Self-supervised learning has been an active area of research in the past few years. Contrastive learning is a type of selfsupervised learning method that has achieved a significant performance improvement on image classification task. However, there has been no work done in its application to fisheye images for autonomous driving. In this paper, we propose FisheyePixPro, which is an adaption of pixel level contrastive learning method PixPro [1] for fisheye images. This is the first attempt to pretrain a contrastive learning based model, directly on fisheye images in a self-supervised approach. We evaluate the performance of learned representations on the WoodScape dataset using segmentation task. Our FisheyePixPro model achieves a 65.78 mIoU score, a significant improvement over the PixPro model. This indicates that pre-training a model on fisheye images have a better performance on a downstream task.
Lane detection and modelling is a crucial module in autonomous driving which enables the vehicle to drive within the ego lane. Typically, CNN based semantic segmentation is used to segment lane markings and then a post processing algorithm fits polynomial models for the lanes based on the road geometry. Recently, direct regression of the lane polynomials were explored but it is still not a mature solution. In this paper, we propose a combination of deep learning based semantic segmentation and a graphical model based lane fitting. We use conditional random fields (CRFs) to effectively fit lane polynomials in the presence of noisy segmentation maps. The proposed method provides an accuracy improvement of 15% relatively to the conventional post processing baseline.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.