3D object detection based on high⁃precision map enhancement
|更新时间:2025-05-26
|
3D object detection based on high⁃precision map enhancement
“In the field of autonomous driving, researchers have proposed a 3D object detection algorithm HME3D based on high-precision map enhancement. By combining traditional convolution and Transformer, a novel map feature extraction module HFE is constructed to improve detection performance. The model's advantages were validated on the nuScenes dataset, with a 2.81 mAP improvement in accuracy compared to the pure point cloud baseline model.”
Journal of Jilin University(Engineering and Technology Edition)Vol. 53, Issue 3, Pages: 802-809(2023)
TAO Bo,YAN Fu-wu,YIN Zhi-shuai,et al.3D object detection based on high⁃precision map enhancement[J].Journal of Jilin University(Engineering and Technology Edition),2023,53(03):802-809.
TAO Bo,YAN Fu-wu,YIN Zhi-shuai,et al.3D object detection based on high⁃precision map enhancement[J].Journal of Jilin University(Engineering and Technology Edition),2023,53(03):802-809. DOI: 10.13229/j.cnki.jdxbgxb20221254.
3D object detection based on high⁃precision map enhancement