Study on the Indoor SLAM Using Kinect

Takeda, Yuji; Aoyama, Norifumi; Tanaami, Takahiro; Mizumi, Syoto; Kamata, Hiroyuki

doi:10.1007/978-4-431-54216-2_24

Cited by 5 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To completely evaluate the performance of the proposed mapping method, the classical ICP mapping method [32] and the RGB-D ICP mapping method [33] are also implemented under the same conditions. The average lengths of the test trajectories in the small room scene, the medium room scene, the large room scene, and the corridor scene are 7.3 meters, 10.6 meters, 32.8 meters, and 16.9 meters, respectively.…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

“…In recent years, with the emergence of consumer-level RGB-D sensors, RGB and depth cameras are utilized cooperatively to build dense 3D maps of indoor environments [30][31][32][33]. Compared with previous SLAM methods, RGB-D SLAM is able to preserve the full structural features of indoor scenes and present a superior dense 3D map.…”

Section: Introductionmentioning

confidence: 99%

“…In RGB-D SLAM systems, the Iterative Closest Point (ICP) [34] algorithm is a typical method to align the sequential point clouds captured by depth sensors. Then, the aligned point clouds are used to estimate the consecutive frame status (the rotation matrix and the translation vector) and generate the 3D map [32]. In addition, joint optimization combining visual feature matching and shape-based registration is employed to improve the accuracy of the 3D map [33].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual Map Construction Using RGB-D Sensors for Image-Based Localization in Indoor Environments

Feng

Tan

2017

Journal of Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Simulation Results and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Map Construction Using RGB-D Sensors for Image-Based Localization in Indoor Environments

Feng

Tan

2017

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…This makes it easy to integrate and use the RGB-D camera for robotic applications. The usage of the ROS platform and leveraging its packages for simulation and visualization streamlines the process of 3D reconstruction [14]. A package very widely used for generating 3D point clouds of the environment for navigation is the RTAB-Map [15].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Object Elimination based Indoor 3D Mapping System

Mane¹

2021

IJRASET

View full text Add to dashboard Cite

In today's world, the need for autonomous robots is increasing at an exponential rate and the implementation of Simultaneous Localisation And Mapping (SLAM) is gaining more and more attention. One of the major component of SLAM is 3D Mapping of the environment which enables autonomous robots to perceive the environment like a human does for which many Depth cameras or RGB-D cameras prove useful. This paper proposes a continuous real-time 3D mapping system that tackles the long existing problem of point cloud distortion induced by dynamic objects in the frame. Our method uses the Microsoft Kinect V1 as the RGB-D camera and the packages in the Robotic Operating System (ROS) like the Real Time Appearance Based Mapping (RTAB-map) for 3D reconstruction. A ROS based method is used to implement dynamic object elimination in real-time. For the purpose of dynamic objects detection in the frame, two algorithms -Deep Learning based tiny YOLO-v3 and a Machine Learning based Haar Cascade classifier are used. The results from the two are compared in terms of accuracy, execution time and mean Average Precision (mAP) and it was inferred that although HaarCascade model is comparatively less accurate when detecting objects, it is two times faster than YOLO which makes the system more real-time. The real-time implementation was given more preference while selecting the model.

show abstract

“…The interframe motion, between a pair of RGB-D images, is normally estimated through the explicit matching of surface geometry. These methods can be classified into three main categories: (1) Iterative Closest Point (ICP) variants ( [3], [4], [5], [6]), (2) feature-based registrations ( [7], [8]), and (3) hybrid approaches ( [9], [10], [11], [12], [13]). …”

Section: Introductionmentioning

confidence: 99%

A real-time distributed relative pose estimation algorithm for RGB-D camera equipped visual sensor networks

Wang

Şekercioğlu

Drummond

2013

2013 Seventh International Conference on Distributed Smart Cameras (ICDSC)

View full text Add to dashboard Cite

In mobile visual sensor networks, relative pose (location and orientation) estimation is a prerequisite to accomplish a wide range of collaborative tasks. In this paper, we present a distributed, peer-to-peer algorithm for relative pose estimation in a network of mobile robots equipped with RGB-D cameras acting as a visual sensor network.Our algorithm uses the depth information to estimate the relative pose of a robot when camera sensors mounted on different robots observe a common scene from different angles of view. To create the algorithm, we first developed a framework based on the beam-based sensor model to eliminate the adverse effects of the situations where two views of a scene each are partially seen by the sensors. Then, in order to cancel the bias introduced by the beam-based sensor model, we developed a scheme that allows the algorithm to symmetrize across the two views.We conducted simulations and also implemented the algorithm on our mobile visual sensor network testbed. Both the simulations and experimental results indicate that the proposed algorithm is fast enough for real-time operation and able to maintain a high estimation accuracy. To our knowledge, it is the first distributed relative pose estimation algorithm that uses the depth information captured by multiple RGB-D cameras. I. INTRODUCTIONThe latest advances in video technology, inexpensive camera sensors, and distributed processing allow the wide utilization of image sensors. It has resulted in a new paradigm-visual sensor network [1]. Visual sensor networks observe and process image/video data give rich information on situation awareness. Replacing the conventional RGB cameras with RGB-D camera sensors (e.g., Microsoft Kinect [2]) which can capture color image along with per-pixel depth information, visual sensor networks promise a wider range of the innovative applications, such as 3D reconstruction, object localization, etc.In this paper, we consider mobile visual sensor networks of robots equipped with RGB-D camera sensors to observe the environment. We treat each robot as a mobile RGB-D sensor. The goal is to enable each mobile RGB-D sensor to obtain the precise location and orientation information of other sensors. In order to achieve this goal, we present a peer-topeer, distributed depth image registration algorithm estimating the relative pose between multiple sensors when two or more sensors observe a common scene from different angles.Many research works have been proposed to determine the pose of a single RGB-D sensor in the last few years. The most

show abstract

Study on the Indoor SLAM Using Kinect

Cited by 5 publications

References 5 publications

Visual Map Construction Using RGB-D Sensors for Image-Based Localization in Indoor Environments

Visual Map Construction Using RGB-D Sensors for Image-Based Localization in Indoor Environments

Dynamic Object Elimination based Indoor 3D Mapping System

A real-time distributed relative pose estimation algorithm for RGB-D camera equipped visual sensor networks

Contact Info

Product

Resources

About