.png){kind=icon}
返回
Parallelization of Non-Maximum Suppression
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3134639.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Non-maximum suppression (NMS) is an unavoidable post-processing step in the object detection pipeline. NMS selects the bounding boxes with a locally maximum confidence score and eliminates its neighboring candidates which have a large overlap with the selected boxes. Because this procedure is a sequential and iterative algorithm of O(N-2) complexity, NMS running time is too slow to be applied to real-time object detection on the image which has many objects. To consider this issue, we propose a parallel computation method using GPU multi-cores to compute faster than the previous NMS. Our parallel NMS replicates the candidate boxes and performs both IoU calculation and comparison in parallel. We drastically reduced the complexity from O(N-2) to O(N) and the time consumption of NMS to be applied to real-time detection with negligible degradation of detection performance and very slight additional memory consumption. Furthermore, when there is a small number of overlapped objects, our parallel NMS achieved an improvement in precision.
Keyword:
Non-maximum suppression
parallel NMS
mode detection
object detection
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Crystalline‐State Reaction with Allosteric Effect in Spin‐Crossover, Interpenetrated Networks with Magnetic and Optical Bistability具有磁和光学双稳态的自旋交叉，互穿网络中具有变构效应的晶态反应
PREAI
分享收藏分享收藏
查看更多内容