Sirvi Autor "van Gent, Jan Aare" järgi

Nüüd näidatakse 1 - 2 2

Eesti Rahvusarhiivi digiarhiivi nägude klasterdamine
(2018) van Gent, Jan Aare; Tambet Matiisen
Eesti Rahvusarhiivi kogud sisaldavad sadu tuhandeid digiteeritud pilte, kuid enamik isikuid nendel piltidel on märgendamata. Käsitsi märgendamise lihtsustamiseks pakutakse töös välja automaatse märgendamise süsteem, mis põhineb piltidelt tuvastatud nägudel. Iga leitud näo jaoks leitakse tehisnärvivõrkude abil tunnusvektor ning need tunnusvektorid klasterdatakse eukleidilise kauguse alusel. Töös on realiseeritud süsteemi prototüüp, mis sisaldab näotuvastust, klasterdamist ja märgendite automaatset määramist. Lisaks hinnati klasterdusalgoritmi parameetriks oleva raadiuse mõju tekkivate klastrite ühetaolisusele ja täielikkusele. Samuti hinnati protsessi erinevates etappides kasutatud aja ning mälu sõltuvust piltide arvust. Töö sisaldab ülevaadet näotuvastuse, näopunktide määramise, nägude joondamise, tunnuste eraldamise, klasterdamise ning automaatse märgendamise meetoditest.
Using LiDAR as Camera for End-to-End Driving
(Tartu Ülikool, 2021) van Gent, Jan Aare; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Research on autonomous driving has seen a growing surge in popularity in the last decade. One of the more interesting avenues of autonomous driving, known as end-toend (E2E) driving, involves training a neural network to predict control signals directly from input sensors. Usually, the main sensor used for E2E driving is a regular frontfacing camera. Cameras are the preferred sensor since they can perceive the road and traffic the way humans see it. Additionally, to make self-driving affordable, the sensor set should be relatively simple and cost-effective, which simple front-facing dashcams excel at. However, Light Detection And Ranging (LiDAR) instruments give accurate distance estimations and can be more robust to weather and lighting conditions than regular cameras. In this thesis, the feasibility of using LiDAR as a camera for E2E driving is evaluated. Specifically, the sensor examined is the Ouster OS1-128 LiDAR instrument, which can output measurements as a 360-degree raster image with range, intensity and ambience channels. A convolutional neural network (CNN) was trained to predict steering angles from LiDAR images. In addition, multiple experiments, including varying the data and the network architecture, were performed. The trained models were evaluated with both offline with open-loop metrics and online with closed-loop metrics. The evaluation results confirm that using LiDAR measurements as a raster image (instead of point cloud) allows to make use of the well-tested CNN networks for E2E driving. This means that Ouster OS1-128 lidar can be used as a drop-in replacement for the camera in E2E driving solutions, with potential improvements due to range sensing, less sensitivity to weather and lighting conditions and novel data augmentation opportunities.