This seems like the most recent openly available slam package I could find. So let’s try it out

whenever using ros always

source /opt/ros/kinetic/setup.bash



when using ros

rosnode info or rosnode list to inspect running nodes

rostopic gets the avaiable messages

Something like this. However, should edit the yaml config file

sudo apt-get install ros-kinetic-usb-cam

rosrun usb_cam usb_cam_node

To inspect the image

rosrun image_view image_view imag=/usb_cam/image_raw

rosrun usb_cam usb_cam_node __name:=camera

changes the topic name to camera

rosrun ORB_SLAM2 Mono Vocabulary/ORBvoc.txt Examples/Monocular/TUM1.yaml

Dang. I’m pretty impressed. With a bad calibration file and no tuning, it works ok in short term. Blur clearly seems like an issue.

The contents of the example yaml config


# Camera Parameters. Adjust them!

# Camera calibration and distortion parameters (OpenCV) 
Camera.fx: 517.306408
Camera.fy: 516.469215 318.643040 255.313989

Camera.k1: 0.262383
Camera.k2: -0.953104
Camera.p1: -0.005358
Camera.p2: 0.002628
Camera.k3: 1.163314

# Camera frames per second 
Camera.fps: 30.0

# Color order of the images (0: BGR, 1: RGB. It is ignored if images are grayscale)
Camera.RGB: 1

# ORB Parameters

# ORB Extractor: Number of features per image
ORBextractor.nFeatures: 1000

# ORB Extractor: Scale factor between levels in the scale pyramid 	
ORBextractor.scaleFactor: 1.2

# ORB Extractor: Number of levels in the scale pyramid	
ORBextractor.nLevels: 8

# ORB Extractor: Fast threshold
# Image is divided in a grid. At each cell FAST are extracted imposing a minimum response.
# Firstly we impose iniThFAST. If no corners are detected we impose a lower value minThFAST
# You can lower these values if your images have low contrast			
ORBextractor.iniThFAST: 20
ORBextractor.minThFAST: 7

# Viewer Parameters
Viewer.KeyFrameSize: 0.05
Viewer.KeyFrameLineWidth: 1
Viewer.GraphLineWidth: 0.9
Viewer.CameraSize: 0.08
Viewer.CameraLineWidth: 3
Viewer.ViewpointX: 0
Viewer.ViewpointY: -0.7
Viewer.ViewpointZ: -1.8
Viewer.ViewpointF: 500

Other things to consider LSD-SLAM



Actually, many people are recommending svo and dso saying orb_slam while the better behaving one, works poorly on the pi


Also a perhaps useful ROS short course;=2745s

Old 6/16:

So I downloaded a cool looking package

roslaunch svo_ros live.launch

You need to have a camera running

sudo apt-get install ros-jade-usb-cam

run with

rosrun usb_cam usb_cam_node

You can see it using image_viewer

rosrun image_viewer image_viewer image:=/cam_usb/image_raw

Change the param file in svo_ros so that the camera has the same resolution and stuff