Object Tracking and Prediction
- ● Built both location classifier and scale classifier.
- ● Built parallel pipeline for multiple targets tracking.
- ● Conducted test on overlap targets tracking.
- ● Combined Appearance-based tracking with Kalman filter.
- ● Added a work-around approach for handling occlusions.
- ● Calculated and predicted the motion and position when occlusion is assumed.
3D point cloud semantic segmentation
Parsing Point Cloud into Disjoint Spaces
● Detection incorporating void spaces
○ Detecting the peak-gap-peak pattern ○ Merging
● Canonical Coordinate System Among Spaces
Semantic blocks to pixel level boundary segmentation
- ● Enforcing Contextual Consistency using CRF
- ● Updating the Disjoint Space Parsing Results