Deep Dual-Resolution Road Scene Segmentation Networks Based on Decoupled Dynamic Filter and Squeeze–Excitation Module
Open Access
Abstract
Image semantic segmentation is an important part of automatic driving assistance technology. The complexity of road scenes and the real-time requirements of application scenes for segmentation algorithm are the challenges facing segmentation algorithms. In order to meet the above challenges, Deep Dual-resolution Road Scene Segmentation Networks based on Decoupled Dynamic Filter and Squeeze–Excitation (DDF&SE-DDRNet) are proposed in this paper. The proposed DDF&SE-DDRNet uses decoupled dynamic filter in each module to reduce the number of network parameters and enable the network to dynamically adjust the weight of each convolution kernel. We add the Squeeze-and-Excitation module to each module of DDF&SE-DDRNet so that the local feature map in the network can obtain global features to reduce the impact of image local interference on the segmentation result. The experimental results on the Cityscapes dataset show that the segmentation accuracy of DDF&SE-DDRNet is at least 2% higher than that of existing algorithms. Moreover, DDF&SE-DDRNet also has satisfactory inferring speed.Keywords
Funding Information
- Jilin City Science and Technology Development Plan Project (20210103080)
This publication has 18 references indexed in Scilit:
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic SegmentationInternational Journal of Computer Vision, 2021
- The Improvement of Road Driving Safety Guided by Visual Inattentional BlindnessIEEE Transactions on Intelligent Transportation Systems, 2021
- Task Decomposition and Synchronization for Semantic Biomedical Image SegmentationIEEE Transactions on Image Processing, 2020
- Coarse-to-Fine Semantic Segmentation From Image-Level LabelsIEEE Transactions on Image Processing, 2019
- BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation2018
- Squeeze-and-Excitation Networks2018
- Efficient ConvNet for real-time semantic segmentation2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fully convolutional networks for semantic segmentation2015