Data association for object-based SLAM

Sammanfattning: The thesis tackles the problem of data association for monocular object-basedSLAM, which gets often omitted in related works. A method for estimating ellipsoid object landmark representations is implemented. This method uses bounding box multi-view object detections from 2D images with the help ofYOLOv3 object detector and ORB-SLAM2 for camera pose estimation. The online data association uses SIFT image feature matching and landmark back projection matching against bounding box detections to associate these object detections. This combination and its evaluation is the main contribution of the thesis. The overall algorithm is tested on several datasets, both real-world and computer rendered. The association algorithm manages well on the tested sequences and it is shown that matching with the back projections of the ellipsoid landmarks improves the robustness of the approach. It is shown that with some implementation changes, the algorithm can run at real-time. The landmark estimation part works satisfactory for landmark initialization. Based on the findings future work is proposed.