how can i use RGBDSlam with image
i have a sequence of image with the format bmp(or png), they are rgb and depth image,there is no bagfiles. how can i use RGBDSlam with those dataset. thanks!
ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
i have a sequence of image with the format bmp(or png), they are rgb and depth image,there is no bagfiles. how can i use RGBDSlam with those dataset. thanks!
After you brings up RGBDSLAM by using Kinect or other RGBD sensors, you can use rqt
to check what are the input topics of RGB and depth image for RGBDSLAM.
Let's say the topic names are /rgb_image and /depth_image, then you need to publish images in your dataset to /rgb_image and /depth_image. You can do it by reading the images from OpenCV and publish it to topics. (You might need this ref.)
Due to some problem I cannot indicate the precise topic name. But I think you can find out by yourself.
Asked: 2015-07-22 07:41:01 -0500
Seen: 328 times
Last updated: Jul 24 '15
RGBDSLAM Installation Problems
openni-dev/ps-engine with rgbdslam_freiburg
Convert a 16 bit compressed kinect depth image to something usable?
how to use SIFTGPU and ORB in RGBDSLAM
Implementing ColorOcTree in OctoMap using RGBDSLAM
libg2o installation problem on ROS Hydro Raspbian Wheezy
RGB-D slam fails on catkin_make
Using custom publisher with RGBDSlam
How to take a 3D point cloud of rotating object with a fixed kinect position using RGBDSLAM?