Print Email Facebook Twitter Constructing and Evaluating Complex Event-based Datasets for Increasing Performance of Instance Segmentation Models Title Constructing and Evaluating Complex Event-based Datasets for Increasing Performance of Instance Segmentation Models Author Manolache, Alexandru-Dragos (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Pattern Recognition and Bioinformatics) Contributor Tömen, N. (mentor) Strafforello, O. (mentor) Liu, X. (mentor) Cavalcante Siebert, L. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-22 Abstract Event-based cameras represent a new alternative to traditional frame based sensors, with advantages in lower output bandwidth, lower latency and higher dynamic range, thanks to their independent, asynchronous pixels. These advantages prompted the development of computer vision methods on event data in the last decade, however event-based datasets are still in early stages in terms of size and complexity compared to normal datasets (e.g. ImageNet). This paper explores event data augmentation by superimposing two existing event datasets (N-MNIST and N-Caltech101) and by adding uniform noise. It shows that training an instance segmentation model on noisy datasets does not improve its performance, but the amount and type of noise added in the background decreases the performance of such model. Subject Event-based visionEvent-based datasetsEvent-based data augmentationDynamic Vision Sensor To reference this document use: http://resolver.tudelft.nl/uuid:fd7d1ed1-dad1-4c3d-99c5-633ce2764460 Part of collection Student theses Document type bachelor thesis Rights © 2022 Alexandru-Dragos Manolache Files PDF RP_paper_final.pdf 8.89 MB Close viewer /islandora/object/uuid:fd7d1ed1-dad1-4c3d-99c5-633ce2764460/datastream/OBJ/view