A Method of Real Time and Fast Lane Line Detection

2018 ◽  
Author(s):  
Honghua Xu ◽  
Li Li ◽  
Ming Fang ◽  
Lin Hu
Keyword(s):  
Real Time ◽  
Line Detection ◽  
Lane Line ◽  
Fast Lane

scholarly journals Lane Line Detection System Based on Improved Yolo V3 Algorithm

2021 ◽  
Author(s):  
Gaoqing Ji ◽  
Yunchang Zheng
Keyword(s):  
Real Time ◽  
Detection System ◽  
Detection Algorithm ◽  
Horizontal Distribution ◽  
Lane Detection ◽  
Cluster Center ◽  
Line Detection ◽  
Detection Accuracy ◽  
Time Performance ◽  
Lane Line

Abstract Aiming at the problems of low accuracy and poor real-time performance of Yolo v3 algorithm in lane detection, a lane detection system based on improved Yolo v3 algorithm is proposed. Firstly, according to the characteristics of inconsistent vertical and horizontal distribution density of lane line pictures, the lane line pictures are divided into s * 2S grids; Secondly, the detection scale is adjusted to four detection scales, which is more suitable for small target detection such as lane line; Thirdly, the convolution layer in the original Yolo v3 algorithm is adjusted from 53 layers to 49 layers to simplify the network; Finally, the parameters such as cluster center distance and loss function are improved. The experimental results show that when using the improved detection algorithm for lane line detection, the average detection accuracy map value is 92.03% and the processing speed is 48 fps.Compared with the original Yolo v3 algorithm, it is significantly improved in detection accuracy and real-time performance.

Real-Time Line Detection Method for Camera Images of the Rescue Robot

2010 ◽  
Vol 130 (11) ◽  
pp. 2039-2046
Author(s):  
Munetoshi Numada ◽  
Masaru Shimizu ◽  
Takuma Funahashi ◽  
Hiroyasu Koshimizu
Keyword(s):  
Real Time ◽  
Detection Method ◽  
Line Detection ◽  
Time Line ◽  
Rescue Robot

Pendeteksian Ruang Kosong Parkir di dalam Ruangan

2018 ◽  
Vol 10 (1) ◽  
pp. 34-40
Author(s):  
Nunik Afriliana ◽  
Rosalina Rosalina ◽  
Regina Valeria
Keyword(s):  
Real Time ◽  
Line Detection ◽  
Cascade Classifier ◽  
Index Terms

Menemukan tempat parkir kosong di tempat parkir dalam ruangan seperti pusat perbelanjaan menjadi kesulitan banyak pengemudi, terutama saat jam sibuk di kota-kota besar. Dalam makalah ini, sebuah sistem deteksi kekosongan tempat parkir dalam ruangan diusulkan, dengan menggunakan sistem kamera yang melibatkan OpenCV untuk mempercepat waktu dalam mencari tempat parkir bagi pengemudi kendaraan dengan memberi mereka informasi lokasi dan tempat parkir. Sistem ini menggunakan metode deteksi objek statis, yaitu Haar-Like Cascade Classifier yang dikombinasikan dengan Hough Line Detection untuk mengidentifikasi area parkir kosong dari gambar parkir yang diambil secara real time melalui kamera IP atau kamera USB. Sistem ini dirancang untuk disematkan dengan sistem manajemen parkir sebuah bangunan sebagai alat yang menyediakan tempat parkir untuk membantu pengemudi kendaraan memasuki area parkir. Index Terms—Haar-Like Cascade Classifier, Hough Line Detection, Sistem Maanajemen Parkir

scholarly journals Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant

2021 ◽  
Vol 11 (22) ◽  
pp. 10713
Author(s):  
Dong-Gyu Lee
Keyword(s):  
Real Time ◽  
Computational Efficiency ◽  
Autonomous Driving ◽  
Learning Approaches ◽  
Practical Applications ◽  
Task Learning ◽  
Lane Line ◽  
High Level ◽  
Time Autonomous

Autonomous driving is a safety-critical application that requires a high-level understanding of computer vision with real-time inference. In this study, we focus on the computational efficiency of an important factor by improving the running time and performing multiple tasks simultaneously for practical applications. We propose a fast and accurate multi-task learning-based architecture for joint segmentation of drivable area, lane line, and classification of the scene. An encoder-decoder architecture efficiently handles input frames through shared representation. A comprehensive understanding of the driving environment is improved by generalization and regularization from different tasks. The proposed method learns end-to-end through multi-task learning on a very challenging Berkeley Deep Drive dataset and shows its robustness for three tasks in autonomous driving. Experimental results show that the proposed method outperforms other multi-task learning approaches in both speed and accuracy. The computational efficiency of the method was over 93.81 fps at inference, enabling execution in real-time.

Sign in / Sign up

Export Citation Format

Share Document