Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit

By Xiang-Yang Li, Jun Yu Li, Xiaolin Hu, Jian Yang. IEEE transactions on intelligent transportation systems (Print), 2020

321 citations recorded by the source corpus.

The task of traffic line detection is a fundamental yet challenging problem. Previous approaches usually conduct traffic line detection via a two-stage way, namely the line segment detection followed by a segment clustering, which is very likely to ignore the global semantic information of an entire line. To address the problem, we propose an end-to-end system called Line-CNN (L-CNN), in which the key component is a novel line proposal unit (LPU). The LPU utilizes line proposals as references to locate accurate traffic curves, which forces the system to learn the global feature representation of the entire traffic lines. We benchmark the proposed L-CNN on two public datasets including MIKKI and TuSimple, and the results suggest that L-CNN outperforms the state-of-the-art methods. In addition, L-CNN can run at approximately 30 f/s on a Titan X GPU, which indicates the practicability and effectiveness of L-CNN for real-time intelligent self-driving systems.

Subfields: Automotive Engineering, Civil and Structural Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/954e2e2f4821ecb6a4fe676760a11302fc727f89

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

1. Yicheng Liu
2. Xiaodan Liang
3. Hang Zhao

In Civil and Structural Engineering

1. Zhenguo Li

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Xiaodan Liang
3. Luc Van Gool
4. Ming-Hsuan Yang
5. Xiaogang Wang
6. Yi Yang
7. Alan L. Yuille
8. Shuicheng Yan

Citations in the corpus

• PolyLaneNet: Lane Estimation via Deep Polynomial Regression (2020, methodology): “After that, in [8], the authors proposed Line-CNN, a model in which the key component is the line proposal unit (LPU) adapted from the region proposal network (RPN) of Faster R-CNN.”
• End-to-end Lane Shape Prediction with Transformers (2020, methodology): “Line-CNN [8] transfers the success of Faster-RCNN [16] into lane detection by predicting offsets based on pre-designed straight rays (like anchor boxes), which achieves state-of-the-art accuracy.”
• Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection (2020, methodology): “Hence, some recent works have proposed solutions in other directions [13, 23].”
• CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending (2020, methodology): “Line-CNN [14] introduces a line proposal network to propose a set of ray aiming to capture the actual lane.”
• CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution (2021, unknown): “Another approach is anchor-based methods [25, 22, 39].”
• CLRNet: Cross Layer Refinement Network for Lane Detection (2022, methodology): “Line-CNN [8] is the pioneering work to use line anchors in lane detection.”
• VectorMapNet: End-to-end Vectorized HD Map Learning (2022, background): “, 2019), line segments (Li et al., 2019), and Bézier curves (Feng et al.”