https://scholars.lib.ntu.edu.tw/handle/123456789/640000
標題: | Revisiting Depth-guided Methods for Monocular 3D Object Detection by Hierarchical Balanced Depth | 作者: | Chen, Yi Rong Tseng, Ching Yu Liou, Yi Syuan Wu, Tsung Han WINSTON HSU |
關鍵字: | autonomous driving | monocular 3D object detection | 公開日期: | 1-一月-2023 | 卷: | 229 | 來源出版物: | Proceedings of Machine Learning Research | 摘要: | Monocular 3D object detection has seen significant advancements with the incorporation of depth information. However, there remains a considerable performance gap compared to LiDAR-based methods, largely due to inaccurate depth estimation. We argue that this issue stems from the commonly used pixel-wise depth map loss, which inherently creates the imbalance of loss weighting between near and distant objects. To address these challenges, we propose MonoHBD (Monocular Hierarchical Balanced Depth), a comprehensive solution with the hierarchical mechanism. We introduce the Hierarchical Depth Map (HDM) structure that incorporates depth bins and depth offsets to enhance the localization accuracy for objects. Leveraging RoIAlign, our Balanced Depth Extractor (BDE) module captures both scene-level depth relationships and object-specific depth characteristics while considering the geometry properties through the inclusion of camera calibration parameters. Furthermore, we propose a novel depth map loss that regularizes object-level depth features to mitigate imbalanced loss propagation. Our model reaches state-of-the-art results on the KITTI 3D object detection benchmark while supporting real-time detection. Excessive ablation studies are also conducted to prove the efficacy of our proposed modules. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/640000 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。