logo
    Monocular ORB-SLAM Application in Underwater Scenarios
    18
    Citation
    12
    Reference
    10
    Related Paper
    Citation Trend
    Abstract:
    This paper presents an experimental evaluation of monocular ORB-SLAM applied to underwater scenarios. It is investigated as an alternative SLAM method with minimal instumentation compared to other approaches that integrate different sensors such as inertial and acoustic sensors. ORB-SLAM creates a 3D map based on image frames and estimates the position of the robot by using a feature-based front-end and a graph-based back-end. The performance of ORB-SLAM is evaluated through experiments in different settings with varying lighting, visibility and water dynamics. Results show good performance given the right conditions and demonstrate that ORB-SLAM can work well in the underwater environment. Based on our findings the paper outlines possible enhancements which should further improve on the algorithms performance.
    Keywords:
    Orb (optics)
    Monocular
    Visibility
    Position (finance)
    Feature (linguistics)
    This paper describes in a detailed manner a method to implement a simultaneous localization and mapping (SLAM) system based on monocular vision for applications of visual odometry, appearance‐based sensing, and emulation of range‐bearing measurements. SLAM techniques are required to operate mobile robots in a priori unknown environments using only on‐board sensors to simultaneously build a map of their surroundings; this map will be needed for the robot to track its position. In this context, the 6‐DOF (degree of freedom) monocular camera case (monocular SLAM) possibly represents the harder variant of SLAM. In monocular SLAM, a single camera, which is freely moving through its environment, represents the sole sensory input to the system. The method proposed in this paper is based on a technique called delayed inverse‐depth feature initialization, which is intended to initialize new visual features on the system. In this work, detailed formulation, extended discussions, and experiments with real data are presented in order to validate and to show the performance of the proposal.
    Monocular
    Initialization
    Visual Odometry
    Feature (linguistics)
    Odometry
    Citations (19)
    Vision-based Simultaneous Localisation and Mapping (Visual SLAM) is a new hot topic in intelligent robotic applications. A new method for the implementation of a visual SLAM system with monocular vision is proposed in this paper. The general framework of our system is first displayed, and then all the main sub-processes are described step by step. In our design we use the ORB feature to represent each natural landmark with an improved map management and modified covariance extended Kalman filter (MVEKF) to estimate the 6D pose of a free-moving camera. In order to validate and demonstrate the performance of the system, some related experiments are carried out. The experimental results show that our method is feasible, robust and efficient.
    Orb (optics)
    Monocular
    Monocular vision
    Feature (linguistics)
    Landmark
    Citations (3)
    In this paper, we propose an underwater object detection method using monocular vision sensors. In addition to commonly used visual features such as color and intensity, we investigate the potential of underwater object detection using light transmission information. The global contrast of various features is used to initially identify the region of interest (ROI), which is then filtered by the image segmentation method, producing the final underwater object detection results. We test the performance of our method with diverse underwater datasets. Samples of the datasets are acquired by a monocular camera with different qualities (such as resolution and focal length) and setups (viewing distance, viewing angle, and optical environment). It is demonstrated that our ROI detection method is necessary and can largely remove the background noise and significantly increase the accuracy of our underwater object detection method.
    Monocular
    Monocular vision
    Region of interest
    Citations (64)
    Most of the monocular visual odometry approaches are based on feature algorithms.However, not all the feature point is necessarily favorable for the matching process. In this paper weaddress novel technique of ORB as feature point detection to achieve real time necessity. We propose amethod which is precise and real time which generate multiple views with spatial angles. We generate adataset using Intel T265 camera and implements Monocular visual odometry with the help of variousfeature detection/matching algorithms to estimate the performance in indoor and outdoor environment,respectively. We demonstrate that how various image matching and detection algorithms works fordifferent environment.
    Visual Odometry
    Monocular
    Feature (linguistics)
    Odometry
    Orb (optics)
    Feature Matching
    Tracking (education)
    Citations (0)
    Monocular visual simultaneous localization and mapping (SLAM) performs effectively in camera pose estimation and 3D sparse reconstruction of natural scenes. However, in monocular endoscopic environment, serious distortion of the images and the inconstant illumination, even the lack of surface texture, make SLAM-based tracking and 3D dense reconstruction still a challenge. In response to the above problems, it is proposed to use local features to match adjacent frames in ORB-SLAM system for the endoscopic poses estimation and keyframes selection, then combined with the probabilistic monocular stereo technology to calculate the dense depth map from keyframes, and finally complete the 3D dense reconstruction of the endoscopic scene. The experimental results proved that this method can track the endoscope robustly and reconstruct a 3D point cloud with high density and smoothness.
    Monocular
    Bundle adjustment
    3D Reconstruction
    Tracking (education)
    Orb (optics)
    The development of monocular visual simultaneous localization and mapping (VSLAM) has slowly begun in recent years. At present, the sensors used for VSLAM include monocular, binocular, or depth. For visual mapping, two problems will be encountered and the mapping cannot be performed. One is when there are not enough feature points, the camera's pose at the next moment cannot be estimated, such as a wall. The other is the VSLAM of dynamic environment changes may not be recognized as the same object because the feature matching needs to be coded through its surrounding environment, so it is easy to lose track when encountering changes in light. Compared with binocular and depth, monocular vision lacks depth information, but because it is cheap and easy to install, it needs to be used by multiple people. The current research proposes adding other information, including the camera height, the scene of the reference object and depth estimation by learning methods. The study uses the OpenVSLAM architecture to estimate the camera height scale, and proposes the mechanism be based on the change in the average scale of the first five key frames, with the average scale being updated at the same time to correct the current scale. Through this method, the drastic changes in scale are corrected, and the accuracy of trajectory positioning is improved. We also evaluate our proposed method on a real KITTI Dataset and demonstrate the proposed algorithm is effective and feasible for monocular visual SLAM.
    Visual Odometry
    Monocular
    Feature (linguistics)
    Monocular vision
    Bundle adjustment
    Feature Matching
    Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.
    Monocular
    Parallax
    Monocular vision
    Tracking (education)
    Bundle adjustment
    Citations (13)
    [abstFig src='/00280004/06.jpg' width='300' text='Monocular Visual Localization in Tsukuba Challenge 2015. Left: result of localization inside the map created by ORB-SLAM. Right: position tracking at starting point.' ] For the 2015 Tsukuba Challenge, we realized an implementation of vision-based localization based on ORB-SLAM. Our method combined mapping based on ORB-SLAM and Velodyne LIDAR SLAM, and utilized these maps in a localization process using only a monocular camera. We also apply sensor fusion method of odometer and ORB-SLAM from all maps. The combined method delivered better accuracy than the original ORB-SLAM, which suffered from scale ambiguities and map distance distortion. This paper reports on our experience when using ORB-SLAM for visual localization, and describes the difficulties encountered.
    Orb (optics)
    Odometer
    Monocular
    Bundle adjustment
    Citations (36)
    In recent years some direct monocular SLAM methods have appeared achieving impressive semi-dense or dense 3D scene reconstruction. At the same time, feature-based monocular SLAM methods can obtain more accurate trajectory than direct methods, but only obtain sparse feature point map rather than semi-dense or even dense map like direct methods. With the development of deep learning, it becomes possible to predict the depth map of a scene given a single RGB image. In this paper we demonstrate how depth prediction module via deep learning can be used as a plug-in module in highly accurate feature-based monocular SLAM (e.g. ORB-SLAM). Both accurate trajectory from ORB-SLAM and dense 3D reconstruction from depth prediction can be achieved. Evaluation results show that dense scene reconstruction can be obtained from highly accurate feature-based monocular SLAM.
    Monocular
    Feature (linguistics)
    Orb (optics)
    RGB color model