Multi Path Real-time Semantic Segmentation Network in Road Scenarios

扫码查看

原文链接

NETL
NSTL
Springer Nature

外文摘要：Semantic segmentation is a critical task in computer vision. Existing methods often struggle to balance accuracy and computational efficiency when processing high-resolution images, limiting their application scenarios. To address these limitations, we introduce RepMPSeg, a novel re-parameterization-based multi-path real-time semantic segmentation network. RepMPSeg improves upon traditional dual-branch architectures. It features two independent yet interconnected branches: a high-resolution branch for detailed feature capture and a low-resolution branch for global semantic information extraction. By employing re-parameterization techniques, the basic convolutional blocks are optimized to enhance feature capture and local context information. During training, parallel convolution structures are utilized, which are then streamlined into a single kernel during inference to maintain performance while reducing computational complexity. The high-resolution branch leverages sub-pixel sampling and 1×1 convolutions to improve the receptive field and minimize computational load, while the low-resolution branch uses 4× downsampling to enhance semantic information extraction. Features from both branches are fused through the re-parameterization-based Hybrid Downsampling Module (RepHDM), which aligns and combines features effectively. Our experiments on the Cityscapes and CamVid datasets demonstrate that RepMPSeg achieves a balance between speed and accuracy, outperforming state-of-the-art methods. Specifically, RepMPSeg achieves an mIoU of 77.4 and an FPS of 91.4 on the Cityscapes dataset, and an mIoU of 78.6 and an FPS of 117.33 on the CamVid dataset, making it a highly efficient solution for real-time semantic segmentation in road scenarios.

外文关键词：

Real-time semantic segmentationRe-parameterizationHigh-resolution imagesDual-branch architecture

作者：

Gao Pengfei、Tian Xiaolong、Liu Cuihong、Yang Chenfei

展开 >

作者单位：

Zhengzhou Railway Vocational and Technical College, Zhengzhou 450000, Henan, China||Henan Rail Transit Intelligent Safety Engineering Technology Research Center, Zhengzhou 450000, Henan, China||Zhengzhou Key Laboratory of Advanced Functional Materials, Zhengzhou 450000, Henan, China

Zhengzhou Railway Vocational and Technical College, Zhengzhou 450000, Henan, China||Henan Rail Transit Intelligent Safety Engineering Technology Research Center, Zhengzhou 450000, Henan, China

Zhengzhou Railway Vocational and Technical College, Zhengzhou 450000, Henan, China

Zhengzhou Railway Vocational and Technical College, Zhengzhou 450000, Henan, China||Zhengzhou Key Laboratory of Advanced Functional Materials, Zhengzhou 450000, Henan, China

展开 >

出版年：

2025

DOI：

10.1007/s13177-024-00434-z

International journal of intelligent transportation systems research

ISSN：1868-8659

年,卷(期)：2025.23(1)

参考文献量39