Contrastive Learning for Lane Detection via Cross-Similarity
- URL: http://arxiv.org/abs/2308.08242v3
- Date: Fri, 1 Sep 2023 08:12:30 GMT
- Title: Contrastive Learning for Lane Detection via Cross-Similarity
- Authors: Ali Zoljodi, Sadegh Abadijou, Mina Alibeigi, Masoud Daneshtalab
- Abstract summary: Lane markings have strong shape priors, but their visibility is easily compromised.
A large amount of data is required to train a lane detection approach that can withstand natural variations caused by low visibility.
Our solution, Contrastive Learning for Lane Detection via cross-similarity (CLLD), is a self-supervised learning method.
- Score: 0.5735035463793009
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Detecting road lanes is challenging due to intricate markings vulnerable to
unfavorable conditions. Lane markings have strong shape priors, but their
visibility is easily compromised. Factors like lighting, weather, vehicles,
pedestrians, and aging colors challenge the detection. A large amount of data
is required to train a lane detection approach that can withstand natural
variations caused by low visibility. This is because there are numerous lane
shapes and natural variations that exist. Our solution, Contrastive Learning
for Lane Detection via cross-similarity (CLLD), is a self-supervised learning
method that tackles this challenge by enhancing lane detection models
resilience to real-world conditions that cause lane low visibility. CLLD is a
novel multitask contrastive learning that trains lane detection approaches to
detect lane markings even in low visible situations by integrating local
feature contrastive learning (CL) with our new proposed operation
cross-similarity. Local feature CL focuses on extracting features for small
image parts, which is necessary to localize lane segments, while
cross-similarity captures global features to detect obscured lane segments
using their surrounding. We enhance cross-similarity by randomly masking parts
of input images for augmentation. Evaluated on benchmark datasets, CLLD
outperforms state-of-the-art contrastive learning, especially in
visibility-impairing conditions like shadows. Compared to supervised learning,
CLLD excels in scenarios like shadows and crowded scenes.
Related papers
- LDTR: Transformer-based Lane Detection with Anchor-chain Representation [11.184960972042406]
Lane detection scenarios with limited- or no-visual-clue of lanes remain challenging and crucial for automated driving.
Inspired by the DETR architecture, we propose LDTR, a transformer-based model to address these issues.
Experimental results demonstrate that LDTR achieves state-of-the-art performance on well-known datasets.
arXiv Detail & Related papers (2024-03-21T12:29:26Z) - Sketch and Refine: Towards Fast and Accurate Lane Detection [69.63287721343907]
Lane detection is a challenging task due to the complexity of real-world scenarios.
Existing approaches, whether proposal-based or keypoint-based, suffer from depicting lanes effectively and efficiently.
We present a "Sketch-and-Refine" paradigm that utilizes the merits of both keypoint-based and proposal-based methods.
Experiments show that our SRLane can run at a fast speed (i.e., 278 FPS) while yielding an F1 score of 78.9%.
arXiv Detail & Related papers (2024-01-26T09:28:14Z) - Decoupling the Curve Modeling and Pavement Regression for Lane Detection [67.22629246312283]
curve-based lane representation is a popular approach in many lane detection methods.
We propose a new approach to the lane detection task by decomposing it into two parts: curve modeling and ground height regression.
arXiv Detail & Related papers (2023-09-19T11:24:14Z) - LVLane: Deep Learning for Lane Detection and Classification in
Challenging Conditions [2.5641096293146712]
We present an end-to-end lane detection and classification system based on deep learning methodologies.
In our study, we introduce a unique dataset meticulously curated to encompass scenarios that pose significant challenges for state-of-the-art (SOTA) lane localization models.
We propose a CNN-based classification branch, seamlessly integrated with the detector, facilitating the identification of distinct lane types.
arXiv Detail & Related papers (2023-07-13T16:09:53Z) - Vision-Based Robust Lane Detection and Tracking under Different
Challenging Environmental Conditions [8.312192184427762]
Lane marking detection is fundamental for both advanced driving assistance systems.
Here, we propose a robust lane detection and tracking method with three key technologies.
Experimental results show that the average detection rate is 97.55%, and the average processing time is 22.33 msec/frame.
arXiv Detail & Related papers (2022-10-19T01:25:21Z) - Repainting and Imitating Learning for Lane Detection [52.5220065495956]
Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows.
We propose a novel Repainting and Imitating Learning framework containing a pair of teacher and student.
Our method introduces no extra time cost during inference and can be plug-and-play in various cutting-edge lane detection networks.
arXiv Detail & Related papers (2022-10-11T02:26:39Z) - RCLane: Relay Chain Prediction for Lane Detection [76.62424079494285]
We present a new method for lane detection based on relay chain prediction.
Our strategy allows us to establish new state-of-the-art on four major benchmarks including TuSimple, CULane, CurveLanes and LLAMAS.
arXiv Detail & Related papers (2022-07-19T16:48:39Z) - Semantically Contrastive Learning for Low-light Image Enhancement [48.71522073014808]
Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images.
We propose an effective semantically contrastive learning paradigm for LLE (namely SCL-LLE)
Our method surpasses the state-of-the-arts LLE models over six independent cross-scenes datasets.
arXiv Detail & Related papers (2021-12-13T07:08:33Z) - Preprocessing Methods of Lane Detection and Tracking for Autonomous
Driving [0.0]
Real time lane detection and tracking (LDT) is one of the most consequential parts to performing the above tasks.
In this paper, we survey preprocessing methods for detecting lane marking as well as tracking lane boundaries in real time focusing on vision-based system.
arXiv Detail & Related papers (2021-04-10T13:03:52Z) - Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle
Re-Identification [53.6218051770131]
Cross-view consistent feature representation is key for accurate vehicle ReID.
Existing approaches resort to supervised cross-view learning using extensive extra viewpoints annotations.
We present a pluggable Weakly-supervised Cross-View Learning (WCVL) module for vehicle ReID.
arXiv Detail & Related papers (2021-03-09T11:51:09Z) - Lane Detection Model Based on Spatio-Temporal Network With Double
Convolutional Gated Recurrent Units [11.968518335236787]
Lane detection will remain an open problem for some time to come.
A-temporal network with double Conal Gated Recurrent Units (ConvGRUs) proposed to address lane detection in challenging scenes.
Our model can outperform the state-of-the-art lane detection models.
arXiv Detail & Related papers (2020-08-10T06:50:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.