A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.
2D Feature Tracking project using OpenCV detectors and descriptors for keypoint tracking in multiple frames. The project uses a variety of detectors and descriptors and performs analysis of the best possible combination with regards to processing time and detection precision.
The Kanade-Lucas-Tomasi (KLT) Feature Tracker algorithm estimates the 2D translation and scale changes of an image template between original template coordinates and a given reference image using the Inverse Compositional algorithm.