Automated Point Cloud Registration Approach Optimized for a Stop-and-Go Scanning System

The latest advances in mobile platforms, such as robots, have enabled the automatic acquisition of full coverage point cloud data from large areas with terrestrial laser scanning. Despite this progress, the crucial post-processing step of registration, which aligns raw point cloud data from separate local coordinate systems into a unified coordinate system, still relies on manual intervention. To address this practical issue, this study presents an automated point cloud registration approach optimized for a stop-and-go scanning system based on a quadruped walking robot. The proposed approach comprises three main phases: perpendicular constrained wall-plane extraction; coarse registration with plane matching using point-to-point displacement calculation; and fine registration with horizontality constrained iterative closest point (ICP). Experimental results indicate that the proposed method successfully achieved automated registration with an accuracy of 0.044 m and a successful scan rate (SSR) of 100% within a time frame of 424.2 s with 18 sets of scan data acquired from the stop-and-go scanning system in a real-world indoor environment. Furthermore, it surpasses conventional approaches, ensuring reliable registration for point cloud pairs with low overlap in specific indoor environmental conditions.

HeteroFusion: Dense Scene Reconstruction Integrating Multi-Sensors

We present a novel approach to integrate data from multiple sensor types for dense 3D reconstruction of indoor scenes in realtime. Existing algorithms are mainly based on a single RGBD camera and thus require continuous scanning of areas with sufficient geometric features. Otherwise, tracking may fail due to unreliable frame registration. Inspired by the fact that the fusion of multiple sensors can combine their strengths towards a more robust and accurate self-localization, we incorporate multiple types of sensors which are prevalent in modern robot systems, including a 2D range sensor, an inertial measurement unit (IMU), and wheel encoders. We fuse their measurements to reinforce the tracking process and to eventually obtain better 3D reconstructions. Specifically, we develop a 2D truncated signed distance field (TSDF) volume representation for the integration and ray-casting of laser frames, leading to a unified cost function in the pose estimation stage. For validation of the estimated poses in the loop-closure optimization process, we train a classifier for the features extracted from heterogeneous sensors during the registration progress. To evaluate our method on challenging use case scenarios, we assembled a scanning platform prototype to acquire real-world scans. We further simulated synthetic scans based on high-fidelity synthetic scenes for quantitative evaluation. Extensive experimental evaluation on these two types of scans demonstrate that our system is capable of robustly acquiring dense 3D reconstructions and outperforms state-of-the-art RGBD and LiDAR systems.

Distributed Architecture to Integrate Sensor Information: Object Recognition for Smart Cities

Object recognition, which can be used in processes such as reconstruction of the environment map or the intelligent navigation of vehicles, is a necessary task in smart city environments. In this paper, we propose an architecture that integrates heterogeneously distributed information to recognize objects in intelligent environments. The architecture is based on the IoT/Industry 4.0 model to interconnect the devices, which are called smart resources. smart resources can process local sensor data and offer information to other devices as a service. These other devices can be located in the same operating range (the edge), in the same intranet (the fog), or on the Internet (the cloud). smart resources must have an intelligent layer in order to be able to process the information. A system with two smart resources equipped with different image sensors is implemented to validate the architecture. Our experiments show that the integration of information increases the certainty in the recognition of objects by 2-4%. Consequently, in intelligent environments, it seems appropriate to provide the devices with not only intelligence, but also capabilities to collaborate closely with other devices.

Real-Time RGB-D Simultaneous Localization and Mapping Guided by Terrestrial LiDAR Point Cloud for Indoor 3-D Reconstruction and Camera Pose Estimation

In recent years, low-cost and lightweight RGB and depth (RGB-D) sensors, such as Microsoft Kinect, have made available rich image and depth data, making them very popular in the field of simultaneous localization and mapping (SLAM), which has been increasingly used in robotics, self-driving vehicles, and augmented reality. The RGB-D SLAM constructs 3D environmental models of natural landscapes while simultaneously estimating camera poses. However, in highly variable illumination and motion blur environments, long-distance tracking can result in large cumulative errors and scale shifts. To address this problem in actual applications, in this study, we propose a novel multithreaded RGB-D SLAM framework that incorporates a highly accurate prior terrestrial Light Detection and Ranging (LiDAR) point cloud, which can mitigate cumulative errors and improve the system’s robustness in large-scale and challenging scenarios. First, we employed deep learning to achieve system automatic initialization and motion recovery when tracking is lost. Next, we used terrestrial LiDAR point cloud to obtain prior data of the landscape, and then we applied the point-to-surface inductively coupled plasma (ICP) iterative algorithm to realize accurate camera pose control from the previously obtained LiDAR point cloud data, and finally expanded its control range in the local map construction. Furthermore, an innovative double window segment-based map optimization method is proposed to ensure consistency, better real-time performance, and high accuracy of map construction. The proposed method was tested for long-distance tracking and closed-loop in two different large indoor scenarios. The experimental results indicated that the standard deviation of the 3D map construction is 10 cm in a mapping distance of 100 m, compared with the LiDAR ground truth. Further, the relative cumulative error of the camera in closed-loop experiments is 0.09%, which is twice less than that of the typical SLAM algorithm (3.4%). Therefore, the proposed method was demonstrated to be more robust than the ORB-SLAM2 algorithm in complex indoor environments.

Fast 3D Semantic Mapping in Road Scenes

Fast 3D reconstruction with semantic information in road scenes is of great requirements for autonomous navigation. It involves issues of geometry and appearance in the field of computer vision. In this work, we propose a fast 3D semantic mapping system based on the monocular vision by fusion of localization, mapping, and scene parsing. From visual sequences, it can estimate the camera pose, calculate the depth, predict the semantic segmentation, and finally realize the 3D semantic mapping. Our system consists of three modules: a parallel visual Simultaneous Localization And Mapping (SLAM) and semantic segmentation module, an incrementally semantic transfer from 2D image to 3D point cloud, and a global optimization based on Conditional Random Field (CRF). It is a heuristic approach that improves the accuracy of the 3D semantic labeling in light of the spatial consistency on each step of 3D reconstruction. In our framework, there is no need to make semantic inference on each frame of sequence, since the 3D point cloud data with semantic information is corresponding to sparse reference frames. It saves on the computational cost and allows our mapping system to perform online. We evaluate the system on road scenes, e.g., KITTI, and observe a significant speed-up in the inference stage by labeling on the 3D point cloud.

Visual Information Fusion through Bayesian Inference for Adaptive Probability-Oriented Feature Matching

This work presents a visual information fusion approach for robust probability-oriented feature matching. It is sustained by omnidirectional imaging, and it is tested in a visual localization framework, in mobile robotics. General visual localization methods have been extensively studied and optimized in terms of performance. However, one of the main threats that jeopardizes the final estimation is the presence of outliers. In this paper, we present several contributions to deal with that issue. First, 3D information data, associated with SURF (Speeded-Up Robust Feature) points detected on the images, is inferred under the Bayesian framework established by Gaussian processes (GPs). Such information represents a probability distribution for the feature points’ existence, which is successively fused and updated throughout the robot’s poses. Secondly, this distribution can be properly sampled and projected onto the next 2D image frame in t+1, by means of a filter-motion prediction. This strategy permits obtaining relevant areas in the image reference system, from which probable matches could be detected, in terms of the accumulated probability of feature existence. This approach entails an adaptive probability-oriented matching search, which accounts for significant areas of the image, but it also considers unseen parts of the scene, thanks to an internal modulation of the probability distribution domain, computed in terms of the current uncertainty of the system. The main outcomes confirm a robust feature matching, which permits producing consistent localization estimates, aided by the odometer’s prior to estimate the scale factor. Publicly available datasets have been used to validate the design and operation of the approach. Moreover, the proposal has been compared, firstly with a standard feature matching and secondly with a localization method, based on an inverse depth parametrization. The results confirm the validity of the approach in terms of feature matching, localization accuracy, and time consumption.

Geometric Integration of Hybrid Correspondences for RGB-D Unidirectional Tracking

Traditionally, visual-based RGB-D SLAM systems only use correspondences with valid depth values for camera tracking, thus ignoring the regions without 3D information. Due to the strict limitation on measurement distance and view angle, such systems adopt only short-range constraints which may introduce larger drift errors during long-distance unidirectional tracking. In this paper, we propose a novel geometric integration method that makes use of both 2D and 3D correspondences for RGB-D tracking. Our method handles the problem by exploring visual features both when depth information is available and when it is unknown. The system comprises two parts: coarse pose tracking with 3D correspondences, and geometric integration with hybrid correspondences. First, the coarse pose tracking generates the initial camera pose using 3D correspondences with frame-by-frame registration. The initial camera poses are then used as inputs for the geometric integration model, along with 3D correspondences, 2D-3D correspondences and 2D correspondences identified from frame pairs. The initial 3D location of the correspondence is determined in two ways, from depth image and by using the initial poses to triangulate. The model improves the camera poses and decreases drift error during long-distance RGB-D tracking iteratively. Experiments were conducted using data sequences collected by commercial Structure Sensors. The results verify that the geometric integration of hybrid correspondences effectively decreases the drift error and improves mapping accuracy. Furthermore, the model enables a comparative and synergistic use of datasets, including both 2D and 3D features.

Enhanced RGB-D Mapping Method for Detailed 3D Indoor and Outdoor Modeling

RGB-D sensors (sensors with RGB camera and Depth camera) are novel sensing systems that capture RGB images along with pixel-wise depth information. Although they are widely used in various applications, RGB-D sensors have significant drawbacks including limited measurement ranges (e.g., within 3 m) and errors in depth measurement increase with distance from the sensor with respect to 3D dense mapping. In this paper, we present a novel approach to geometrically integrate the depth scene and RGB scene to enlarge the measurement distance of RGB-D sensors and enrich the details of model generated from depth images. First, precise calibration for RGB-D Sensors is introduced. In addition to the calibration of internal and external parameters for both, IR camera and RGB camera, the relative pose between RGB camera and IR camera is also calibrated. Second, to ensure poses accuracy of RGB images, a refined false features matches rejection method is introduced by combining the depth information and initial camera poses between frames of the RGB-D sensor. Then, a global optimization model is used to improve the accuracy of the camera pose, decreasing the inconsistencies between the depth frames in advance. In order to eliminate the geometric inconsistencies between RGB scene and depth scene, the scale ambiguity problem encountered during the pose estimation with RGB image sequences can be resolved by integrating the depth and visual information and a robust rigid-transformation recovery method is developed to register RGB scene to depth scene. The benefit of the proposed joint optimization method is firstly evaluated with the publicly available benchmark datasets collected with Kinect. Then, the proposed method is examined by tests with two sets of datasets collected in both outside and inside environments. The experimental results demonstrate the feasibility and robustness of the proposed method.