Gemini’s vision processing system is designed to provide data on surrounding mission elements as the vehicle navigates. Each mission has its own vision module which can be run or started independent of every other module, which saves processor time by only running the necessary processes. Mission elements are detected by a combination of edge detection, color thresholding, and graph segmentation, though not all elements use every algorithm, according to Cornell. Camera data can also be saved to disk to be used later for off-line mission tuning.
Gemini’s new CUAUV Automated Vision Evaluator (CAVE) helps analyze vision performance by keeping a database of logged video and providing a graphical framework for quick annotation and automated testing. CAVE also organizes captured logs and allows searching by metadata, including information such as weather conditions within a video, video location, and which mission elements are present within a video. Read more about the CAVE system here.
The RoboSub competition takes place July 28-August 3 at the SSC Pacific TRANSEC in San Diego, CA. The Gemini team is made up of 43 students from three of Cornell’s colleges.
View more information on the Gemini AUV.
Share your vision-related news by contacting James Carroll, Senior Web Editor, Vision Systems Design
To receive news like this in your inbox, click here.
Join our LinkedIn group | Like us on Facebook | Follow us on Twitter | Check us out on Google +
Page 1 | Page 2
