Abstract:The traditional visual SLAM systems take the monocular or stereo camera as input sensor, with complex map initialization and map point triangulation steps needed for 3D map reconstruction, which are easy to fail, computationally complex and can cause noisy measurements. The emergence of RGB-D camera which provides RGB image together with depth information breaks this situation. While a number of RGB-D SLAM systems have been proposed in recent years, the current classification research on RGB-D SLAM is very lac… Show more
“…At present, for SLAM algorithms, RGB-D cameras have been introduced and three-dimensional maps can be created in real-time, and a variety of different RGB-D SLAM algorithms have been proposed. Most of these RGB-D SLAM are used for indoor localization and object dense reconstruction [9]. Mono SLAM [10] and ORB-SLAM2 [11] based on the feature point method can directly obtain the camera's pose in space and the sparse point cloud map, but the obtained map cannot be directly used for navigation.…”
Section: Slam (Simultaneous Localization and Mappingmentioning
In this paper, we extend RGB-D SLAM to address the problem that sparse map-building RGB-D SLAM cannot directly generate maps for indoor navigation and propose a SLAM system for fast generation of indoor planar maps. The system uses RGBD images to generate positional information while converting the corresponding RGBD images into 2D planar lasers for 2D grid navigation map reconstruction of indoor scenes under the condition of limited computational resources, solving the problem that the sparse point cloud maps generated by RGB-D SLAM cannot be directly used for navigation. Meanwhile, the pose information provided by RGB-D SLAM and scan matching respectively is fused to obtain a more accurate and robust pose, which improves the accuracy of map building. Furthermore, we demonstrate the function of the proposed system on the ICL indoor dataset and evaluate the performance of different RGB-D SLAM. The method proposed in this paper can be generalized to RGB-D SLAM algorithms, and the accuracy of map building will be further improved with the development of RGB-D SLAM algorithms.
“…At present, for SLAM algorithms, RGB-D cameras have been introduced and three-dimensional maps can be created in real-time, and a variety of different RGB-D SLAM algorithms have been proposed. Most of these RGB-D SLAM are used for indoor localization and object dense reconstruction [9]. Mono SLAM [10] and ORB-SLAM2 [11] based on the feature point method can directly obtain the camera's pose in space and the sparse point cloud map, but the obtained map cannot be directly used for navigation.…”
Section: Slam (Simultaneous Localization and Mappingmentioning
In this paper, we extend RGB-D SLAM to address the problem that sparse map-building RGB-D SLAM cannot directly generate maps for indoor navigation and propose a SLAM system for fast generation of indoor planar maps. The system uses RGBD images to generate positional information while converting the corresponding RGBD images into 2D planar lasers for 2D grid navigation map reconstruction of indoor scenes under the condition of limited computational resources, solving the problem that the sparse point cloud maps generated by RGB-D SLAM cannot be directly used for navigation. Meanwhile, the pose information provided by RGB-D SLAM and scan matching respectively is fused to obtain a more accurate and robust pose, which improves the accuracy of map building. Furthermore, we demonstrate the function of the proposed system on the ICL indoor dataset and evaluate the performance of different RGB-D SLAM. The method proposed in this paper can be generalized to RGB-D SLAM algorithms, and the accuracy of map building will be further improved with the development of RGB-D SLAM algorithms.
“…Moreover, the learning based methods are mostly trained and tested on data belonging the same domain, e.g. LiDAR data in outdoors, which cannot generalise well to other domains without retraining or finetuning, such as sparser point clouds reconstructed with vision-based SLAM systems [36]. Differently, our approach exploits advanced deep local 3D descriptors that are trained with point clouds extracted from RGBD sensors, estimates the 6DoF transformation between a pair of point clouds, and measures the overlap, serving for the loop closure detection task with little domain gap.…”
We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds). L3Ds are emerging compact representations of patches extracted from point clouds that are learned from data using a deep learning algorithm. We propose a novel overlap measure for loop detection by computing the metric error between points that correspond to mutually-nearest-neighbour descriptors after registering the loop candidate point cloud by its estimated relative pose. This novel approach enables us to accurately detect loops and estimate six degrees-of-freedom poses in the case of small overlaps. We compare our L3D-based loop closure approach with recent approaches on LiDAR data and achieve state-of-theart loop closure detection accuracy. Additionally, we embed our loop closure approach in RESLAM, a recent edge-based SLAM system, and perform the evaluation on real-world RGBD-TUM and synthetic ICL datasets. Our approach enables RESLAM to achieve a better localisation accuracy compared to its original loop closure strategy.
“…Zhang et al [11] give an overview of current RGB-D SLAM algorithms. The typical method for localizing the sensor pose in the TSDF is frame-to-model geometric ICP [1], where a back-projected point cloud from the previous position is used with the point-to-plane metric and Gauss Newton for minimizing the registration error.…”
Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping. The popular method of fusing depth information into a truncated signed distance function (TSDF) and applying the marching cubes algorithm for mesh extraction has severe issues with thin structures: not only does it lead to loss of accuracy, but it can generate completely wrong surfaces. To address this, we propose the directional TSDFa novel representation that stores opposite surfaces separate from each other. The marching cubes algorithm is modified accordingly to retrieve a coherent mesh representation. We further increase the accuracy by using surface gradient-based ray casting for fusing new measurements. We show that our method outperforms state-of-the-art TSDF reconstruction algorithms in mesh accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.