Sirvi Autor "Ploter, Maksim" järgi

Nüüd näidatakse 1 - 1 1

Eyes Wide Shut: Analyzing Object Detection Performance Under Degraded Sensor Input Scenarios
(Tartu Ülikool, 2025) Ploter, Maksim; Matiisen, Tambet, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
Autonomous Driving Systems (ADS) promise safer roads, better traffic flow, and reduced environmental impact. The Society of Automotive Engineers (SAE) International’s J3016 standard [1] stipulates stringent safety requirements for ADS, particularly concerning their operational behavior during dynamic driving task performance-relevant system failures. The perception task, which includes the fundamental computer vision task of object detection, is a key capability that distinguishes ADS from a “regular” vehicle. In the last decade, there has been remarkable progress in various computer vision tasks, and the object detection task in particular. However, many contemporary state-of-the-art models are specialists, with strong inductive biases for specific data types, making them difficult, if not impossible, to use for ADS. To address this limitation, the thesis introduces two novel recurrent architectures: the Recurrent Perceiver (RPerceiver) and its multi-modal variant, the Recurrent Perceiver Multi-Modal (RPerceiverMM). The efficacy of these architectures was evaluated on a novel benchmark dataset, ”detectionmoving-mnist-easy”, proposed in this thesis. The experimental results suggest the proposed models’ effectiveness in leveraging temporal information, particularly in challenging cases such as objects that are partially visible while leaving the video frame. Furthermore, this research investigated specific training procedures designed to simulate complete sensor failures and non-deterministic data availability. The findings indicate that these proposed training strategies significantly improve model robustness, demonstrating enhanced performance when faced with conditions analogous to real-world ADS sensor system failures. This work contributes to the development of more resilient perception systems crucial for the safe deployment of ADS. The code was open-sourced at GitHub 1.