计算机工程2024，Vol.50Issue(3)：242-249,8.DOI:10.19678/j.issn.1000-3428.0067370
动态场景下基于语义分割的视觉SLAM方法
Visual SLAM Method Based on Semantic Segmentation in Dynamic Scenes
摘要
Abstract
A semantic visual SLAM algorithm based on an improved semantic segmentation network DeepLabv3plus and multiview geometry is designed to address the issues of poor robustness and susceptibility to interference from dynamic objects in visual Synchronous Localization And Map(SLAM)construction in dynamic scenes.Based on the semantic segmentation network DeepLabv3plus,a lightweight convolutional network MobileNetV2 is used for feature extraction,and depthwise separable convolutions are used instead of standard convolutions in the Atrous Spatial Pyramid Pooling(ASPP)module.Simultaneously,an attention mechanism is introduced to propose an improved semantic segmentation network DeepLabv3plus.Combining the improved semantic segmentation network DeepLabv3plus with multiview geometry,a dynamic point detection method is proposed to enhance the robustness of visual SLAM in dynamic scenes.On this basis,a three-dimensional semantic static map containing both semantic and geometric information is constructed.The experimental results on the TUM dataset demonstrate that compared with ORB-SLAM2,the highest Root Mean Square Error(RMSE)and Standard Deviation(SD)values increased by more than 98%and 97%,respectively.关键词
DeepLabv3plus网络/视觉同步定位与建图/多视图几何/动态场景/语义地图Key words
DeepLabv3plus network/visual Synchronous Localization And Map(SLAM)/multiview geometry/dynamic scenes/semantic map分类
信息技术与安全科学引用本文复制引用
杜晓英,袁庆霓,齐建友,王晨,杜飞龙,任澳..动态场景下基于语义分割的视觉SLAM方法[J].计算机工程,2024,50(3):242-249,8.基金项目
国家自然科学基金(52165063,52065010) （52165063,52065010）
贵州省科技厅资助项目([2022]重点024,[2022]一般140,[2023]一般094,[2023]一般025) （[2022]重点024,[2022]一般140,[2023]一般094,[2023]一般025）
贵州大学实验室开放资助项目(SYSKF2023-089). （SYSKF2023-089）
