Advancements in robotics and mapping technology have spotlighted the development of Simultaneous Localization and Mapping (SLAM) systems as a key research area. However, the high cost of advanced SLAM systems poses a significant barrier to research and development in the field, while many low-cost SLAM systems, operating under resource constraints, fail to achieve high-precision real-time mapping and localization, rendering them unsuitable for practical applications. This paper introduces a cost-effective SLAM system design that maintains high performance while significantly reducing costs. Our approach utilizes economical components and efficient algorithms, addressing the high-cost barrier in the field. First, we developed a robust robotic platform based on a traditional four-wheeled vehicle structure, enhancing flexibility and load capacity. Then, we adapted the SLAM algorithm using the LiDAR-inertial Odometry framework coupled with the Fast Iterative Closest Point (ICP) algorithm to balance accuracy and real-time performance. Finally, we integrated the 3D multi-goal Rapidly exploring Random Tree (RRT) algorithm with Nonlinear Model Predictive Control (NMPC) for autonomous exploration in complex environments. Comprehensive experimental results confirm the system’s capability for real-time, autonomous navigation and mapping in intricate indoor settings, rivaling more expensive SLAM systems in accuracy and efficiency at a lower cost. Our research results are published as open access, facilitating greater accessibility and collaboration.

Recently, researchers have realized a number of achievements involving deep-learning-based neural networks for the tasks of segmentation and detection based on 2D images, 3D point clouds, etc. Using 2D and 3D information fusion for the advantages of compensation and accuracy improvement has become a hot research topic. However, there are no critical reviews focusing on the fusion strategies of 2D and 3D information integration based on various data for segmentation and detection, which are the basic tasks of computer vision. To boost the development of this research domain, the existing representative fusion strategies are collected, introduced, categorized, and summarized in this paper. In addition, the general structures of different kinds of fusion strategies were firstly abstracted and categorized, which may inspire researchers. Moreover, according to the methods included in this paper, the 2D information and 3D information of different methods come from various kinds of data. Furthermore, suitable datasets are introduced and comparatively summarized to support the relative research. Last but not least, we put forward some open challenges and promising directions for future research.

With the expansion of model scale and the improvement of model accuracy, the real-time rendering and displaying of 3D mesh models remain infeasible. To relieve such pressure, mesh simplification methods have been proposed to reduce the structural complexity while preserving the appearance. This work introduces a shape-preserving simplification method for urban building models. Compared to traditional simplification methods that only consider preserving local geometric features, we also consider the overall shapes of building models to avoid collapse with an increased simplification rate. The proposed method works in four steps. First, we filter mesh models to yield planar structures while preserving sharp features. Second, we detect the shapes of planar regions. Third, we simplify the planar and non-planar regions constrained by the overall shapes and local geometric features. Finally, we remap the texture. Experiments show the effectiveness of this method by evaluating it on various building models and comparing its performance with the original QEM algorithms. Furthermore, we maintain better spatial consistency in building models with different levels of detail (LOD) than traditional methods.

With the progress of photogrammetry and computer vision technology, three-dimensional (3D) reconstruction using aerial oblique images has been widely applied in urban modelling and smart city applications. However, state-of-the-art image-based automatic 3D reconstruction methods cannot effectively handle the unavoidable geometric deformation and incorrect texture mapping problems caused by moving cars in a city. This paper proposes a method to address this situation and prevent the influence of moving cars on 3D modelling by recognizing moving cars and combining the recognition results with a photogrammetric 3D modelling procedure. Through car detection using a deep learning method and multiview geometry constraints, we can analyse the state of a car’s movement and apply a proper preprocessing method to the geometrically model generation and texture mapping steps of 3D reconstruction pipelines. First, we apply the traditional Mask R-CNN object detection method to detect cars from oblique images. Then, a detected car and its corresponding image patch calculated by the geometry constraints in the other view images are used to identify the moving state of the car. Finally, the geometry and texture information corresponding to the moving car will be processed according to its moving state. Experiments on three different urban datasets demonstrate that the proposed method is effective in recognizing and removing moving cars and can repair the geometric deformation and error texture mapping problems caused by moving cars. In addition, the methods proposed in this paper can be applied to eliminate other moving objects in 3D modelling applications.

Although great success has been achieved in instance segmentation, accurate segmentation of instances remains difficult, especially at object edges. This problem is more prominent for instance segmentation in remote sensing imagery due to the diverse scales, variable illumination, smaller objects, and complex backgrounds. We find that most current instance segmentation networks do not consider the segmentation difficulty of different instances and different regions within the instance. In this paper, we study this problem and propose an ensemble method to segment instances from remote sensing images, considering the enhancement of hard-to-segment instances and instance edges. First, we apply a pixel-level Dice metric that reliably describes the segmentation quality of each instance to achieve online hard instance learning. Instances with low Dice values are studied with emphasis. Second, we generate a penalty map based on the analysis of boundary shapes to not only enhance the edges of objects but also discriminatively strengthen the edges of different shapes. That is, different areas of an object, such as internal areas, flat edges, and sharp edges, are distinguished and discriminatively weighed. Finally, the hard-to-segment instance learning and the shape-penalty map are integrated for precise instance segmentation. To evaluate the effectiveness and generalization ability of the proposed method, we train with the classic instance segmentation network Mask R-CNN and conduct experiments on two different types of remote sensing datasets: the iSAID-Reduce100 and the JKGW_WHU datasets, which have extremely different feature distributions and spatial resolutions. The comprehensive experimental results show that the proposed method improved the segmentation results by 2.78% and 1.77% in mask AP on the iSAID-Reduce100 and JKGW_WHU datasets, respectively. We also test other state-of-the-art (SOTA) methods that focus on inaccurate edges. Experiments demonstrate that our method outperforms these methods.