Motivation<\/h5>\n
Mobile robots use SLAM system to better understand environment<\/p>\n
Problem<\/h5>\n
Dynamic objects often disrupt camera tracking and mapping<\/p>\n
Solution<\/h5>\n
Filter out the dynamic features and only rely on static features<\/p>\n
![\"\"](\"http:\/\/mscvprojects.ri.cmu.edu\/2019teama\/wp-content\/uploads\/sites\/16\/2019\/05\/1sad-300x222.png\")
<\/p>\n
Image source:\u00a0Bescos, Berta, et al. “DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes.” IEEE Robotics and Automation Letters 3.4 (2018): 4076-4083.<\/p>\n
PART2: Illumination Invariant Cross-spectral Feature Matching (FALL 2019)<\/h4>\n
When a robot performing visual SLAM in a scene, one thing that can keep changing is the illumination condition. In some cases, the change in illumination is severe and in order to reliably localize during this change, a robust feature that is invariant to non-linear intensity variations is required.\u00a0 This type of feature has many real-world applications such as re-localization across day-night cycles,\u00a0 cross-spectral registration, etc. Our project is focused on how to develop such feature with non-learning method.<\/p>\n
Motivation<\/h5>\n
Indoor robot localization with day-night cycles\/across different illuminations<\/p>\n
Problem<\/h5>\n
Different illumination\/different spectral cause non-linear intensity changes and make feature matching hard<\/p>\n
Solution<\/h5>\n
Develop a pose invariant feature that is fast, and robust to changes in illumination<\/p>\n
<\/p>\n