自動運転における車線検出のためのリアルタイム完全教師なしドメイン適応
Real-Time Fully Unsupervised Domain Adaptation for Lane Detection in Autonomous Driving
バッチ正規化パラメータのみを適応させる軽量な教師なし手法により、Nvidia Jetson Orin上で30FPSを維持しながら車線検出のドメイン適応を実現した。
著者: Kshitij Bhardwaj, Zishen Wan, Arijit Raychowdhury, Ryan Goldhahn
分類: cs.CV, cs.RO
原文アブストラクト
While deep neural networks are being utilized heavily for autonomous driving, they need to be adapted to new unseen environmental conditions for which they were not trained. We focus on a safety critical application of lane detection, and propose a lightweight, fully unsupervised, real-time adaptation approach that only adapts the batch-normalization parameters of the model. We demonstrate that our technique can perform inference, followed by on-device adaptation, under a tight constraint of 30 FPS on Nvidia Jetson Orin. It shows similar accuracy (avg. of 92.19%) as a state-of-the-art semi-supervised adaptation algorithm but which does not support real-time adaptation.
