RGB-D sensors capture RGB images and depth images simultaneously, which makes it possible to acquire the depth information at pixel level. This paper focuses on the use of RGB-D sensors to construct a visual map which is an extended dense 3D map containing essential elements for image-based localization, such as poses of the database camera, visual features, and 3D structures of the building. Taking advantage of matched visual features and corresponding depth values, a novel local optimization algorithm is proposed to achieve point cloud registration and database camera pose estimation. Next, graph-based optimization is used to obtain the global consistency of the map. On the basis of the visual map, the image-based localization method is investigated, making use of the epipolar constraint. The performance of the visual map construction and the image-based localization are evaluated on typical indoor scenes. The simulation results show that the average position errors of the database camera and the query camera can be limited to within 0.2 meters and 0.9 meters, respectively.

Visual localization is employed for indoor navigation and embedded in various applications, such as augmented reality and mixed reality. Image retrieval and geometrical measurement are the primary steps in visual localization, and the key to improving localization efficiency is to reduce the time consumption of the image retrieval. Therefore, a hierarchical clustering-based image-retrieval method is proposed to hierarchically organize an off-line image database, resulting in control of the time consumption of image retrieval within a reasonable range. The image database is hierarchically organized by two stages: scene-level clustering and sub-scene-level clustering. In scene-level clustering, an improved cumulative sum algorithm is proposed to detect change points and then group images by global features. On the basis of scene-level clustering, a feature tracking-based method is introduced to further group images into sub-scene-level clusters. An image retrieval algorithm with a backtracking mechanism is designed and applied for visual localization. In addition, a weighted KNN-based visual localization method is presented, and the estimated query position is solved by the Armijo–Goldstein algorithm. Experimental results indicate that the running time of image retrieval does not linearly increase with the size of image databases, which is beneficial to improving localization efficiency.

Recently, monocular localization has attracted increased attention due to its application to indoor navigation and augmented reality. In this paper, a drift-aware monocular localization system that performs global and local localization is presented based on a pre-constructed dense three-dimensional (3D) map. In global localization, a pixel-distance weighted least squares algorithm is investigated for calculating the absolute scale for the epipolar constraint. To reduce the accumulative errors that are caused by the relative position estimation, a map interaction-based drift detection method is introduced in local localization, and the drift distance is computed by the proposed line model-based maximum likelihood estimation sample consensus (MLESAC) algorithm. The line model contains a fitted line segment and some visual feature points, which are used to seek inliers of the estimated feature points for drift detection. Taking advantage of the drift detection method, the monocular localization system switches between the global and local localization modes, which effectively keeps the position errors within an expected range. The performance of the proposed monocular localization system is evaluated on typical indoor scenes, and experimental results show that compared with the existing localization methods, the accuracy improvement rates of the absolute position estimation and the relative position estimation are at least 30.09% and 65.59%, respectively.

In the global outbreak of corona-virus disease (COVID-19), it is of foremost priority to find an efficient and faster diagnosis method to reduce the transmission rate of the COVID-19 disease. Recently, deep learning-based detection methods have been proposed as a potential diagnostic tool, because there is much essential information in the radio-logical images for COVID-19 detection. This paper intends to develop a hybrid deep neural network (COVID19-ResCapsNet), using the X-ray images, to predict the risk at the onset of disease in patients suffering from COVID-19. The proposed COVID19-ResCapsNet method consists of two steps. The first step is mainly to extract features with the improved Residual feature extraction network. In the final step, several Capsule Networks are employed to classify COVID-19, and Non COVID-19. The proposed method is evaluated on two CXR image datasets(Dataset-1: 4236 images and Dataset-2: 2250 images) and the classification accuracy can reach 0.9988 on Dataset-1 and 0.9933 on Dataset-2 for binary classification cases. The results are compared with several state-of-the-art pre-trained classification models. The effects of two important hyper parameters: different optimizer and batch size, have also been investigated. Hence, the proposed COVID-19 detection model is effective and can be used as the supplementary tool in clinical application.