Reliable Multilane Detection and Classification by Utilizing CNN as a Regression Network

Chougule, Shriyash; Koznek, Nora; Ismail, Asad; Adam, Ganesh; Narayan, Vikram; Schulze, Matthias

doi:10.1007/978-3-030-11021-5_46

Cited by 35 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Regression losses: When the output of a deep learner is expected to be continuous, regression losses are more suitable compared with those classification ones mentioned in section III-A1. In lane marking detection, the most commonly used regression losses are the mean squared error (MSE) [53], [59], [64], [75], [77]- [79], mean absolute error (MAE) [54], [79], [80], and Huber loss defined as…”

Section: Representative Objective Functionsmentioning

confidence: 99%

“…The coordinate network proposed by [54] can directly produce classified lane marking points. The MAE loss function is implemented to characterize the distance between predicted coordinates (xp, yp) and ground truth (xg, yg) (Table IV (2)).…”

Section: B Deep Architecture Focusing On Lane Marking Classificationmentioning

confidence: 99%

“…PointLaneNet [64] also treats lane marking detection as a regression task. Compared with [54], PointLaneNet considers more dense points including starting point, ending point (the bottom of images by default), lane marking center point and lane width (a known value according to laws and regulations) to infer disappeared lane marking features during multiple downsampling. The structure of PointLaneNet is shown in Fig.…”

Section: B Deep Architecture Focusing On Lane Marking Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning in Lane Marking Detection: A Survey

Zhang

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Lane marking detection is a fundamental but crucial step in intelligent driving systems. It can not only provide relevant road condition information to prevent lane departure but also assist vehicle positioning and forehead car detection. However, lane marking detection faces many challenges, including extreme lighting, missing lane markings, and obstacle obstructions. Recently, deep learning-based algorithms draw much attention in intelligent driving society because of their excellent performance. In this paper, we review deep learning methods for lane marking detection, focusing on their network structures and optimization objectives, the two key determinants of their success. Besides, we summarize existing lane-related datasets, evaluation criteria, and common data processing techniques. We also compare the detection performance and running time of various methods, and conclude with some current challenges and future trends for deep learning-based lane marking detection algorithm.

show abstract

Section: Representative Objective Functionsmentioning

confidence: 99%

Section: B Deep Architecture Focusing On Lane Marking Classificationmentioning

confidence: 99%

Section: B Deep Architecture Focusing On Lane Marking Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning in Lane Marking Detection: A Survey

Zhang

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…However, the performance of LaneNet relies on some post-processing parts of the network for pixel embedding and curve fitting, and thus is in turn largely affected by the LaneNet's segmentation part, which also cannot cope well with the challenging scenes of partial lane information above-mentioned for SCNN. In [28], it was suggested that a segmentation approach is not effective for detecting elongated thin lane boundaries, and thus the lane detection problem was posed as a CNN regression task to predict the coordinates of 15 points on each lane line. However, it is not practical to report only the points as the result of lane line prediction, and the number and size of points all affect the training of the network.…”

Section: Closely-related Work a Semantic Segmentationmentioning

confidence: 99%

Ripple-GAN: Lane Line Detection With Ripple Lane Line Detection Network and Wasserstein GAN

Zhang

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

With artificial intelligence technology being advanced by leaps and bounds, intelligent driving has attracted a huge amount of attention recently in research and development. In intelligent driving, lane line detection is a fundamental but challenging task particularly under complex road conditions. In this paper, we propose a simple yet appealing network called Ripple Lane Line Detection Network (RiLLD-Net), to exploit quick connections and gradient maps for effective learning of lane line features. RiLLD-Net can handle most common scenes of lane line detection. Then, in order to address challenging scenarios such as occluded or complex lane lines, we propose a more powerful network called Ripple-GAN, by integrating RiLLD-Net, confrontation training of Wasserstein generative adversarial networks, and multi-target semantic segmentation. Experiments show that, especially for complex or obscured lane lines, Ripple-GAN can produce a superior detection performance to other state-of-the-art methods.

show abstract

“…In [11,12,13,14], fully-convolutional networks are used to obtain a pixelwise representation of lane boundaries. A slightly different approach is proposed in [15], where a CNN is used to estimate polylines points, in order to solve fragmentation issues that often occurr in segmentation networks. They classify the obtained boundaries, but only in terms of position w.r.t.…”

Section: Introductionmentioning

confidence: 99%

Lane Detection and Classification Using Cascaded CNNs

Pizzati

Allodi

Barrera

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Lane detection is extremely important for autonomous vehicles. For this reason, many approaches use lane boundary information to locate the vehicle inside the street, or to integrate GPS-based localization. As many other computer vision based tasks, convolutional neural networks (CNNs) represent the state-of-the-art technology to indentify lane boundaries. However, the position of the lane boundaries w.r.t. the vehicle may not suffice for a reliable positioning, as for path planning or localization information regarding lane types may also be needed. In this work, we present an end-to-end system for lane boundary identification, clustering and classification, based on two cascaded neural networks, that runs in real-time. To build the system, 14336 lane boundaries instances of the TuSimple dataset for lane detection have been labelled using 8 different classes. Our dataset and the code for inference are available online.

show abstract

Reliable Multilane Detection and Classification by Utilizing CNN as a Regression Network

Cited by 35 publications

References 24 publications

Deep Learning in Lane Marking Detection: A Survey

Deep Learning in Lane Marking Detection: A Survey

Ripple-GAN: Lane Line Detection With Ripple Lane Line Detection Network and Wasserstein GAN

Lane Detection and Classification Using Cascaded CNNs

Contact Info

Product

Resources

About