摘要
针对目前实时语义分割方法存在大目标分割不准确、小目标信息丢失的问题,提出一种基于多分支网络的实时语义分割算法。首先,对双边分割网络进行优化,设计了金字塔分支扩大感受野,以覆盖视野内的大目标,充分地将上下文信息结合起来;其次,设计双边指导融合模块,为深层和浅层的特征映射提供指导信息,弥补小目标信息的损失。最后在Cityscapes数据集上进行验证,实验结果表明所提模型以51.3 fps的推理速度使平均交并比达到77.8%,与基准相比,精度提高了2.5个百分点。所提方法采用金字塔分支,在扩大感受野的同时,获取不同尺度的语义边缘区域特性,增强对语义边界的建模能力,且提出的双边指导融合模块可以更有效地融合不同层次的特征,弥补下采样造成的信息丢失,能够更好地指导模型学习。
Aiming at the problems of inaccurate large target segmentation and loss of small target information in current real-time semantic segmentation methods,this paper proposed a real-time semantic segmentation algorithm based on multi-branch networks.First of all,this paper optimized the bilateral segmentation network,and designed pyramid branches to expand the receptive field to cover large objects in the field of view and fully combine context information.Secondly,it designed a bilateral guidance fusion module to map deep and shallow features and provided guidance information to make up for the loss of small target information.Finally,this paper verified the proposed method on the Cityscapes dataset.The experimental results show that the proposed model achieves an average intersection ratio of 77.8%at an inference speed of 51.3 fps,and the accuracy is increased by 2.5 percentage points compared with the baseline.The proposed method adopts the pyramid branch to obtain the characteristics of semantic edge regions at different scales while expanding the receptive field,and enhances the modeling ability of semantic boundaries,and the proposed bilateral guidance fusion module can more effectively integrate features of different levels,compensating for the information loss caused by downsampling can better guide model learning.
作者
廖文森
徐成
刘宏哲
李学伟
Liao Wensen;Xu Cheng;Liu Hongzhe;Li Xuewei(Beijing Key Laboratory of Information Service Engineering,Beijing Union University,Beijing 100101,China;Institute for Brain&Cognitive Sciences,Beijing Union University,Beijing 100101,China)
出处
《计算机应用研究》
CSCD
北大核心
2023年第8期2526-2530,共5页
Application Research of Computers
基金
国家自然科学基金资助项目(62171042,62102033,62006020)
北京市重点科技项目(KZ202211417048)
北京市属高等学校高水平科研创新团队建设支持计划项目(BPHR20220121)
协同创新中心资助项目(CYXC2203)。
关键词
实时语义分割
轻量级
多分支网络
特征融合
real-time semantic segmentation
lightweight
multi-path network
feature fusion
