hjmgarmin / ovd-slam Goto Github PK

请教一下,我自己改了一下yoloV5的网络结构,怎么部署成tensorrt呢?并且orb-slam可以用的

hello author！Is the dynamic feature recognition part inconsistent with the paper?

Hi @HJMGARMIN,

Thanks for your excellent work! I was wondering did you notice any noise in depth from the Bonn dataset (shown in the attached figure, especially the wall and table)?

Following is the code for visualization

import open3d as o3d
import numpy as np


H = 480
W = 640
fx = 542.822841
fy = 542.576870
cx = 315.593520
cy = 237.756098


K = o3d.camera.PinholeCameraIntrinsic(
    width=W,
    height=H,
    fx=fx,
    fy=fy,
    cx=cx,
    cy=cy
)

depth_file = '/home/weining/Downloads/rgbd_bonn_balloon/depth/1548266469.88217.png'
depth_img = o3d.io.read_image(depth_file)
points = o3d.geometry.PointCloud.create_from_depth_image(
    depth = depth_img,
    intrinsic = K,
    depth_scale = 5000,
)

o3d.visualization.draw_geometries([points])

Thanks in advance!
Weining

您好，我按照tensorrt6.0的版本生成了yolov5x.engine，放到model文件夹里为什么运行后剔除不了动态特征点？

大佬您好，感谢开源，我看都是国人，我就用中文了，我想问一下运行哪个程序可以实现稠密重建的效果？我运行了rgbd_tum，跑数据集没有看到稠密建图的结果。

大佬您好，请问yolov5训练用的哪个数据集呢？

这个公式按照我的理解应该是把一个高斯分布转化成标准高斯分布计算卡方值，那分母应该是计算标准差。是否少了一个1/n？另外，计算标准差的话，分母是否也不需要平方了？

我将程序安装完，也成功运行了tum数据集，但是并没有点云地图产生，想问问如何运行出论文里说的稠密点云地图

I have installed the program and successfully ran the TUM dataset, but no point cloud map was generated. I would like to ask how to run the dense point cloud map mentioned in the paper

在TUM3.yaml文件中设置PointCloudMapping: 1
运行TUM数据集时，产生段错误，然后pcl一闪而过
如果PointCloudMapping: 0，则不会产生段错误

你好，在源码中const float invSigma2 = 128 * imDepth.at<float>(kp->pt.y, kp->pt.x) * imDepth.at<float>(kp->pt.y, kp->pt.x) / (fx);
在这里的128/fx，我不是很能理解这里的含义，你能帮我解答一下吗？

您好，您这个按照动态权重改进重投影误差，是只在位姿初始化中的BA使用，还是运动BA，局部BA和全局BA都改进了呢？代码中好像没看见这一部分。

Camera1.k3 optional parameter does not exist...
-Loaded camera 1
Camera.newHeight optional parameter does not exist...
Camera.newWidth optional parameter does not exist...
-Loaded image info
-Loaded RGB-D calibration
-Loaded ORB settings
Viewer.imageViewScale optional parameter does not exist...
-Loaded viewer settings
System.LoadAtlasFromFile optional parameter does not exist...
System.SaveAtlasToFile optional parameter does not exist...
-Loaded Atlas settings
System.thFarPoints optional parameter does not exist...
-Loaded misc parameters
SLAM settings:
-Camera 1 parameters (Pinhole): [ 535.4 539.2 320.1 247.6 ]
-Camera 1 distortion parameters: [ 0 0 0 0 ]
-Original image size: [ 640 , 480 ]
-Current image size: [ 640 , 480 ]
-Sequence FPS: 30
-RGB-D depth map factor: 5000
-Features per image: 1500
-ORB scale factor: 1.2
-ORB number of scales: 8
-Initial FAST threshold: 20
-Min FAST threshold: 7

Loading ORB Vocabulary. This could take a while...
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
已放弃

您好，我在运行代码时opencv报错如下，请问您该如何解决？
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.4.0) /home/opencv-4.4.0/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'

Loading ORB Vocabulary. This could take a while...
Vocabulary loaded!

Initialization of Atlas from scratch
Creation of new map with id: 0
Creation of new map with last KF id: 0
Seq. Name:
load model success
There are 1 cameras in the atlas
Camera 0 is pinhole
0.01 50 1
load model success

Start processing sequence ...
Images in the sequence: 827

First KF:0; Map init KF:0
New Map created with 1071 points
Starting the Viewer
the above is running prompt, i find the running result does not reject dynamic object, its running result is consistent with ORB-SLAM3.
Could answer me, thank you.