10.4121/477934dc-4bf9-4e55-9c90-e882ca3dd9f9.v5

URL

Metadata

Robust vision-based lane detection with spatial-temporal deep learning Collection

Yongqi Dong, Haneen Farah, Bart van Arem, Sandeep Patil, Ruohan Li, Hans Hellendoorn,
Robust vision-based lane detection with spatial-temporal deep learningRelevant publications:(1)   Dong, Y., Patil, S., van Arem, B., & Farah, H. (2023). A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection. Computer-Aided Civil and Infrastructure Engineering, 38(1), pp.67–86.(2)   Li, R.#, & Dong, Y.#,* (2023). Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss. IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 12, pp. 14121-14132, DOI: https://doi.org/10.1109/TITS.2023.3305015.(3)   Patil, S.#, Dong, Y.#,*, Farah, H., & Hellendoorn, J. (2023). “Sequential Neural Network Model with Spatial-Temporal Attention Mechanism for Robust Lane Detection Using Multi Continuous Image Frames”, Joint first author and corresponding author, Accepted by the TRB 2023, Preprint.(4)   Automated lane detection through self-supervised pre-training with masked sequential auto-encoders, fine-tuning with customized PolyLoss, and post-processing with clustering and curve fitting (IDF OCT-22-060, N2033551, submitted and filed) [Patent](5)   Spatial-Temporal Attention Integrated Sequential Neural Network Model for Vision-based Robust Lane Detection Using Multi Continuous Image Frames [Software Copyright]

Citation