Breast tumor segmentation of ultrasound images provides valuable tumor information for early detection and diagnosis. However, speckle noise and blurred boundaries in breast ultrasound images present challenges for tumor segmentation, especially for malignant tumors with irregular shapes. Recent vision transformers have shown promising performance in handling the variation through global context modeling. Nevertheless, they are often dominated by features of large patterns and lack the ability to recognize negative information in ultrasound images, which leads to the loss of breast tumor details (e.g., boundaries and small objects). In this paper, we propose a novel noise suppression and boundary refinement network, NSBR-Net, to simultaneously alleviate speckle noise interference and blurred boundary problems of breast tumor segmentation. Specifically, we propose two innovative designs, namely, the Noise Suppression Module (NSM) and the Boundary Refinement Module (BRM). The NSM filters noise information from the coarse-grained feature maps, while the BRM progressively refines the boundaries of significant lesion objects. Our method demonstrates superior accuracy over state-of-the-art deep learning models, achieving significant improvements of 3.67% on Dataset B and 2.30% on the BUSI dataset in mDice for testing malignant tumors.

Cross-view geo-localization (CVGL) aims to match images of the same location captured from different viewpoints, such as those captured by Unmanned Aerial Vehicles (UAVs) and satellite platforms. The task is particularly challenging due to significant variations in scale, viewpoint, and illumination. Most existing methods employ symmetric sampling strategy to construct drone–satellite image pairs for deep metric learning, but neglect the potential of incorporating multi-view drone images to enhance the viewpoint robustness of features. To address this, we propose leveraging multi-view images to learn Domain-Invariant Discriminative Embeddings (DIDE) for CVGL. DIDE introduces an Inter-view Feature Aggregation Module (IFAM), which dynamically integrates multi-view drone information into robust embeddings. These are used in contrastive learning with satellite embeddings within batches to learn view-invariant discriminative features, while representation learning further improves scene discrimination across batches. To reduce the domain gap, DIDE constructs and aligns drone and satellite prototypes for effective cross-domain feature alignment. Furthermore, we adopt a parameter-efficient transfer learning strategy that leverages the capabilities of pre-trained foundation models while fine-tuning only dual adapters, significantly reducing the trainable parameters. DIDE achieves the state-of-the-art on University-1652 and University-160k, competitive results on SUES-200, and demonstrates strong cross-dataset transferability, with fewer training parameters and lower computational cost.

Deep learning (DL)-based point cloud segmentation methods have been extensively explored, but the majority focus either on local or global feature learning, with few integrating both. These integrated approaches have not been sufficiently explored in complex mountainous scenes with low feature heterogeneity. To address this gap, we propose a novel point-based multiscale spatial Convolution-Swin Transformer network (Point-SCT). Point-SCT combines convolutional local geometric detail capture with global relationship modeling via dynamic window interactions in Transformer, enhancing ground filtering accuracy in challenging mountainous scenes. The encoder incorporates a convolution-based multiscale local feature aggregation (MLFA) approach, integrating local geometric feature encoding local geometric structure encoding (LGSE) and diluent pooling (DP) strategies to effectively aggregate local detailed geometric features while suppressing irrelevant feature vectors and enhancing the representation of low-heterogeneity feature. Additionally, the dynamic spatial window strategy within the Transformer facilitates the capture of long-range feature dependencies. To mitigate noise introduced by RGB in point cloud overlays and sharpen geometric distinctions between the ground and low-lying vegetation, we introduce boundary detector, curvature, and average elevation (BCE) as prior inputs, replacing RGB. Finally, quantitative and qualitative analyses of Point-SCT are conducted on an airborne laser scanning (ALS) dataset from a mountainous area, with ablation studies validating the effectiveness of LGSE, DP, and BCE. The comprehensive experiments demonstrate that Point-SCT robustly segments ground points in complex mountainous scenes, achieving state-of-the-art levels of accuracy and generalization.

This paper introduces an efficient and highly accurate framework for generating precise trajectories to evaluate the performance of SLAM (Simultaneous Localization and Mapping) algorithms. Traditional methods for acquiring high-precision SLAM trajectories typically rely on external high-accuracy trajectory references, such as RTK-GPS or motion capture cameras. However, obtaining high-precision trajectories through conventional means in GPS-denied indoor environments or large underground settings poses a significant challenge. To address this issue, we propose a method of high-precision point cloud matching to calibrate lower-precision point clouds, supplemented by contextual consistency optimization for efficient and accurate trajectory acquisition. We demonstrate the robustness and generalizability of our method using our own dataset, LIVOX-Indoor, with experimental evaluation results showing millimeter-level accuracy.

This paper presents an advanced method for the reliable detection of failures and online calibration of airborne LiDARs and cameras in photogrammetric mapping of remote sensing imagery capture scenarios. Traditional calibration methods without targets typically depend on aligning the spatial structures of LiDAR data with texture features, but acquiring dense LiDAR data for matching and optimization in a short amount of time is challenging in real-time operations. In response to this issue, this paper proposes an image feature encoding method designed to dynamically guide the matching of LiDAR feature points, while simultaneously employing context consistency estimation for additional optimization. Importantly, our method can perceive and recalibrate extrinsic errors in real-time scenarios within natural environments, thereby enhancing the robustness of the calibration. The effectiveness and adaptability of our method are demonstrated using our unique airborne LiDAR-based LIVOX-Airborne datasets, which set a new benchmark in both numerical variability and pixel discrepancy, showcasing a variance of $5.05\times 10^{-4}$ and a mean error of 0.86 pixels.