ELAS_ROS算法在 KITTI数据集实践

下载KITTI数据集的Odometry的00数据集
下载ELAS_ROS代码编译后增加kitti.launch如下：

<launch>
<!-- Launches ELAS node, and rectification nodes for input -->
<!-- Arguments: input stereo namespace and output elas namespace -->
<arg name="stereo" default="narrow_stereo_textured"/>
<arg name="elas_ns" default="elas"/>
<!-- If you already have rectified camera images remove the image_proc nodes -->
<group ns="$(arg stereo)/left">
<node name="left_rect" pkg="image_proc" type="image_proc"/>
</group>
<group ns="$(arg stereo)/right">
<node name="right_rect" pkg="image_proc" type="image_proc"/>
</group>
<!-- This node actually does the stereo reconstruction -->
<node name="$(arg elas_ns)" pkg="elas_ros" type="elas_ros" output="screen">
<remap from="stereo" to="$(arg stereo)"/>
<remap from="image" to="image_rect"/>
<!--<param name="approximate_sync" value="true" />-->
<param name="disp_min" type="int" value="0"/>
<param name="disp_max" type="int" value="255"/>
<param name="support_threshold" type="double" value="0.95"/>
<param name="support_texture" type="int" value="10"/>
<param name="candidate_stepsize" type="int" value="5"/>
<param name="incon_window_size" type="int" value="5"/>
<param name="incon_threshold" type="int" value="5"/>
<param name="incon_min_support" type="int" value="5"/>
<param name="add_corners" type="bool" value="0"/>
<param name="grid_size" type="int" value="20"/>
<param name="beta" type="double" value="0.02"/>
<param name="gamma" type="double" value="3"/>
<param name="sigma" type="double" value="1"/>
<param name="sradius" type="double" value="2"/>
<param name="match_texture" type="int" value="1"/>
<param name="lr_threshold" type="int" value="2"/>
<param name="speckle_sim_threshold" type="double" value="1"/>
<param name="speckle_size" type="int" value="200"/>
<param name="ipol_gap_width" type="int" value="300"/>
<param name="filter_median" type="bool" value="0"/>
<param name="filter_adaptive_mean" type="bool" value="1"/>
<param name="postprocess_only_left" type="bool" value="1"/>
<param name="subsampling" type="bool" value="0"/>
<!-- If your cameras are not synchronised then uncomment the following line -->
<param name="approximate_sync" value="true" type="bool"/>
</node>
</launch>

在ros新建工程xiaoyao后在scripts增加文档doublecam_talk.py如下：

#!/usr/bin/env python
# license removed for brevity
import rospy
from sensor_msgs.msg import Image,CameraInfo
from std_msgs.msg import Header
import cv2
from cv_bridge import CvBridge
import time
import os
w =1241
h =376#xiaoyao
def build_camera_info(sec_test,frame_str):msg_header = Header(stamp=rospy.Time.from_sec(sec_test))#(stamp=rospy.Time.now())#msg_header = Header( stamp=rospy.Time.now() )msg_header.frame_id = 'narrow_stereo_optical_frame'#frame_str#"camera"camera_info = CameraInfo()# store info without headercamera_info.header = msg_headercamera_info.width = wcamera_info.height = hcamera_info.distortion_model = 'plumb_bob'cx = 607.1928cy = 185.2157fx = 718.856fy = 718.856camera_info.K = [fx, 0, cx, 0, fy, cy, 0, 0, 1]camera_info.D = [0, 0, 0, 0, 0]camera_info.R = [1.0, 0, 0, 0, 1.0, 0, 0, 0, 1.0]camera_info.P = [fx, 0, cx, 0, 0, fy, cy, 0, 0, 0, 1.0, 0]camera_info.binning_x =1 camera_info.binning_y =1 #camera_info.roi.do_rectify=Truereturn camera_info def talker():'''/camera/left/image_raw/camera/right/image_raw/camera/left/camera_info/camera/right/camera_info'''pub1 = rospy.Publisher('/narrow_stereo_textured/left/image_raw', Image, queue_size=5)pub2 = rospy.Publisher('/narrow_stereo_textured/right/image_raw', Image, queue_size=5)pubinfo1 = rospy.Publisher('/narrow_stereo_textured/left/camera_info', CameraInfo, queue_size=5)pubinfo2 = rospy.Publisher('/narrow_stereo_textured/right/camera_info', CameraInfo, queue_size=5)rospy.init_node('talker', anonymous=True) rate = rospy.Rate(2)datadir = '/home/cc/orbslam2/data/00/'lpath=datadir+'image_0/'rpath=datadir+'image_1/'i=0f = open(datadir+"times.txt")imglist = os.listdir(lpath)imglist.sort( key=None, reverse=False)#sorted(imglist)#print(imglist)for imgfile in imglist:if rospy.is_shutdown():breakimgname = imgfile#.split('/')[-1]limg = cv2.imread(lpath+imgname)rimg = cv2.imread(rpath+imgname)#print(lpath+imgname,rpath+imgname)lineNum = float( f.readline() )left_camera_info =  build_camera_info(lineNum,'')        right_camera_info = build_camera_info(lineNum,'')left_img_msg   = CvBridge().cv2_to_imgmsg(limg, "bgr8")right_img_msg  = CvBridge().cv2_to_imgmsg(rimg, "bgr8")left_img_msg.header = left_camera_info.headerright_img_msg.header = right_camera_info.headerpubinfo1.publish(left_camera_info) pubinfo2.publish(right_camera_info)pub1.publish(left_img_msg)pub2.publish(right_img_msg)rate.sleep()if __name__ == '__main__':try:talker()except rospy.ROSInterruptException:pass

roscore
roslaunch elas_ros kitti.launch
rosrun xiaoyao doublecam_talk.py

rviz显示
下方Add按钮点击后，
查看Image主题 elas_ros/depth/Image 、elas_ros/image_disparity/Image 、 elas/point_cloud(虚拟机好像显示不了)

之前碰壁：
1.camera_info的格式查看可参考：http://docs.ros.org/en/melodic/api/sensor_msgs/html/msg/CameraInfo.html
rostopic echo /camera/right/camera_info
2.
[image_transport] Topics ‘xxx’ and ‘xxx’ do not appear to be synchronized
图片也有header需要跟camera_info的header同步
3.Rectified topic ‘xxx’ requested but camera publishing ‘xxx’ is uncalibrated
kitti需要内参的书写(在header里的fx)

ELAS_ROS算法在 KITTI数据集实践相关推荐

【MMDetection3D】环境搭建，使用PointPillers训练测试可视化KITTI数据集
文章目录前言 3D目标检测概述 KITTI数据集简介 MMDetection3D 环境搭建数据集准备训练测试及可视化绘制损失函数曲线参考资料前言 2D卷不动了,来卷3D,之后更多地工作会 ...
感知机算法在鸢尾花数据集上的实践
感知机算法在鸢尾花数据集上的实践 1 问题背景 2 数据集的微处理 3 导数据,并进行简单可视化 4 模型算法的训练部分 1 问题背景感知机作为一个比较经典的处理线性二分类的算法,今天想着实践一下, ...
KITTI数据集详解和评价标准
from: https://blog.csdn.net/Solomon1558/article/details/70173223 摘要:本文融合了Are we ready for Autonomous ...
数据集：KITTI数据集分析
摘要:本文融合了Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite和Vision meets Robotics: ...
KITTI 数据集（CVPR 2012） - 点云 3D
KITTI 数据集(CVPR 2012) - 点云 3D 0. KITTI 数据集 - 点云 3D 简述 0.1 KITTI 数据集采集平台 0.2 KITTI 3D 目标检测 - 数据集解析 0.2 ...
Kitti数据集的使用
摘要:本文融合了Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite和Vision meets Robotics: ...
郑捷《机器学习算法原理与编程实践》学习笔记（第七章预测技术与哲学）7.1 线性系统的预测...
7.1.1 回归与现代预测 7.1.2 最小二乘法 7.1.3 代码实现 (1)导入数据 def loadDataSet(self,filename): #加载数据集X = [];Y = []fr = ...
毕设日志——在faster rcnn pytorch上训练KITTI数据集
本次目标: 整理运行代码产生的内容下载KITTI数据集和LSVH数据集修改数据集样式为VOC2007 在新的数据集上训测 2019.4.13 一.准备工作备份之前训练生成的文件models,ou ...
kitti数据集简介、百度网盘分享 kitti-object、kitti-tracking 全套数据集自动驾驶
0 写在前面最近在学习MOT相关知识,之前暑期实习是在一家自动驾驶公司,公司资料里已经有了kitti数据集,所以直接用的,并没有去下载.但是最近自己在学校也用到了这个数据集,所以就去官网下载了,结果 ...
郑捷《机器学习算法原理与编程实践》学习笔记（第四章推荐系统原理）（三）SVD...
4.5.1 SVD算法回顾 A = U∑VT 其中:A是N*M的矩阵,U是M*M的方阵(里面向量正交,称为左奇异向量),∑是一个M*N的矩阵,VT是一个N*N的矩阵(里面向量正交,右奇异向量) 那么奇 ...

ELAS_ROS算法在 KITTI数据集实践

ELAS_ROS算法在 KITTI数据集实践相关推荐

最新文章

热门文章

ELAS_ROS算法 在 KITTI数据集 实践

ELAS_ROS算法 在 KITTI数据集 实践相关推荐

最新文章

热门文章

ELAS_ROS算法在 KITTI数据集实践

ELAS_ROS算法在 KITTI数据集实践相关推荐