Analyzing performance effects of neural networks applied to lane recognition under various environmental driving conditions

Ortegon-Sarmiento, T., Kelouwani, S., Alam, M. Z., Uribe-Quevedo, A., Amamou, A., Paderewski-Rodriguez, P. et Gutierrez-Vela, F. (2022). Analyzing performance effects of neural networks applied to lane recognition under various environmental driving conditions. World Electric Vehicle Journal, 13 (10). p. 191. ISSN 2032-6653 DOI 10.3390/wevj13100191

Prévisualisation

PDF Disponible sous licence Creative Commons Attribution. Télécharger (22MB) | Prévisualisation

Résumé

Lane detection is an essential module for the safe navigation of autonomous vehicles (AVs). Estimating the vehicle’s position and trajectory on the road is critical; however, several environmental variables can affect this task. State-of-the-art lane detection methods utilize convolutional neural networks (CNNs) as feature extractors to obtain relevant features through training using multiple kernel layers. It makes them vulnerable to any statistical change in the input data or noise affecting the spatial characteristics. In this paper, we compare six different CNN architectures to analyze the effect of various adverse conditions, including harsh weather, illumination variations, and shadows/occlusions, on lane detection. Among all the aforementioned adverse conditions, harsh weather in general and snowy night conditions particularly affect the performance by a large margin. The average detection accuracy of the networks decreased by 75.2%, and the root mean square error (RMSE) increased by 301.1%. Overall, the results show a noticeable drop in the networks’ accuracy for all adverse conditions because the features’ stochastic distributions change for each state.

Type de document:	Article
Mots-clés libres:	Autonomous vehicles Benchmark Lane detection Pre-trained networks Transfer learning
Date de dépôt:	22 mai 2024 18:12
Dernière modification:	22 mai 2024 18:12
Version du document déposé:	Version officielle de l'éditeur
URI:	https://depot-e.uqtr.ca/id/eprint/11316

Actions (administrateurs uniquement)

Éditer la notice