.png){kind=icon}
返回
Bounding Box Vectorization for Oriented Object Detection With Tanimoto Coefficient Regression
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2023.3330103.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Current oriented object detection methods mainly utilize a vanilla coordinate-angle representation for bounding box regression, which usually suffers from inconsistency between the bounding box regression losses and prediction errors induced with respect to different rotation angles, aspect ratios, and scales. Therefore, although the existing oriented object detectors have achieved very good performances under coarse evaluation metrics such as AP(50), their performance significantly degrades when using stricter evaluation metric such as AP(75). To address the abovementioned issues, we propose a new regression method with bounding box vectorization that implicitly represents the shape and orientation of an object with a set of orthogonal vectors. By doing this, the proposed method delicately avoids the inconsistency issues encountered in oriented bounding box regression. During training, we introduce the Tanimoto coefficient to evaluate the similarity of the bounding box vector in a shape- and orientation-aware manner, and we refer to the proposed box-to-vector loss as the B2V loss. In addition to 2D object detection, the proposed method can be easily generalized to 3D scenarios involving orientation estimation, such as autonomous driving. We evaluate the proposed method through extensive experiments conducted on four popular oriented object detection datasets, including both 2D and 3D datasets, where the proposed method significantly outperforms the recently developed state-of-the-art methods when using a more accurate evaluation metric.
Keyword:
Object detection
Detectors
Measurement
Three-dimensional displays
Task analysis
Shape
Convergence
Bounding box regression
implicit vector representation
Oriented object detection
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-Shaped Scene Text Detection
OAAI
OAAI分享收藏A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection面向任意对象检测的通用高斯热图标签分配OAAI
OAAI分享收藏
查看更多内容