Nighttime road scene image enhancement based on cycle-consistent generative adversarial network

During nighttime road scenes, images are often affected by contrast distortion, loss of detailed information, and a significant amount of noise. These factors can negatively impact the accuracy of segmentation and object detection in nighttime road scenes. A cycle-consistent generative adversarial n...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2024-06, Vol.14 (1), p.14375-17, Article 14375
Main Authors: Jia, Yanfei, Yu, Wenshuo, Chen, Guangda, Zhao, Liquan
Format: Article
Language:English
Subjects:
639/166
639/705
Artificial intelligence
Decomposition
Deep learning
Encoder-decoder netwrok
Generative adversarial network
Humanities and Social Sciences
Illumination attention module
Methods
multidisciplinary
Neural networks
Nighttime
Nighttime road scene image enhancement
Receptive field
Roads
Science
Science (multidisciplinary)
Semantics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:During nighttime road scenes, images are often affected by contrast distortion, loss of detailed information, and a significant amount of noise. These factors can negatively impact the accuracy of segmentation and object detection in nighttime road scenes. A cycle-consistent generative adversarial network has been proposed to address this issue to improve the quality of nighttime road scene images. The network includes two generative networks with identical structures and two adversarial networks with identical structures. The generative network comprises an encoder network and a corresponding decoder network. A context feature extraction module is designed as the foundational element of the encoder-decoder network to capture more contextual semantic information with different receptive fields. A receptive field residual module is also designed to increase the receptive field in the encoder network.The illumination attention module is inserted between the encoder and decoder to transfer critical features extracted by the encoder to the decoder. The network also includes a multiscale discriminative network to discriminate better whether the image is a real high-quality or generated image. Additionally, an improved loss function is proposed to enhance the efficacy of image enhancement. Compared to state-of-the-art methods, the proposed approach achieves the highest performance in enhancing nighttime images, making them clearer and more natural.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-65270-3