A review of lane detection methods based on deep learning

•This work is the _rst overall review of recent deep learning-based lane detection methods.•Detailed description of representive methods from perpective of computer vision and pattern recognition.•Detailed description of convolution neural networks' architectures and loss functions that used in...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition Ročník 111; s. 107623
Hlavní autoři: Tang, Jigang, Li, Songbin, Liu, Peng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.03.2021
Témata:
Deep learning
Instance segmentation
Lane detection
Semantic segmentation
Deep learning
Instance segmentation
Lane detection
Semantic segmentation
ISSN:0031-3203, 1873-5142
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•This work is the _rst overall review of recent deep learning-based lane detection methods.•Detailed description of representive methods from perpective of computer vision and pattern recognition.•Detailed description of convolution neural networks' architectures and loss functions that used in lanes detector.•Advantages of deep learning-based methods compared with traditional heuristic recognition-based methods.•Current challenges of existing deep learning-based methods and some possible directions to solve the problems. Lane detection is an application of environmental perception, which aims to detect lane areas or lane lines by camera or lidar. In recent years, gratifying progress has been made in detection accuracy. To the best of our knowledge, this paper is the first attempt to make a comprehensive review of vision-based lane detection methods. First, we introduce the background of lane detection, including traditional lane detection methods and related deep learning methods. Second, we group the existing lane detection methods into two categories: two-step and one-step methods. Around the above summary, we introduce lane detection methods from the following two perspectives: (1) network architectures, including classification and object detection-based methods, end-to-end image-segmentation based methods, and some optimization strategies; (2) related loss functions. For each method, its contributions and weaknesses are introduced. Then, a brief comparison of representative methods is presented. Finally, we conclude this survey with some current challenges, such as expensive computation and the lack of generalization. And we point out some directions to be further explored in the future, that is, semi-supervised learning, meta-learning and neural architecture search, etc.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2020.107623