable ground objects and obtaining abundant manual annotations is expensive and arduous. The semi-supervised learning (SSL) strategy can enhance the generalization capability of a model with a small number of labeled samples. In this study, a novel semi-supervised adversarial semantic segmentation network is developed for remote sensing information extraction. A multiscale input convolution module (MICM) is designed to extract sufficient local features, while a Transformer module (TM) is applied for long-range dependency modeling. These modules are integrated to construct a segmentation network with a double-branch encoder. Additionally, a double-branch discriminator network with different convolution kernel sizes is proposed. The segmentation network and discriminator network are jointly trained under the semi-supervised adversarial learning (SSAL) framework to improve its segmentation accuracy in cases with small amounts of labeled data. Taking building extraction as a case study, experiments on three datasets with different resolutions are conducted to validate the proposed network. Semi-supervised semantic segmentation models, in which DeepLabv2, the pyramid scene parsing network (PSPNet), UNet and TransUNet are taken as backbone networks, are utilized for performance comparisons. The results suggest that the approach effectively improves the accuracy of semantic segmentation. The F1 and mean intersection over union (mIoU) accuracy measures are improved by 0.82–11.83% and 0.74–7.5%, respectively, over those of other methods.

Change detection (CD) remains an important issue in remote sensing applications, especially for high spatial resolution (HSR) images, but it has yet to be fully resolved. This work proposes a novel object-based change detection (OBCD) method for HSR images that is based on region–line primitive association analysis and evidence fusion. In the proposed method, bitemporal images are separately segmented, and the segmentation results are overlapped to obtain the temporal region primitives (TRPs). The temporal line primitives (TLPs) are obtained by straight line detection on bitemporal images. In the initial CD stage, Dempster–Shafer evidence theory fuses the multiple items of evidence of the TRPs’ spectrum, edge, and gradient changes, and obtains the initial changed areas. In the refining CD stage, the association between the TRPs and their contacting TLPs in the unchanged areas is established on the basis of the region–line primitive association framework, and the TRPs’ main line directions (MLDs) are calculated. Some changed TRPs omitted in the initial CD stage are recovered by their MLD changes, thereby refining the initial CD results. Different from common OBCD methods, the proposed method considers the change evidence of TRPs’ internal and boundary information simultaneously via information complementation between TRPs and TLPs. The proposed method can significantly reduce missed alarms while maintaining a low level of false alarms in OBCD, thereby improving total accuracy. In our experiments, our method is superior to common CD methods, including change vector analysis (CVA), PCA-k-means, and iterative reweighted multivariate alteration detection (IRMAD), in terms of overall accuracy, missed alarms, and Kappa coefficient.

The timely detection of fishing activities supports the protection of water resources and aids law enforcement in fishing ban and shoreline inspection scenarios. Fishing rods are highly discriminative objects for identifying such activities; however, their slender shapes and varying orientations make feature extraction and precise localization difficult to achieve. The existing slender object detectors typically require oriented bounding-box supervision, resulting in high annotation costs and unstable angle regression. To address these issues, we propose a weakly supervised slender object detection network (WSSO-DETR) with a low annotation cost. It employs horizontal-box supervision and exploits angle relation consistency and scale invariance across multiview transformations, reducing the need for oriented box annotations. The scale and orientation estimated by the horizontal box branch are used to construct a long-axis prior, based on which an oriented object reference point generation module (OORPG) is designed. We further introduce a point set-based oriented decoder (PSOD) and an encoder–decoder feature fusion-based prediction head (E-DFFPH) to model the interactions among object-related point sets and attain improved localization performance. Experiments show that WSSO-DETR improves the mAP₅₀ metric by 2.5–15.3% on Slender COCO, by 1.1–4.8% on Fishing Detect, and by 1.7–4.9% on DOTA-v1.0, demonstrating its effectiveness and generalizability.