Multi-lane Detection Using Instance Segmentation and Attentive Voting

Chang, Donghoon; Chirakkal, Vinjohn V; Goswami, Shubham; Hasan, Munawar; Jung, Taekwon; Kang, Jinkeon; Kee, Seok-Cheol; Lee, Dongkyu; Singh, Ajit Pratap

doi:10.23919/iccas47443.2019.8971488

Cited by 20 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the preprocessing of input frames in [75] involves removing most of the sky region and performing the automobile dashboard. The frame is then scaled to a resolution of 360 × 480.…”

Section: Ii) Deep Learning + Geometric Modellingmentioning

confidence: 99%

“…TuSimple [75], KITTI, Caltech, Cityscapes, ApolloScape, and CULane datasets are online road scene datasets or benchmarks that provide training data for various uses. In this section, several popular public datasets will be discussed.…”

Section: What Was the Dataset Used For The Network Training Validatio...mentioning

confidence: 99%

“…The TuSimple dataset is a publicly available traffic-detection data set (light traffic and clear lane markings). Its label for the training dataset consists of continuous lane curves that start at the bottom of the input image and continue until the horizon VOLUME 11, 2023 passes over the vehicles [75]. It consists of large datasets with training, and the testing number is 326 and 2782 in both bad and excellent weather conditions, respectively [35].…”

Section: ) Tusimple Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Lane Detection in Autonomous Vehicles: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

One of the essential systems in autonomous vehicles for ensuring a secure circumstance for drivers and passengers is the Advanced Driver Assistance System (ADAS). Adaptive Cruise Control, Automatic Braking/Steer Away, Lane-Keeping System, Blind Spot Assist, Lane Departure Warning System, and Lane Detection are examples of ADAS. Lane detection displays information specific to the geometrical features of lane line structures to the vehicle's intelligent system to show the position of lane markings. This article reviews the methods employed for lane detection in an autonomous vehicle. A systematic literature review (SLR) has been carried out to analyze the most delicate approach to detecting the road lane for the benefit of the automation industry. One hundred and two publications from well-known databases were chosen for this review. The trend was discovered after thoroughly examining the selected articles on the method implemented for detecting the road lane from 2018 until 2021. The selected literature used various methods, with the input dataset being one of two types: self-collected or acquired from an online public dataset. In the meantime, the methodologies include geometric modeling and traditional methods, while AI includes deep learning and machine learning. The use of deep learning has been increasingly researched throughout the last four years. Some studies used stand-alone deep learning implementations for lane detection problems. Meanwhile, some research focuses on merging deep learning with other machine learning techniques and classical methodologies. Recent advancements imply that attention mechanism has become a popular combined strategy with deep learning methods. The use of deep algorithms in conjunction with other techniques showed promising outcomes. This research aims to provide a complete overview of the literature on lane detection methods, highlighting which approaches are currently being researched and the performance of existing state-of-the-art techniques. Also, the paper covered the equipment used to collect the dataset for the training process and the dataset used for network training, validation, and testing. This review yields a valuable foundation on lane detection techniques, challenges, and opportunities and supports new research works in this automation field. For further study, it is suggested to put more effort into accuracy improvement, increased speed performance, and more challenging work on various extreme conditions in detecting the road lane.

show abstract

“…First, the preprocessing of input frames in [75] involves removing most of the sky region and performing the automobile dashboard. The frame is then scaled to a resolution of 360 × 480.…”

Section: Ii) Deep Learning + Geometric Modellingmentioning

confidence: 99%

Section: What Was the Dataset Used For The Network Training Validatio...mentioning

confidence: 99%

Section: ) Tusimple Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Lane Detection in Autonomous Vehicles: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The most widely used lane detection approach in imagebased deep learning is segmentation-based lane detection [17,18,10,7,14,15,2,16,3]. These works learn in an end-to-end manner whether each pixel of the image represents the lane.…”

Section: Introductionmentioning

confidence: 99%

Robust Lane Detection via Expanded Self Attention

Lee

et al. 2022

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

The image-based lane detection algorithm is one of the key technologies in autonomous vehicles. Modern deep learning methods achieve high performance in lane detection, but it is still difficult to accurately detect lanes in challenging situations such as congested roads and extreme lighting conditions. To be robust on these challenging situations, it is important to extract global contextual information even from limited visual cues. In this paper, we propose a simple but powerful self-attention mechanism optimized for lane detection called the Expanded Self Attention (ESA) module. Inspired by the simple geometric structure of lanes, the proposed method predicts the confidence of a lane along the vertical and horizontal directions in an image. The prediction of the confidence enables estimating occluded locations by extracting global contextual information. ESA module can be easily implemented and applied to any encoder-decoder-based model without increasing the inference time. The performance of our method is evaluated on three popular lane detection benchmarks (TuSimple, CULane and BDD100K). We achieve state-of-the-art performance in CULane and BDD100K and distinct improvement on TuSimple dataset. The experimental results show that our approach is robust to occlusion and extreme lighting conditions.

show abstract

“…11 The fact that the features obtained by Convolutional Neural Network (CNN) through limited field of view are not sufficient to simulate content that is too far apart. There are also some methods 12,13 to extract rich context without external consumption, and then define lane detection as a mask, 3 mark, 14 and grid 15 semantic segmentation problem, and introduce piece-by-piece convolutions into feature maps so that message transmission can be achieved without additional scene annotations. For some anchor-based methods, 16,17 due to the fixed shape and complex design of the anchor, the prediction line is not flexible, 18 usually only focusing on specific structural information, resulting in the structure not fully functioning and unable to capture the curvature along the curve lane.…”

Section: Introductionmentioning

confidence: 99%

An improved real-time model for divergent and dense lane detection of unmanned vehicles

Zhang

Huang

Zhou³

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Lane detection is the key technology of an advanced driver assistance system. This study proposed an efficient and novel lane detection method, Lane Kernel Parameter Module ResNet-18 (LKPM-ResNet-18), to improve the detection efficiency of lane with complex topologies (such as divergent lines and dense lines). This method can precisely predict the global structure in a bottom-up manner and directly output the curve parameters of the lane alignment model. In addition, LKPM was used to obtain accurately the local structure information and the slender shape of the lane with complex topology, and then the shape convolution kernel parameters of each instance are dynamically predicted to optimize the results of the subsequent output curves. Finally, the prior information of the global lane is fully integrated through the lane structure constraint loss, and the optimization results are fused into the global geometric curve fitting output, so that the fitted lanes are smoother and more continuous. The method proposed has real-time detection efficiency and requires little postprocessing because of the end-to-end direct approach. The validated results show that the efficiency of this method is obviously better than that of State-Of-The-Art (SOTA) methods, such as PointLaneNet and ENet-SAD. The F1 scores increase by 0.43% and 4.92%, respectively compared with the latest CurveLanes-NAS-L and SCNN on the CULane test dataset. The accuracy of 88.98% can be obtained on the CurveLanes test dataset. Meanwhile, the result from real driving environment detection exceeds the top performances of the other by 2.22% with the accuracy of 86.47%.

show abstract

Multi-lane Detection Using Instance Segmentation and Attentive Voting

Cited by 20 publications

References 18 publications

Lane Detection in Autonomous Vehicles: A Systematic Review

Lane Detection in Autonomous Vehicles: A Systematic Review

Robust Lane Detection via Expanded Self Attention

An improved real-time model for divergent and dense lane detection of unmanned vehicles

Contact Info

Product

Resources

About