Improving lane detection with adaptive homography prediction

Chen, Yiman; Xiang, Zhiyu; Du, Wentao

doi:10.1007/s00371-021-02358-1

Cited by 9 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12], HP-Net, a homograph prediction network for lane mark fitting under different slopes, is proposed. Due to the nature of parallel for multiple lanes , the network is trained by reusing the lane labels previously used for the lane marker segmentation task.…”

Section: Prior Structure Information Exploitationmentioning

confidence: 99%

Evaluation of deep-learning based lane detection under low-light environments

2023

International Conference on Computer Vision, Application, and Algorithm (CVAA 2022)

View full text Add to dashboard Cite

Lane detection is an important technology in autonomous driving. Currently, the mainstream lane detection methods are based on deep learning. However, most of deep learning-based lane detection models are trained on images captured on sunny days with enough light. It is concerned about their performance when being used to detect lane lines in low-light environments. In this study, images of lane lines captured in the evening and on rainy days are used to evaluate the performance of a representative LaneNet model. The result shows that the model performed badly when detecting lane lines on rainy days or in the evening. When there is enough lamplight in the evening, the performance of the model is better with part of lane lines being detected, but it still cannot detect correctly as it does on sunny days. Two potential future directions are also proposed in this study.

show abstract

Section: Prior Structure Information Exploitationmentioning

confidence: 99%

Evaluation of deep-learning based lane detection under low-light environments

2023

International Conference on Computer Vision, Application, and Algorithm (CVAA 2022)

View full text Add to dashboard Cite

show abstract

“…However, a difficulty of the traditional inverse perspective is that a fixed transformation matrix is often difficult to adapt to situations such as ramps. The HPnet proposed in [5] can dynamically generate a transformation matrix according to the image. The detection results can be effectively improved by projecting the results output by the SCNN to a bird's-eye view and fitting and outputting them.…”

Section: Traditional Modelsmentioning

confidence: 99%

“…Traditional machine vision al-Information Technology and Control 2023/2/52 298 ways grayscales the image first [16,23,26,27], then uses an edge detection algorithm to extract image edge features [8,16,18,23,26,27], and then uses the Hough transform [8, 16-18, 23, 26, 27, 30] and other methods to obtain the description of the lanes. The researchers use color features to detect lanes [23,31,22], and some researchers use an inverse perspective to solve the difficulty of lane detection caused by the perspective phenomenon [5,9,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lane Detection with Deep Learning: Methods and Datasets

2023

ITC

View full text Add to dashboard Cite

Lane detection problem has been considered as an important computer vision task in autonomous driving. While it has received massive research attention in the literature, the problem is not yet fully solved. In this paper, we present a comprehensive literature review for lane detection, especially those with deep learning models. The latest collection of lane detection datasets is presented. We further fill the research gap by proposing a novel lane detection dataset named MudLane, which focuses on the lane detection task on suburban roads.

show abstract

“…In recent years, lane detection algorithms in complex scenarios have made great progress [ 12 , 13 , 14 ]. Minh et al [ 15 ] proposed an algorithm to improve detection performance mainly by eliminating interference factors (shadows) generated by objects.…”

Section: Introductionmentioning

confidence: 99%

Lane-GAN: A Robust Lane Detection Network for Driver Assistance System in High Speed and Complex Road Conditions

Liu

Wang

et al. 2022

Micromachines

View full text Add to dashboard Cite

Lane detection is an important and challenging part of autonomous driver assistance systems and other advanced assistance systems. The presence of road potholes and obstacles, complex road environments (illumination, occlusion, etc.) are ubiquitous, will cause the blur of images, which is captured by the vision perception system in the lane detection task. To improve the lane detection accuracy of blurred images, a network (Lane-GAN) for lane line detection is proposed in the paper, which is robust to blurred images. First, real and complex blur kernels are simulated to construct a blurred image dataset, and the improved GAN network is used to reinforce the lane features of the blurred image, and finally the feature information is further enriched with a recurrent feature transfer aggregator. Extensive experimental results demonstrate that the proposed network can get robust detection results in complex environments, especially for blurred lane lines. Compared with the SOTA detector, the proposed detector achieves a larger gain. The proposed method can enhance the lane detail features of the blurred image, improving the detection accuracy of the blurred lane effectively, in the driver assistance system in high speed and complex road conditions.

show abstract

Improving lane detection with adaptive homography prediction

Cited by 9 publications

References 33 publications

Evaluation of deep-learning based lane detection under low-light environments

Evaluation of deep-learning based lane detection under low-light environments

Lane Detection with Deep Learning: Methods and Datasets

Lane-GAN: A Robust Lane Detection Network for Driver Assistance System in High Speed and Complex Road Conditions

Contact Info

Product

Resources

About