{"id":128,"date":"2020-12-22T20:39:58","date_gmt":"2020-12-22T20:39:58","guid":{"rendered":"http:\/\/mscvprojects.ri.cmu.edu\/2020teama\/?page_id=128"},"modified":"2020-12-22T21:27:43","modified_gmt":"2020-12-22T21:27:43","slug":"depth-based-pruning","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/depth-based-pruning\/","title":{"rendered":"Depth Based Pruning"},"content":{"rendered":"\n
\"\"
This represents a case where there is a place where between two time instances there is a low dynamic change (object removal). So if we individually map the scene using ORBSLAM3, the points corresponding to the object would be present in the first case and absent in the second<\/figcaption><\/figure>\n\n\n\n
\"\"
If we are moving in scene 2 but re-use the map from scene 1. The final map generated (after scene 2) would also contain points corresponding to the points on the shelf from scene 1. These points would be present in the map but be absent in the actual scene.<\/figcaption><\/figure>\n\n\n\n
\"\"
This is our strategy of selecting absent points. Keypoints from map are tested with the current depthmap. The depth at the pixel according to the stored map (using geometry) is compared with the actual depthmap value at the expected location. And based on the above conditions, it is marked as absent or not. At the end of the sequence, we will remove all points marked as absent.<\/figcaption><\/figure>\n\n\n\n

Results<\/h3>\n\n\n\n
\n