News

A new 3D Video Stabilization Algorithm has been developed by the IPCV-LAB to remove the camera jitter from image sequences captured by planetary robots. First, the frame to frame surface 3D motion with respect to the camera coordinate system is estimated and accumulated over time. The estimation is performed by maximizing a likelihood function of the frame to frame intensity differences measured at key observation points. Then, the jitter is determined as the perspective projection of the difference between the accumulated surface 3D translation and a smoothed version of it. Finally, the stabilized video is synthesized by moving the entire content of each image with a displacement vector having the same magnitude but opposite direction to the estimated jitter for that image. The experimental results with synthetic data revealed real time operation with low latency and a reduction of the jitter in a factor of 20. Experimental results with real image sequences captured by a rover platform in indoor and outdoor conditions show very reliable and encouraging stabilization results. 

 

A detailed description of the algorithm can be fould here.

On April 19th and 21st, 2016, at 2 pm, Dr. Geovanni Martinez demonstrated the RTK dGPS Outdoor Guidence System of the Seekur Jr. rover in the gardens of the School of Electrical Engineering for the UCR Technology Fair participants. They had also the opportunity to teleoperate the rover.

Dr. Geovanni Martinez gave a talk entitled "Intensity-Difference Based Monocular Visual Odometry for Planetary Rovers" at the University of Costa Rica as part of the commemoration of the 19th aniversary of the School of Geography.

Dr. Geovanni Martinez gave a talk entitled "Intensity-Difference Based Monocular Visual Odometry for Planetary Rovers: A Case Study" at the “United Nations/Costa Rica Workshop on Human Space Technology”, San Jose, Costa Rica, 7-11 March, 2016.

Prof. Dr. Johanna Wanke, German Federal Minister of Education and Research visited the University of Costa Rica. During her visit, Dr. Geovanni Martinez, IPCV-LAB coordinator,  had the opportunity to explain the latest results obtained through research projects in the area of vision-based navigation systems for autonomous planetary robots, specifically the results obtained by testing the intensity-difference based monocular visual odometry algorithm in a real robot platform in outdoor sunlit conditions. This later algorithm was recently debeloped at the IPCV-LAB for robot positioning using a single video camera.

Informatic Center representatives of the University of Costa Rica visited the IPCV-LAB. The visit was to learn personally about the research projects, which are being carried out by the IPCV-LAB for vision-based navigation of autonomous planetary robots. In addition, the IPCV-LAB received an invitation to participate in the UCR Technology Fair that they are organizing.

During the week of robotics organized by the ARCOS-LAB, Dr. Geovanni Martinez, IPCV-LAB coordinator, had the opportunity to give the following three talks: 1) Intensity-Difference Based Monocular Visual Odometry for Planetary Rovers (on January 25th, from 2 pm to 3 pm), 2) Vision-Based Teleoperation of Robotic Arms (on January 25th, from 3 pm to 4 pm) and 3) Vision-Based Autonomous Navigation for Planetary Rovers (on January 26th, from 1 pm to 2 pm). This later talk included a demonstration of the autonomous capabilities of the Seekur Jr. rover, which was recently acquired for testing the vison-based autonomous navigation systems, which are being developed at the IPCV-LAB.  

Ana Maria Romero, Investment Promotion Manager, Paula Bogantes, Advanced Manufacturing Sector Manager, Karin Lachner, Director of Marketing, Mariana Bustamante, Life Sciences Sector Investment Promotion Executive, and Diana Salazar, Senior Aftercare Executive, of the Costa Rican Invesment Promotion Agency (CINDE) visited the IPCV-LAB. Dr. Geovanni Martinez gave them a talk about the IPCV-LAB's research projects and showed them the two robots (Husky A200 and Seekur Jr.) used for validation of the computer vision algorithm, which are being developed in the IPCV-LAB for visual-based autonomous navigation of mobile robots, particularly for planetary robots.

On Monday December 7, 2015, took place the day of open doors of the School of Electrical Engineering at the University of Costa Rica. During this day many people visited the Image Processing and Computer Vision Research Laboratory (IPCV-LAB) to learn about the latest results of the conducted research and also to see the Seekur Jr. robot, which was recently acquired by the IPCV-LAB to test computer vision algorithms, such as visual odometry algorithms, for autonomous robotics. 

The Rector of the University of Costa Rica, Dr. Hening Jensen, visited the IPCV-LAB. Dr. Geovanni Martinez gave him a talk about the IPCV-LAB's research projects and also showed him the new rover Seekur Jr. that was recently acquired by the IPCV-LAB for testing visual odometry algorithms in any weather and terrain. The rover will also be used to test other computer vision algorithms, which are being developed also in the IPCV-LAB for visual-based autonomous navigation of mobile robots.

Pages