Semantic change detection (SCD) has gradually emerged as a prominent research focus in remote sensing image processing due to its critical role in earth observation applications. In view of its powerful semantic-driven feature extraction capability, the Segment Anything Model (SAM) has demonstrated its suitability across various visual scenes. However, it suffers from significant performance degradation when confronted with remote sensing images, especially those containing various ground objects that possess significant inter-class similarity and substantial intra-class variations. To address the above issues, we propose SCD-SAM, aiming to leverage the potent visual recognition capabilities of SAM for enhanced accuracy and robustness in SCD. Specifically, we introduce a contextual semantic change-aware dual encoder that combines MobileSAM and CNN to extract progressive semantic change features in parallel, and inject local features into the MobileSAM encoder through depth feature interaction to compensate for the Transformer’s limitations in perceiving local semantic details. Besides, in order to utilize the strong visual feature extraction capability of MobileSAM in remote sensing images, we propose a semantic adaptor that aggregates semantic-oriented information about changing objects. To better integrate the extracted contextual semantic information, we devise a progressive feature aggregation dual decoder that aggregates binary change features and semantic change features respectively, alleviating the semantic gap across different scales. The quantitative and visual results show that SCD-SAM outperforms the state-of-the-art SCD methods on publicly open SCD datasets (e.g., SECOND-CD and Landsat-CD). The code will be made available at https://github.com/yzygit1230/SCD-SAM.

Building change detection (BCD) is essential for urban dynamic measurement. Deep learning has demonstrated significant potential in image processing, providing powerful feature extraction capabilities for BCD tasks. However, existing methods do not adequately mine multiscale feature information and ignore the importance of multiscale feature alignment, leading to an inadequate representation of the internal structure. Therefore, we propose a hybrid attention-aware transformer network (HATNet) designed to effectively extract and interact with multiscale context information. Specifically, HATNet first incorporates a hybrid attention-aware feature extractor (HAFE) module that integrates self-attention (SA) and coordinate-attention (CA) to effectively extract complementary multiscale features. The SA establishes long-range dependencies between multiscale features, while the CA captures spatial dependencies and preserves positional details. Then, we devise a building saliency detection enhancement (BSDE) module that utilizes three independent channels to facilitate the identification and localization of changed buildings, fostering a symbiotic relationship between unchanged and changed areas. Furthermore, we adopt a coarse-to-fine feature interaction (CFFI) module to progressively fuse multiscale features using a hierarchical strategy. In order to better locate the changed detail features, we introduce a global feature alignment (GFA) module to achieve global multiscale feature alignment. HATNet surpasses eight BCD methods on LEVIR-CD, WHU-CD, and S2Looking-CD datasets. The experimental results provide compelling evidence of our method to precisely detect and measure building changes. The codes are available at https://github.com/yzygit1230/HATNet .

Object detection is a challenging task in aerial images, where many objects have large aspect ratios and are densely arranged. Most anchor-based rotating detectors assign anchors for ground-truth objects by a fixed restriction of the rotation Intersection-over-Unit $(IoU)$ between anchors and objects, which directly follow horizontal detectors. Due to many directional objects with a large aspect ratio, the object-anchor $IoU$ is heavily influenced by the angle, which may cause few anchors assigned for some ground-truth objects. In this study, we propose an anchor selection method based on sample balance assigning anchors adaptively, which we name the Self-Adaptive Anchor Selection ($A^2$S-Det) method. For each ground-truth object, $A^2$S-Det selects a set of candidate anchors by horizontal $IoU$. Then, an adaptive threshold module is adopted on the set of candidate anchors, which calculates a boundary of these candidate anchors aiming to keep a balance between positive and negative anchors. In addition, we propose a coordinate regression of relative reference ($C{R}^3$) module to precisely regress the rotating bounding box. We test our method on a public aerial image dataset, and prove better performance than many other one-stage detectors and two-stage detectors, achieving the $mAP$ of 70.64. An efficiency anchor matching method helps the detector achieve better performance for objects with large aspect ratios.

In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood correlation image analyses are performed to highlight pixels with high probabilities of being changed or unchanged, which can be used as a prerequisite for object-based analyses. Third, based on the coarse-to-fine segmentation and pixel-based pre-classification results, change possibilities are calculated for various objects. Furthermore, changed and unchanged objects identified at different scales are automatically selected to serve as training samples. The spectral and texture features of each object are extracted. Finally, uncertain objects are classified using the RoF classifier. Multi-scale classification results are combined using a majority voting rule to generate the final CD results. In experiments using two pairs of real high-resolution remote sensing datasets, our proposed approach outperformed existing methods in terms of CD accuracy, verifying its feasibility and effectiveness.

The object detection in UAV application is a challenging task due to the diversity of target scales, variation of views and complex backgrounds. To solve several challenges, including dense objects, objects with arbitrary orientation and diversity of aspect ratios, this paper proposes an end-to-end object detection method based on the convolutional neural network. In this paper, the feature extraction performance is enhanced by utilizing a deep residual neural network. Multi-scale feature maps are obtained through fusion with different convolutional layers, thus combining the high-level semantic information and low-level detail information. Rotation Region Proposal Network is adopted to generate rotated regions, which makes the bounding box sensitive to dense objects in aerial images. Meanwhile, the RoIAlign is used and a convolution layer is appended in the classification stage. And Focal loss is used in the classification stage. The proposed method focuses on arbitrary-oriented and dense objects in UAV images. After a comprehensive evaluation with several state-of-the-art object detection algorithms, the proposed method is proved to be effective to detect multi-class artificial objects in aerial images. Extensive experiments are conducted on the DOTA, VEDAI and the VisDrone UAV image datasets, which demonstrate that the proposed method can obtain discriminative features through the improved multi-scale feature extraction and the rotating region network. The results on the above datasets show that our method obtains gains in mAP compared with several state-of-the-art methods.

To solve the matching problems caused by the large intensity difference between the multi-source images and the nonlinear radiation distortion, we present a multi-source image matching approach that considers the orientation of the phase sharpness. First, the scale-space of the image pyramid was constructed, and the phase consistency of the image frequency domain was solved to obtain the maximum moment feature, and the KAZE operator is used to extract the feature points. Next, the Log-Gabor even symmetric filter was used to perform Fourier transform, and the improved local phase sharpness feature and phase orientation feature were constructed respectively to replace the gradient amplitude and gradient direction feature of the image. A descriptor of local phase sharpness orientation (LPSO) was established through the log-polar description template, and finally the Euclidean distance was used to measure the similarity to obtain the corresponding points. Multiple sets of typical multi-source images were used as data sources, and the LPSO algorithm was compared with SIFT, LGHD, RIFT and HAPCG algorithms in datasets. Evaluation of the algorithm performances indicates that the proposed method is more accurate and robust in the task of multi-source image matching.