GSoC 2017 Summary

Project Name: Vision based Terrain Traversability Estimation for Planetary Robots and Astronauts Project Mentors: Karan Saxena Antonio Del Mestro Project Repo: View on Github Working with: Italian Mars Society Python Software Foundation Project Abstract: Implementing a vision based terrain traversability estimator for planetary rovers and astronauts to eliminate heavy hardware used in current techniques. Some …

Camera position with Pose Transformations

As discussed in the previous blog, with fundamental matrix the necessity is not being fulfilled. Below are the proposals for final evaluation. 1. Track the camera with pose transformations. 2. Estimate the height and correspond it to the distance where the camera is standing. 3. Correlate the terrain patches to the position on which the object …

Camera Position with Fundamental Matrix

As discussed in the last post a rtabmap_ros is executed with a recorded video. Rtabmap_ros provided a .bag file which publishes below ROS topics while executed. As seen in the picture, it publishes camera info for both the left and right cameras also. The images that are being published are compressed and image view package …

Visual Odometry for a Recorded Video

Phase-1 evaluation has been completed last week and there has been a good amount of progress in the project as of now. The complete architecture is understood and many approaches have been explored. Thanks to my mentors Karan Saxena and Antonio Del Mestro 🙂 The proposed solution for publishing RGBD images on desired ROS topics …

ROS Publisher for Kinect2 RGBD Images

As discussed in the previous post, we need a script that publishes RGBD images from Kinect v2 on ROS topics to compute VO. Below are the ROS topics that are needed for rtabmap_ros to compute Visual Odometry. There are many ROS packages that are available for this job but very few of them are currently …

RGB-D Visual Odometry on ROS

The important aspect of the project is Visual Odometry(VO). It estimates the trajectory of the camera in the world coordinate system which is useful for retrieving the current terrain patch on which the astronaut is standing. For monocular visual odometry, PTAM has been used. The mapping thread in PTAM is heavy and the trajectory wasn't …

Setting up Kinect v2 for Ubuntu

After considerable attempts on monocular visual odometry, we have shifted to using a depth sensor which is expected to give accurate visual odometry compared to a monocular camera. So, the first step would be setting up the Kinect v2. Kinect v2 has got a good support on Windows through the Kinect SDK but doesn't have …

GSoC 2017 Acceptance

GSoC 2017 selected students list is out. Happy to see my name on the list 🙂 GSoC has been a dream in my second year of bachelor's and it was the main reason that drove me to start learning computer programming. Starting with Mozilla FXOS, I have learned many skills and understood many open source …

Terrain Estimation by a Monocular Camera

Project Overview A Rover or an astronaut is mounted with a monocular camera from which the live streaming data can be accessed through a ROS topic. At every step, the camera can view some part of the region which is in front of it but not the terrain which is exactly below or immediate to …

HTML Video Compositor

Mozilla is planning to do an HTML Video compositor. This is the first online HTML Video compositor in the world :D. The base for the project is html-video-compositor built by BBC. Though we have to implement a lot more things which are missing in BBC html-video-compositor API. With the help of Chai Thug, I have …