Deep learning algorithms have recently provided new ideas for various change detection (CD) tasks, which have yielded promising results. However, accurately identifying urban land cover and land use (LCLU) changes remains challenging in the very high-resolution (HR) remote sensing images due to the difficulties in effectively modeling the features from ground objects with different times and different spatial locations. In this letter, a multiscale swin transformer (MST)-based deeply supervised network (MSTDSNet) is proposed for monitoring urban LCLU changes using bi-temporal very HR remote sensing images. The wider and deeper layer aggregation (WDLA) is first introduced to improve the distinguishability of multiscale features. Subsequently, MST is adopted to make the most of the available spatial information in the refined multiscale features. Moreover, channel-wise dependencies (CWDS) are integrated as a soft constraint to directly supervise WDLA. Experiments are conducted on the widely used SYSU-CD and LEVIR-CD datasets. Compared with other state-of-the-art CD methods, MSTDSNet provides favorable performance, with the highest F1 of 80.33% and 88.10%, respectively.

Most object detection methods based on remote sensing images are generally dependent on a large amount of high-quality labeled training data. However, due to the slow acquisition cycle of remote sensing images and the difficulty in labeling, many types of data samples are scarce. This makes few-shot object detection an urgent and necessary research problem. In this paper, we introduce a remote sensing few-shot object detection method based on text semantic fusion relation graph reasoning (TSF-RGR), which learns various types of relationships from common sense knowledge in an end-to-end manner, thereby empowering the detector to reason over all classes. Specifically, based on the region proposals provided by the basic detection network, we first build a corpus containing a large number of text language descriptions, such as object attributes and relations, which are used to encode the corresponding common sense embeddings for each region. Then, graph structures are constructed between regions to propagate and learn key spatial and semantic relationships. Finally, a joint relation reasoning module is proposed to actively enhance the reliability and robustness of few-shot object feature representation by focusing on the degree of influence of different relations. Our TSF-RGR is lightweight and easy to expand, and it can incorporate any form of common sense information. Sufficient experiments show that the text information is introduced to deliver excellent performance gains for the baseline model. Compared with other few-shot detectors, the proposed method achieves state-of-the-art performance for different shot settings and obtains highly competitive results on two benchmark datasets (NWPU VHR-10 and DIOR).

Land use and land cover (LULC) change is frequent in mountainous terrain of southern China. Although remote sensing technology has become an important tool for gathering and monitoring LULC dynamics, image pairs can occur scale changes, noises, geometrical distortions and illuminated variations if these are acquired from different types of sensors (e.g., satellites). Meanwhile, how to design an efficient land cover change detection algorithm that ensures a high detection rate remains a critical and challenging step. To address these problems, we propose a robust multi-temporal change detection framework for land cover change in mountainous terrain which contains the following contributions. (i) To transform multi-temporal remote sensing image pairs acquired by different type of sensors into the same coordinate system by image registration, a multi-scale feature description is generated using layers formed via a pretrained VGG network. (ii) A gradually increasing selection of inliers is defined for improving the robustness of feature points registration, and L2-minimizing estimate (L2E) based energy optimization is formulated to calculate a reasonable position in a reproducing kernel Hilbert space. (iii) Fuzzy CMeans classifier is adopted to generate a similarity matrix between image pair of geometric correction, and a robust and contractive change map is built through feature similarity analysis. Extensive experiments on multi-temporal image pairs taken by different type of satellites (e.g., Chinese GF, Landsat) or small unmanned aerial vehicles (UAVs) are conducted. Experimental results show that our method provides better performances in most cases after comparing with five state-of-the-art image registration methods and four state-of-the-art change detection methods.

Land degradation, soil erosion and illegal occupation in mountainous terrain of southern China have led to an ever-decreasing stock of cultivated land. Small unmanned aerial vehicles (UAVs) are used to collect images with very fine spatial and temporal resolutions. However, acquired image pairs of the same scene often contain scale changes, noises and rotated changes at different temporal scales. To address these problems, we propose a small UAV-based multi-temporal change detection for cultivated land cover in mountainous terrain which contains the following contributions. First, the multi-scale feature description includes convolutional neural network (CNN)-based feature descriptor (CFD) and neighbouring structure descriptor (NSD), where CFD is generated using layers formed via a pretrained Visual Geometry Group (VGG)-16 architecture. Second, a gradually increasing selection of inliers is defined for improving the robustness of feature point registration. Finally, intuitionistic fuzzy C-Means (IFCM) classifier is adopted to generate a similarity matrix between image pair of geometric correction process. The performance of proposed method is validated on multi-temporal image pairs taken by the small UAV. Experimental results show that the proposed method can detect cultivated land cover change at small size and scattered distribution landscapes, obtain satisfactory change detection results.

In airport ground-traffic surveillance systems, the detection of an aircraft and its head (AIH) is an important task in aircraft trajectory judgment. However, accurately detecting an AIH in high-resolution optical remote sensing images is a challenging task due to the difficulty in effectively modeling the features of aircraft objects, such as changes in appearance, large-scale differences, complex compositions, and cluttered background. In this paper, we propose an end-to-end rotated aircraft and aircraft head detector (RAIH-Det) based on ConvNeXt-T (Tiny) and cyclical local loss. Firstly, a new U-shaped network based on ConvNeXt-T with the same performance as the Local Vision Transformer (e.g., Swin Transformer) is presented to assess the relationships among aircraft in the spatial domain. Then, in order to enhance the sharing of more mutual information, the extended BBAVectors with six vectors captures the oriented bounding box (OBB) of the aircraft in any direction, which can assist in head keypoint detection by exploiting the relationship between the local and overall structural information of aircraft. Simultaneously, variant cyclical focal loss is adopted to regress the heatmap location of keypoints on the aircraft head to focus on more reliable samples. Furthermore, to perform a study on AIH detection and simplify aircraft head detection, the OBBs of the “plane” category in the DOTA-v1.5 dataset and the corresponding head keypoints annotated by our volunteers were integrated into a new dataset called DOTA-Plane. Compared with other state-of-the-art rotated object and keypoint detectors, RAIH-Det, as evaluated on DOTA-Plane, offered superior performance.

Visual inspection of the workplace and timely reminders of unsafe behaviors (e.g, not wearing a helmet) are particularly significant for avoiding injuries to workers on the construction site. Video surveillance systems generate large amounts of non-structure image data on site for this purpose; however, they require real-time recognition automation solutions based on computer vision. Although various deep-learning-based models have recently provided new ideas for identifying helmets in traffic monitoring, few solutions suitable for industry applications have been discussed due to the complex scenarios of construction sites. In this paper, a fast and robust network based on a mutilscale Swin Transformer is proposed for safety helmet detection (FRSHNet) at construction sites, which contains the following contributions. Firstly, MAE-NAS with the variant of MobileNetV3’s MobBlock as a basic block is applied to implement feature extraction. Simultaneously, a multiscale Swin Transformer module is utilized to obtain the spatial and contexture relationships in the multiscale features. Subsequently, in order to meet the scheme requirements of real-time helmet detection, efficient RepGFPN are adopted to integrate refined multiscale features to form a pyramid structure. Extensive experiments were conducted on the publicly available Pictor-v3 and SHWD datasets. The experimental results show that FRSHNet consistently provided a favorable performance, outperforming the existing state-of-the-art models.