Pinned Repositories
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.
Astra_VideoCapture
使用厂家为奥比中光的Astra-s深度摄像头采集3DLine-SLAM所使用的数据集,该数据集的形式和TUM RGB-D 数据集的形式是一样的,采集的数据集可以在ORB-SLAM程序上进行使用,需要说明的是:3DLine-SLAM算法为我们新开发的算法,该算法在ORB-SLAM上进行开发。
CameraCalibrate
相机标定程序
dvo_slam
Dense Visual Odometry and SLAM
ED_Lib
Implementations of edge (ED, EDColor, EDPF), line (EDLines), circle (EDCircles) detection algorithms.
EdgeDrawing
该程序是边缘检测代码,论文是ED那篇,用锚点法,里面的内容对论文还原度很高。参数也想同,锚点设定方法是我自己改进的锚点设定方法。我们将该改进的锚点法用于我们在ORB-SLAM方法基础上改进而来的3DLine-SLAM,图片测试完后会写下三张测试图片,分别是梯度图(GradientImg.jpg)/锚点图(AnchorImg.jpg)/边缘图(SaveImage.png)。注意:在将一张输入图进行边缘描绘测试时,会显示一些列过程图且会保存一些试验结果,如果要将该程序运行于您自己的程序中,则需要将一部分程序段进行删除。
Kinect2_VideoCapture
该算法为在Linux下使用微软公司开发的Kinect2.0深度相机采集同TUM RGB-D数据集相同形式的数据的小程序。该程序在Linux下可以运行,帧率大概以来计算机性能可以保持25帧以上采集速率。数据集可以使用在我们自己开发的3DLine-SLAM程序上,构建出半稠密地图,同时该采集的数据也可以使用在ORB-SLAM程序上。注意:对应的相机内参受多种因素影响需要自行测量得出,直接使用TUM的数据精度会有一定区别。
line_detector
line segment detector(lsd) & edge drawing line detector(edl) & hough line detector(standard &.probabilistic) for detection
RX5808-Div
自制的RX5808接收机
VideoToImage
本程序可以将视频转换成单张RGB图像和其时间戳信息,因为现在的许多程序不是直接读取视频进行处理,使用该程序可以将视频转换成相应的一帧帧图像,该程序图片保存在文件名为rgb的文件夹中,在其之外会有一个rgb.txt的文件,这个文件则是时间戳信息,注意视频拍摄时可以是尺寸比较大的,但是转换之后,程序会将其最大像素边变成640像素大小,另一边按比例缩小。
BTREE-C802's Repositories
BTREE-C802/3DLine-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.
BTREE-C802/EdgeDrawing
该程序是边缘检测代码,论文是ED那篇,用锚点法,里面的内容对论文还原度很高。参数也想同,锚点设定方法是我自己改进的锚点设定方法。我们将该改进的锚点法用于我们在ORB-SLAM方法基础上改进而来的3DLine-SLAM,图片测试完后会写下三张测试图片,分别是梯度图(GradientImg.jpg)/锚点图(AnchorImg.jpg)/边缘图(SaveImage.png)。注意:在将一张输入图进行边缘描绘测试时,会显示一些列过程图且会保存一些试验结果,如果要将该程序运行于您自己的程序中,则需要将一部分程序段进行删除。
BTREE-C802/Astra_VideoCapture
使用厂家为奥比中光的Astra-s深度摄像头采集3DLine-SLAM所使用的数据集,该数据集的形式和TUM RGB-D 数据集的形式是一样的,采集的数据集可以在ORB-SLAM程序上进行使用,需要说明的是:3DLine-SLAM算法为我们新开发的算法,该算法在ORB-SLAM上进行开发。
BTREE-C802/VideoToImage
本程序可以将视频转换成单张RGB图像和其时间戳信息,因为现在的许多程序不是直接读取视频进行处理,使用该程序可以将视频转换成相应的一帧帧图像,该程序图片保存在文件名为rgb的文件夹中,在其之外会有一个rgb.txt的文件,这个文件则是时间戳信息,注意视频拍摄时可以是尺寸比较大的,但是转换之后,程序会将其最大像素边变成640像素大小,另一边按比例缩小。
BTREE-C802/Kinect2_VideoCapture
该算法为在Linux下使用微软公司开发的Kinect2.0深度相机采集同TUM RGB-D数据集相同形式的数据的小程序。该程序在Linux下可以运行,帧率大概以来计算机性能可以保持25帧以上采集速率。数据集可以使用在我们自己开发的3DLine-SLAM程序上,构建出半稠密地图,同时该采集的数据也可以使用在ORB-SLAM程序上。注意:对应的相机内参受多种因素影响需要自行测量得出,直接使用TUM的数据精度会有一定区别。
BTREE-C802/ED_Lib
Implementations of edge (ED, EDColor, EDPF), line (EDLines), circle (EDCircles) detection algorithms.
BTREE-C802/RX5808-Div
自制的RX5808接收机
BTREE-C802/CameraCalibrate
相机标定程序
BTREE-C802/dragoon
六足机器人
BTREE-C802/dso_ros
forked from https://github.com/JakobEngel/dso_ros
BTREE-C802/ElasticFusion
Real-time dense visual SLAM system
BTREE-C802/glfw
A multi-platform library for OpenGL, OpenGL ES, Vulkan, window and input
BTREE-C802/InsectRobotSimulation
hexapod
BTREE-C802/libfreenect2
Open source drivers for the Kinect for Windows v2 device
BTREE-C802/Line3Dpp
Line3D++ - Multi-View Stereo using Line Segments
BTREE-C802/mono_dataset_code
Code for Monocular Visual Odometry Dataset - https://vision.cs.tum.edu/data/datasets/mono-dataset
BTREE-C802/NiTE-2.0.0
BTREE-C802/ONE-Robot
2015年做的一个基于IMU和STM32的独轮自平衡机器人
BTREE-C802/opencv
Open Source Computer Vision Library
BTREE-C802/OpenNI-Linux-x64-2.3
BTREE-C802/OpenNI2
OpenNI2
BTREE-C802/ORB_Line_SLAM
line feature based SLAM, modified based on the famous ORB-SLAM2
BTREE-C802/ORB_SLAM
A Versatile and Accurate Monocular SLAM
BTREE-C802/ORB_SLAM2
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
BTREE-C802/pl-slam
This code contains an algorithm to compute stereo visual SLAM by using both point and line segment features.
BTREE-C802/rovio
BTREE-C802/rpg_svo
Semi-direct Visual Odometry
BTREE-C802/semidense-lines
Incremental 3D Line Segment Extraction for Surface Reconstruction from Semi-dense SLAM
BTREE-C802/slambook
BTREE-C802/tum_ardrone
Repository for the tum_ardrone ROS package, implementing autonomous flight with PTAM-based visual navigation for the Parrot AR.Drone.