computer-vision-1

Drivable Area Detection

3260 papers • 126 benchmarks • 313 datasets

The drivable area detection is a subset topic of object detection. The model marks the safe and legal roads for regular driving in color blocks shaped by area.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in drivable-area-detection-1

Trend

Dataset

Best Model

Actions

BDD100K val

Libraries

i

Use these libraries to find drivable-area-detection-1 models and implementations

Datasets

BDD100K

Subtasks

No subtasks available.

Most implemented papers

YOLOP: You Only Look Once for Panoptic Driving Perception

Xinggang Wang, X. Bai, Wenqing Cheng, Dongsheng Wu, Man-Wen Liao, Wei-Tian Zhang, Wen-Yu Liu•Tue Aug 24 2021

To the best knowledge, this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS), and maintain excellent accuracy.

391

Content

0

Paper Graph

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Trevor Darrell, F. Yu, Haofeng Chen, Xin Wang, Wenqi Xian, Yingying Chen, Fangchen Liu, Vashisht Madhavan•Fri May 11 2018

This work constructs BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving and shows that special training strategies are needed for existing models to perform such heterogeneous tasks.

2531 0

Paper Graph

HybridNets: End-to-End Perception Network

H. Phan, Dat Vu, Bao Ngo•Wed Mar 16 2022

An end-to-end perception network to perform multitasking, including traffic object detection, drivable area segmentation and lane detection simultaneously, called HybridNets, which achieves better accuracy than prior art and is a practical and accurate solution to the multitasking problem.

113 0

Paper Graph

YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception

Qichao Zhao, Shuyi Zhang, Yinzi Chen, Zhenlin Zhang, Jinwei Yuan•Tue Aug 23 2022

This paper proposed an effective and efficient multi-task learning network to simultaneously perform the task of traffic object detection, drivable road area segmentation and lane detection and achieved the new state-of-the-art SOTA performance in terms of accuracy and speed on the challenging BDD100K dataset.

98 0

Paper Graph

TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars

Minh Pham, Huy Che Quang, Dinh Phuc Nguyen, D. Lam•Wed Jul 19 2023

This paper proposes a lightweight model for the driveable area and lane line segmentation, TwinLiteNet, designed cheaply but achieves accurate and efficient segmentation results, and can run in real-time on embedded devices with limited computing power.

27 0

Paper Graph

You Only Look at Once for Real-Time and Generic Multi-Task

Graduate Student Member Ieee Jiayuan. Wang, S. M. I. Q. M. Jonathan Wu, Senior Member Ieee Ning Zhang, Q. M. Jonathan, Wu Wang•Sun Oct 01 2023

This study incorporates A-YOLOM, an adaptive, real-time, and lightweight multi-task model designed to concurrently address object detection, drivable area segmentation, and lane line segmentation tasks, and develops an end-to-end multi-task model with a unified and streamlined segmentation structure.

57 0

Paper Graph

Adding a benchmark result helps the community track progress.