A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network

To solve the semantic segmentation problem of night driving-scene images, which often have low brightness, low contrast, and uneven illumination, a nighttime driving-scene segmentation method based on a light-enhanced network was proposed. Firstly, we designed a light enhancement network, which comp...

Full description

Saved in:
Bibliographic Details
Main Authors: Lihua Bi, Wenjiao Zhang, Xiangfei Zhang, Canlin Li
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:World Electric Vehicle Journal
Subjects:
Online Access:https://www.mdpi.com/2032-6653/15/11/490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850227840187891712
author Lihua Bi
Wenjiao Zhang
Xiangfei Zhang
Canlin Li
author_facet Lihua Bi
Wenjiao Zhang
Xiangfei Zhang
Canlin Li
author_sort Lihua Bi
collection DOAJ
description To solve the semantic segmentation problem of night driving-scene images, which often have low brightness, low contrast, and uneven illumination, a nighttime driving-scene segmentation method based on a light-enhanced network was proposed. Firstly, we designed a light enhancement network, which comprises two parts: a color correction module and a parameter predictor. The color correction module mitigates the impact of illumination variations on the segmentation network by adjusting the color information of the image. Meanwhile, the parameter predictor accurately predicts the parameters of the image filter through the analysis of global content, including factors such as brightness, contrast, hue, and exposure level, thereby effectively enhancing the image quality. Subsequently, the output of the light enhancement network is input into the segmentation network to obtain the final segmentation prediction. Experimental results show that the proposed method achieves mean Intersection over Union (mIoU) values of 59.4% on the Dark Zurich-test dataset, outperforming other segmentation algorithms for nighttime driving-scenes.
format Article
id doaj-art-c7d926bd1b0a4c8290e9186a2fb2475d
institution OA Journals
issn 2032-6653
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series World Electric Vehicle Journal
spelling doaj-art-c7d926bd1b0a4c8290e9186a2fb2475d2025-08-20T02:04:43ZengMDPI AGWorld Electric Vehicle Journal2032-66532024-10-01151149010.3390/wevj15110490A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced NetworkLihua Bi0Wenjiao Zhang1Xiangfei Zhang2Canlin Li3School of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450000, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450000, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450000, ChinaTo solve the semantic segmentation problem of night driving-scene images, which often have low brightness, low contrast, and uneven illumination, a nighttime driving-scene segmentation method based on a light-enhanced network was proposed. Firstly, we designed a light enhancement network, which comprises two parts: a color correction module and a parameter predictor. The color correction module mitigates the impact of illumination variations on the segmentation network by adjusting the color information of the image. Meanwhile, the parameter predictor accurately predicts the parameters of the image filter through the analysis of global content, including factors such as brightness, contrast, hue, and exposure level, thereby effectively enhancing the image quality. Subsequently, the output of the light enhancement network is input into the segmentation network to obtain the final segmentation prediction. Experimental results show that the proposed method achieves mean Intersection over Union (mIoU) values of 59.4% on the Dark Zurich-test dataset, outperforming other segmentation algorithms for nighttime driving-scenes.https://www.mdpi.com/2032-6653/15/11/490semantic segmentationimage enhancementnighttime driving-scenedeep learning
spellingShingle Lihua Bi
Wenjiao Zhang
Xiangfei Zhang
Canlin Li
A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network
World Electric Vehicle Journal
semantic segmentation
image enhancement
nighttime driving-scene
deep learning
title A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network
title_full A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network
title_fullStr A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network
title_full_unstemmed A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network
title_short A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network
title_sort nighttime driving scene segmentation method based on light enhanced network
topic semantic segmentation
image enhancement
nighttime driving-scene
deep learning
url https://www.mdpi.com/2032-6653/15/11/490
work_keys_str_mv AT lihuabi anighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT wenjiaozhang anighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT xiangfeizhang anighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT canlinli anighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT lihuabi nighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT wenjiaozhang nighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT xiangfeizhang nighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork
AT canlinli nighttimedrivingscenesegmentationmethodbasedonlightenhancednetwork