.png){kind=icon}
返回
MonoPoly: A practical monocular 3D object detector
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108967.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
3D object detection plays a pivotal role in driver assistance systems and has practical requirements for small storage and fast inference. Monocular 3D detection alternatives abandon the complexity of LiDAR setup and pursues the effectiveness and efficiency of the vision scheme. In this work, we propose a set of anchor-free monocular 3D detectors called MonoPoly based on the keypoint paradigm. Specifically, we design a polynomial feature aggregation sampling module to extract multi-scale context features for aux-iliary training and alleviate classification and localization misalignment through an attention-aware loss. Extensive experiments show that the proposed MonoPoly series achieves an excellent trade-off between performance and model size while maintaining real-time efficiency on KITTI and nuScenes datasets. (c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Object detection
Monocular 3D
Real-time
Light -weight
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏分享收藏Spatial information enhancement network for 3D object detection from point cloud基于空间信息增强网络的点云三维目标检测.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
3D-CenterNet: 3D object detection network for point clouds with center estimation priority *3D-CenterNet: 具有中心估计优先级的点云3D物体检测网络 *PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏 没有更多内容
没有更多内容