This study presents a new end-to-end change detection network, called difference-enhancement dense-attention convolutional neural network (DDCNN), that is designed for detection of changes in the bitemporal optical remote sensing images. To model the internal correlation between high-level and low-level features, a dense attention method consisting of several up-sampling attention units is proposed. Both the up-sampling spatial and up-sampling channel attention are adopted by the unit. The unit, which can use high-level features with rich category information to guide the selection of low-level features, can use the spatial context information to capture the changed features of ground objects. Furthermore, DDCNN also pays attention to the differentiating features of the bitemporal images. By introducing a DE unit, each pixel is weighted and the features are selectively aggregated. The combination of dense attention and the DE unit improves the effectiveness of the network and its accuracy in extracting the change features. The effectiveness of the proposed approach is demonstrated via five challenge data sets. The experimental results show that DDCNN achieves new state-of-the-art change detection performance on these five challenging data sets. For the seasonal change detection data set in particular, compared with the best existing change detection model, the proposed method increases the F1 score and IoU by 2.96% and 5.17%, respectively; compared with the baseline method, our method improved 3.75% and 6.50% on the F1 score and IoU, respectively.

The common statistical methods for rail tunnel deformation and disease detection usually require a large amount of equipment and manpower to achieve full section detection, which are time consuming and inefficient. The development trend in the industry is to use laser scanning for full section detection. In this paper, a design scheme for a tunnel monitoring and measuring system with laser scanning as the main sensor for tunnel environmental disease and deformation analysis is proposed. The system provides functions such as tunnel point cloud collection, section deformation analysis, dislocation analysis, disease extraction, tunnel and track image generation, roaming video generation, etc. Field engineering indicated that the repeatability of the convergence diameter detection of the system can reach ±2 mm, dislocation repeatability can reach ±3 mm, the image resolution is about 0.5 mm/pixel in the ballast part, and the resolution of the inner wall of the tunnel is about 1.5 mm/pixel. The system can include human–computer interaction to extract and label diseases or appurtenances and support the generation of thematic disease maps. The developed system can provide important technical support for deformation and disease detection of rail transit tunnels.

Synthetic aperture radar (SAR) satellites produce large quantities of remote sensing images that are unaffected by weather conditions and, therefore, widely used in marine surveillance. However, because of the hysteresis of satellite-ground communication and the massive quantity of remote sensing images, rapid analysis is not possible and real-time information for emergency situations is restricted. To solve this problem, this paper proposes an on-board ship detection scheme that is based on the traditional constant false alarm rate (CFAR) method and lightweight deep learning. This scheme can be used by the SAR satellite on-board computing platform to achieve near real-time image processing and data transmission. First, we use CFAR to conduct the initial ship detection and then apply the You Only Look Once version 4 (YOLOv4) method to obtain more accurate final results. We built a ground verification system to assess the feasibility of our scheme. With the help of the embedded Graphic Processing Unit (GPU) with high integration, our method achieved 85.9% precision for the experimental data, and the experimental results showed that the processing time was nearly half that required by traditional methods.

Reconstructing building models at different levels of detail (LoDs) from airborne laser scanning point clouds is urgently needed for wide application as this method can balance between the user’s requirements and economic costs. The previous methods reconstruct building LoDs from the finest 3D building models rather than from point clouds, resulting in heavy costs and inflexible adaptivity. The scale space is a sound theory for multi-scale representation of an object from a coarser level to a finer level. Therefore, this paper proposes a novel method to reconstruct buildings at different LoDs from airborne Light Detection and Ranging (LiDAR) point clouds based on an improved morphological scale space. The proposed method first extracts building candidate regions following the separation of ground and non-ground points. For each building candidate region, the proposed method generates a scale space by iteratively using the improved morphological reconstruction with the increase of scale, and constructs the corresponding topological relationship graphs (TRGs) across scales. Secondly, the proposed method robustly extracts building points by using features based on the TRG. Finally, the proposed method reconstructs each building at different LoDs according to the TRG. The experiments demonstrate that the proposed method robustly extracts the buildings with details (e.g., door eaves and roof furniture) and illustrate good performance in distinguishing buildings from vegetation or other objects, while automatically reconstructing building LoDs from the finest building points.

Scan matching, an approach to recover the relative position and orientation of two laser scans, is a very important technique for indoor positioning and indoor modeling. The iterative closest point (ICP) algorithm and its variants are the most well-known techniques for such a problem. However, ICP algorithms rely highly on the initial guess of the relative transformation, which will reduce its power for practical applications. In this paper, an initial-free 2D laser scan matching method based on point and line features is proposed. We carefully design a framework for the detection of point and line feature correspondences. First, distinct feature points are detected based on an extended 1D SIFT, and line features are extracted via a modified Split-and-Merge algorithm. In this stage, we also give an effective strategy for discarding unreliable features. The point and line features are then described by a distance histogram; the pairs achieving best matching scores are accepted as potential correct correspondences. The histogram cluster technique is adapted to filter outliers and provide an accurate initial value of the rigid transformation. We also proposed a new relative pose estimation method that is robust to outliers. We use the lq-norm (0 < q < 1) metric in this approach, in contrast to classic optimization methods whose cost function is based on the l₂-norm of residuals. Extensive experiments on real data demonstrate that the proposed method is almost as accurate as ICPs and is initial free. We also show that our scan matching method can be integrated into a simultaneous localization and mapping (SLAM) system for indoor mapping.

Accurate and efficient extraction of road marking plays an important role in road transportation engineering, automotive vision, and automatic driving. In this article, we proposed a dense feature pyramid network (DFPN)-based deep learning model, by considering the particularity and complexity of road marking. The DFPN concatenated its shallow feature channels with deep feature channels so that the shallow feature maps with high resolution and abundant image details can utilize the deep features. Thus, the DFPN can learn hierarchical deep detailed features. The designed deep learning model was trained end to end for road marking instance extraction with mobile laser scanning (MLS) point clouds. Then, we introduced the focal loss function into the optimization of deep learning model in road marking segmentation part, to pay more attention to the hard-classified samples with a large extent of background. In the experiments, our method can achieve better results than state-of-the-art methods on instance segmentation of road markings, which illustrated the advantage of the proposed method.