Pinned Repositories
2D-3D-pose-tracking
Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences
3DLine-SLAM
3DLines-SLAM: A Monocular Vision Semi-Dense 3D Reconstruction Based on ORB-SLAM Abstract-Producing high-quality 3D maps and calculating more accurate camera pose has always been the goal of SLAM technology. The requirements of SLAM technology such as real-time, low computational cost, and low hardware cost are contradictory to the above objectives. For the issues listed above, we propose a novel semi-dense reconstruction algorithm based on the monocular ORB-SLAM system by matching the line segment features extracted from keyframes. Specifically, we build upon ORB-SLAM, the system first provides a set of keyframes and their corresponding camera poses and a series of map points in real-time. Then we use our developed a keyframe re-culling algorithm to culling redundant keyframes. Then an improved line segment extraction method is used to extract line segments in each keyframe. Finally, we use purely geometric constraints to generates accurate 3D scene model by matching 2D line segments from different keyframes. We thoroughly evaluate and in-depth analysis of our approach, the results show our system runs steadily and reliably. Not only the whole system has strong robustness, but also it can quickly generate an accurate 3d model online with low computational costs.
AdaptiveGoalManagement
AliceVision
Photogrammetric Computer Vision Framework
als_ros
An advanced localization system for ROS use.
ALVIO
Adaptive Line and Point Feature-based Visual Inertial Odometry for Robust Localization in Indoor Environments
awesome-gis
😎Awesome GIS is a collection of geospatial related sources, including cartographic tools, geoanalysis tools, developer tools, data, conference & communities, news, massive open online course, some amazing map sites, and more.
cam_rtsp
opencv - rtsp
hpp2plantuml
Convert C++ header files to PlantUML
MORB
Official repository of the local feature MORB, a multi-scale binary descriptor based on ORB that improves the accuracy of feature matching under scale changes.
Dung-ND's Repositories
Dung-ND/2D-3D-pose-tracking
Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences
Dung-ND/3DLine-SLAM
3DLines-SLAM: A Monocular Vision Semi-Dense 3D Reconstruction Based on ORB-SLAM Abstract-Producing high-quality 3D maps and calculating more accurate camera pose has always been the goal of SLAM technology. The requirements of SLAM technology such as real-time, low computational cost, and low hardware cost are contradictory to the above objectives. For the issues listed above, we propose a novel semi-dense reconstruction algorithm based on the monocular ORB-SLAM system by matching the line segment features extracted from keyframes. Specifically, we build upon ORB-SLAM, the system first provides a set of keyframes and their corresponding camera poses and a series of map points in real-time. Then we use our developed a keyframe re-culling algorithm to culling redundant keyframes. Then an improved line segment extraction method is used to extract line segments in each keyframe. Finally, we use purely geometric constraints to generates accurate 3D scene model by matching 2D line segments from different keyframes. We thoroughly evaluate and in-depth analysis of our approach, the results show our system runs steadily and reliably. Not only the whole system has strong robustness, but also it can quickly generate an accurate 3d model online with low computational costs.
Dung-ND/ALVIO
Adaptive Line and Point Feature-based Visual Inertial Odometry for Robust Localization in Indoor Environments
Dung-ND/cartographer_detailed_comments
Dung-ND/CV-MonoSLAM
:camera:This is a monocular SLAM project based on ceiling vision.
Dung-ND/EdgeDirectVO
Edge-Direct Visual Odometry
Dung-ND/event-based_vision_resources
Dung-ND/Fast-3D-Pointcloud-Segmentation
Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding
Dung-ND/GSLAM
A General Simultaneous Localization and Mapping Framework which supports feature based or direct method and different sensors including monocular camera, RGB-D sensors or any other input types can be handled.
Dung-ND/indoorjs
Indoor mapping for floorplans using on fabricjs
Dung-ND/intrinsic3d
Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)
Dung-ND/libSGM
Stereo Semi Global Matching by cuda
Dung-ND/LineEstimator
Vision-based Line Estimation and Tracking algorithms for Visual Odometry and SLAM
Dung-ND/LOAM_NOTED
loam code noted in Chinese（loam中文注解版）
Dung-ND/loam_velodyne
Laser Odometry and Mapping (Loam) is a realtime method for state estimation and mapping using a 3D lidar.
Dung-ND/openMVS
open Multi-View Stereo reconstruction library
Dung-ND/openvslam
OpenVSLAM: A Versatile Visual SLAM Framework
Dung-ND/ORIS
Image Stitching Algorithm for UAV Aerial Capture Based on Improved ORB and RANSAC
Dung-ND/point_cloud_segmentation
Standard point-cloud segmentation methods to be used with the Robot Operating System (ROS)
Dung-ND/ros_rtsp
ROS node to subscribe to an image and serve it up as a RTSP video feed.
Dung-ND/rosbag2video
converts image sequence in ros bag files to video files
Dung-ND/SDR
Code for 'Segment-based Disparity Refinement with Occlusion Handling for Stereo Matching'
Dung-ND/semidense-lines
Incremental 3D Line Segment Extraction for Surface Reconstruction from Semi-dense SLAM
Dung-ND/SLAM-2D-LIDAR-SCAN
Excellent FastSLAM with 2D Laser Scan Match in Python Environment
Dung-ND/stvo-pl
Stereo Visual Odometry by combining point and line segment features
Dung-ND/svgurt
Image -> SVG Vectorizing Tool - Live at:
Dung-ND/tf_remapper_cpp
More efficient version of tf/tf_remap able to handle TFs at kHz with tens of subscribers.
Dung-ND/tf_visual_tools
Manually manipulate TFs in ROS using this Rviz plugin.
Dung-ND/ucoslam-cv3
Updated UcoSLAM to compile for OpenCV 3
Dung-ND/vue-indoor
VueJS wrapper for indoorjs