


Virtual-real domain adaptation method for autonomous driving lane detection and classification
arXiv paper "Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving", May 2022, work at the University of Waterloo, Canada.
While supervised detection and classification frameworks for autonomous driving require large annotated datasets, Unsupervised Domain Adaptation (UDA) driven by synthetic data generated by illuminating real simulated environments , Unsupervised Domain Adaptation) method is a low-cost, less time-consuming solution. This paper proposes a UDA scheme of adversarial discriminative and generative methods for lane line detection and classification applications in autonomous driving.
Also introduces the Simulanes dataset generator, which takes advantage of CARLA's huge traffic scenes and weather conditions to create a natural synthetic dataset. The proposed UDA framework takes the labeled synthetic dataset as the source domain, while the target domain is the unlabeled real data. Use adversarial generation and feature discriminator to debug the learning model and predict the lane location and category of the target domain. Evaluation is performed with real and synthetic datasets.
The open source UDA framework is atgithubcom/anita-hu/sim2real-lane-detection, and the data set generator is at github.com/anita-hu/simulanes.
Real-world driving is diverse, with varying traffic conditions, weather, and surrounding environments. Therefore, the diversity of simulation scenarios is crucial to the good adaptability of the model in the real world. There are many open source simulators for autonomous driving, namely CARLA and LGSVL. This article chooses CARLA to generate the simulation data set. In addition to the flexible Python API, CARLA also contains rich pre-drawn map content covering urban, rural and highway scenes.
Simulation data generator Simulanes generates a variety of simulation scenarios in urban, rural and highway environments, including 15 lane categories and dynamic weather. The figure shows samples from the synthetic dataset. Pedestrian and vehicle participants are randomly generated and placed on the map, increasing the difficulty of the dataset through occlusion. According to the TuSimple and CULane datasets, the maximum number of lanes near the vehicle is limited to 4, and row anchors are used as labels.
Since the CARLA simulator does not directly provide lane location labels, CARLA's waypoint system is used to generate labels. A CARLA waypoint is a predefined position for the vehicle autopilot to follow, located in the center of the lane. In order to obtain the lane position label, the waypoint of the current lane is moved left and right by W/2, where W is the lane width given by the simulator. These moved waypoints are then projected into the camera coordinate system and spline-fitted to generate labels along predetermined row anchor points. The class label is given by the simulator and is one of 15 classes.
To generate a dataset with N frames, divide N evenly across all available maps. From the default CARLA map, towns 1, 3, 4, 5, 7 and 10 were used, while towns 2 and 6 were not used due to differences between the extracted lane position labels and the lane positions of the image. For each map, vehicle participants are spawned at random locations and move randomly. Dynamic weather is achieved by smoothly changing the position of the sun as a sinusoidal function of time and occasionally producing storms, which affect the appearance of the environment through variables such as cloud cover, water volume and standing water. To avoid saving multiple frames at the same location, check if the vehicle has moved from the previous frame's location and regenerate a new vehicle if it has been stationary for too long.
When the sim-to-real algorithm is applied to lane detection, an end-to-end approach is adopted and the Ultra-Fast-Lane-Detection (UFLD) model is used as the basic network. UFLD was chosen because its lightweight architecture can achieve 300 frames/second at the same input resolution while achieving performance comparable to state-of-the-art methods. UFLD formulates the lane detection task as a row-based selection method, where each lane is represented by a series of horizontal positions of predefined rows, i.e., row anchors. For each row anchor, the position is divided into w grid cells. For the i-th lane and j-th row anchor, location prediction becomes a classification problem, where the model outputs the probability Pi,j of selecting (w 1) grid cell. The additional dimension in the output is no lanes.
UFLD proposes an auxiliary segmentation branch to aggregate features at multiple scales to model local features. This is only used during training. With the UFLD method, cross-entropy loss is used for segmentation loss Lseg. For lane classification, a small branch of the fully connected (FC) layer is added to receive the same features as the FC layer for lane position prediction. The lane classification loss Lcls also uses cross-entropy loss.
In order to alleviate the domain drift problem of UDA settings, UNIT ("Unsupervised Image-to-Image Translation Networks", NIPS, 2017) & MUNIT## are adopted #("Multimodal unsupervised image-to-image translation," ECCV 2018) adversarial generation method, and adversarial discriminative method using feature discriminator. As shown in the figure: an adversarial generation method (A) and an adversarial discrimination method (B) are proposed. UNIT and MUNIT are represented in (A), which shows the generator input for image translation. Additional style inputs to MUNIT are shown with dashed blue lines. For simplicity, the MUNIT-style encoder output is omitted as it is not used for image translation.
The above is the detailed content of Virtual-real domain adaptation method for autonomous driving lane detection and classification. For more information, please follow other related articles on the PHP Chinese website!

Harness the Power of On-Device AI: Building a Personal Chatbot CLI In the recent past, the concept of a personal AI assistant seemed like science fiction. Imagine Alex, a tech enthusiast, dreaming of a smart, local AI companion—one that doesn't rely

Their inaugural launch of AI4MH took place on April 15, 2025, and luminary Dr. Tom Insel, M.D., famed psychiatrist and neuroscientist, served as the kick-off speaker. Dr. Insel is renowned for his outstanding work in mental health research and techno

"We want to ensure that the WNBA remains a space where everyone, players, fans and corporate partners, feel safe, valued and empowered," Engelbert stated, addressing what has become one of women's sports' most damaging challenges. The anno

Introduction Python excels as a programming language, particularly in data science and generative AI. Efficient data manipulation (storage, management, and access) is crucial when dealing with large datasets. We've previously covered numbers and st

Before diving in, an important caveat: AI performance is non-deterministic and highly use-case specific. In simpler terms, Your Mileage May Vary. Don't take this (or any other) article as the final word—instead, test these models on your own scenario

Building a Standout AI/ML Portfolio: A Guide for Beginners and Professionals Creating a compelling portfolio is crucial for securing roles in artificial intelligence (AI) and machine learning (ML). This guide provides advice for building a portfolio

The result? Burnout, inefficiency, and a widening gap between detection and action. None of this should come as a shock to anyone who works in cybersecurity. The promise of agentic AI has emerged as a potential turning point, though. This new class

Immediate Impact versus Long-Term Partnership? Two weeks ago OpenAI stepped forward with a powerful short-term offer, granting U.S. and Canadian college students free access to ChatGPT Plus through the end of May 2025. This tool includes GPT‑4o, an a


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

Safe Exam Browser
Safe Exam Browser is a secure browser environment for taking online exams securely. This software turns any computer into a secure workstation. It controls access to any utility and prevents students from using unauthorized resources.

WebStorm Mac version
Useful JavaScript development tools

SAP NetWeaver Server Adapter for Eclipse
Integrate Eclipse with SAP NetWeaver application server.

MinGW - Minimalist GNU for Windows
This project is in the process of being migrated to osdn.net/projects/mingw, you can continue to follow us there. MinGW: A native Windows port of the GNU Compiler Collection (GCC), freely distributable import libraries and header files for building native Windows applications; includes extensions to the MSVC runtime to support C99 functionality. All MinGW software can run on 64-bit Windows platforms.

Atom editor mac version download
The most popular open source editor