文献类型：期刊文献

英文题名：Bird's Eye View Semantic Segmentation based on Improved Transformer for Automatic Annotation

作者：Liang, Tianjiao[1,2];Pan, Weiguo[1,2];Bao, Hong[1,2];Fan, Xinyue[1,2];Li, Han[1,2]

第一作者：Liang, Tianjiao

通讯作者：Pan, WG[1];Bao, H[1];Pan, WG[2];Bao, H[2]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]corresponding author), Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China.|[1141739]北京联合大学机器人学院;[11417]北京联合大学;[11417103]北京联合大学北京市信息服务工程重点实验室;

年份：2023

卷号：17

期号：8

起止页码：1996-2015

外文期刊名：KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS

收录：;EI(收录号：20233814742477);Scopus(收录号：2-s2.0-85171294533);WOS:【SCI-EXPANDED(收录号:WOS:001064641900002)】；

基金：This work supported part by Beijing Natural Science Foundation (4232026); National Natural Science Foundation of China (grant nos. 62272049, 61932012, 61871039, 61906017, 62171042, 62102033 and 62006020) and Key project of science and technology of Beijing Education Commission (KZ202211417048); The Project of Construction and Support for high-level Innovative Teams of Beijing Municipal Institutions (Grant No. BPHR20220121) academic research projects of Beijing Union University (ZK10202202)

语种：英文

外文关键词：Transformer; Semantic Segmentation; High-Definition maps; Automatic Annotation

摘要：High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against state-of-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.