Real-time Scalable Dense Surfel Mapping

Wang, Kaixuan; Gao, Fei; Shen, Shaojie

doi:10.1109/icra.2019.8794101

Cited by 57 publications

(64 citation statements)

References 23 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FlashFusion [50] can obtain real-time globally consistent dense 3D reconstruction using CPU computing. DenseSurfelMapping [51] is a surfel-based real-time mapping system and can be used for UAVs. Voxblox builds the TSDF and ESDF in real-time on a CPU for UAV navigation.…”

Section: Related Workmentioning

confidence: 99%

CDSFusion: Dense Semantic SLAM for Indoor Environment Using CPU Computing

et al. 2022

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) require the ability to robustly perceive surrounding scenes for autonomous navigation. The semantic reconstruction of the scene is a truly functional understanding of the environment. However, high-performance computing is generally not available on most UAVs, so a lightweight real-time semantic reconstruction method is necessary. Existing methods rely on GPU, and it is difficult to achieve real-time semantic reconstruction on CPU. To solve the problem, an indoor dense semantic Simultaneous Localization and Mapping (SLAM) method using CPU computing is proposed in this paper, named CDSFusion. The CDSFusion is the first system integrating RGBD-based Visual-Inertial Odometry (VIO), semantic segmentation and 3D reconstruction in real-time on a CPU. In our VIO method, the depth information is introduced to improve the accuracy of pose estimation, and FAST features are used for faster tracking. In our semantic reconstruction method, the PSPNet (Pyramid Scene Parsing Network) pre-trained model is optimized to provide the semantic information in real-time on the CPU, and the semantic point clouds are fused using Voxblox. The experimental results demonstrate that camera tracking is accelerated without loss of accuracy in our VIO, and a 3D semantic map is reconstructed in real-time, which is comparable to one generated by the GPU-dependent method.

show abstract

Section: Related Workmentioning

confidence: 99%

CDSFusion: Dense Semantic SLAM for Indoor Environment Using CPU Computing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In this article, Surfel is used to fuse the depth map and RGB map obtained from RGB-D sensor to reconstruct the indoor scene. Each surfel stores the location of the corresponding spatial point, the radius, the normal vector, the color, and the time information [16]. The position, normal vector, and color will be updated according to the weighted fusion result, and the radius is obtained by the distance between the surface and the optical center of camera [8].…”

Section: Dense Reconstruction Of Scenesmentioning

confidence: 99%

Real-Time Dense Reconstruction of Indoor Scene

Niu¹,

Hu²,

Niu³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Real-time dense reconstruction of indoor scenes is of great research value for the application and development of service robots, augmented reality, cultural relics conservation and other fields. ORB-SLAM2 method is one of the excellent open source algorithms in visual SLAM system, which is often used in indoor scene reconstruction. However, it is time-consuming and can only build sparse scene map by using ORB features to solve camera pose. In view of the shortcomings of ORB-SLAM2 method, this article proposes an improved ORB-SLAM2 solution, which uses a direct method based on light intensity to solve the camera pose. It can greatly reduce the amount of computation, the speed is significantly improved by about 5 times compared with the ORB feature method. A parallel thread of map reconstruction is added with surfel model, and depth map and RGB map are fused to build the dense map. A Realsense D415 sensor is used as RGB-D cameras to obtain the three-dimensional (3D) point clouds of an indoor environments. After calibration and alignment processing, the sensor is applied in the reconstruction experiment of indoor scene with the improved ORB-SLAM2 method. Results show that the improved ORB-SLAM2 algorithm cause a great improvement in processing speed and reconstructing density of scenes.

show abstract

“…These strategies use monocular camera, 27 stereo camera, 28 monocular camera with IMU, 12 or stereo camera with IMU. 13 In this article, we will deploy the VINS-MONO for localization and Dense Surfel Mapping to get local dense point cloud map.…”

Section: Related Workmentioning

confidence: 99%

“…But we use an inexpensive and lightweight stereo camera (Intel Realsense D435) for perception in this article. We deploy the VINS-MONO 12 for localization and Dense Surfel Mapping 13 to get local dense point cloud map. We also use Octomap to perform three-dimensional (3-D) map building for its efficient memory usage.…”

Section: Introductionmentioning

confidence: 99%

A low-cost autonomous navigation system for a quadrotor in complex outdoor environments

Wang

Liu

2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

In this article, we design a low-cost navigation system for a quadrotor working in unknown outdoor environments. To reduce the computing burden of the quadrotor, we build a separated system and transfer the computing resources from onboard side to ground station side. Both sides’ communication is guaranteed by 5G wireless networks. We utilize a stereo camera to acquire point clouds and build Octomap for the quadrotor’s navigation. Then, the trajectory is generated in two stages. In the first stage, a modified RRT*-CONNECT algorithm is adopted to generate a set of collision-free waypoints. In the second stage, a curve fitting algorithm is utilized to get a smooth piecewise Bezier trajectory. The advantage of the proposed method is to optimize the path into a safe, smooth, and dynamically feasible trajectory in real time. The modules of the state estimation, dense mapping, and motion planning are integrated into a DJI Matrice 100 quadrotor. Finally, simulation and experiments are both conducted to show the validity and practicality of our method.

show abstract

Real-time Scalable Dense Surfel Mapping

Cited by 57 publications

References 23 publications

CDSFusion: Dense Semantic SLAM for Indoor Environment Using CPU Computing

CDSFusion: Dense Semantic SLAM for Indoor Environment Using CPU Computing

Real-Time Dense Reconstruction of Indoor Scene

A low-cost autonomous navigation system for a quadrotor in complex outdoor environments

Contact Info

Product

Resources

About