Part 1: Testing with actual k-means and 3 agentsDuring this testing, each agent is only processing the features that belong to it (determined by distances from features to its k-means label). Because the video is 7 seconds, there are 7 images. Initially:
Here are the numbers of matches broken down to each agent for each image: Testing runtime: Part 2: Parameterize video processing functionalityThree additional ROS parameters are added to the configuration file: data_format, video_extraction_frame_rate and absolute_video_path. Now the user can specify whether to input data from images or a video, what is the extraction frame rate, as well as the location of the target video all in the ROS parameter file. All parameters have been tested. They are working correctly. Part 3: Documentations and more
0 Comments
Leave a Reply. |
Archives
May 2020
Categories |