Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss

Y. Dong, Ruohan Li, H. Farah

Research output: Contribution to conferencePosterScientific

15 Downloads (Pure)


Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the valuable features and aggregate contextual information, especially
the interrelationships between lane lines and other regions of the images in continuous frames. To fill this research gap and upgrade lane detection performance, this paper proposes a pipeline consisting of self pre-training with masked sequential autoencoders and fine-tuning with customized PolyLoss for the end-to-end neural network models using multi-continuous image frames. The masked sequential autoencoders are adopted to pretrain the neural network models with reconstructing the missing pixels from a random masked image as the objective. Then, in the fine-tuning segmentation phase where lane detection segmentation is performed, the continuous image frames are served as the inputs, and the pre-trained model weights are transferred and further updated using the backpropagation mechanism with
customized PolyLoss calculating the weighted errors between the output lane detection results and the labeled ground truth. Extensive experiment results demonstrate that, with the proposed pipeline, the lane detection model performance on both normal and challenging scenes can be advanced beyond the state-of-the art results, while the training time can be substantially shortened.
Original languageEnglish
Number of pages1
Publication statusPublished - 2023
EventThe 102nd Annual Meeting Transportation Research Board - Mt Vernon Convention Center, Washington DC, United States
Duration: 8 Jan 202312 Jan 2023
Conference number: 102


ConferenceThe 102nd Annual Meeting Transportation Research Board
Country/TerritoryUnited States
CityWashington DC
Internet address


Dive into the research topics of 'Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss'. Together they form a unique fingerprint.

Cite this