激光与光电子学进展, 2019, 56 (4): 041502, 网络出版: 2019-07-31
基于改进特征金字塔的Mask R-CNN目标检测方法 
下载： 1977次
Mask R-CNN Object Detection Method Based on Improved Feature Pyramid
机器视觉 模式识别 目标检测 卷积神经网络 特征金字塔 machine vision pattern recognition object detection convolutional neural network feature pyramid
摘要
提出了一种基于改进特征金字塔的Mask R-CNN目标检测方法。实验结果表明,在目标边缘和包围盒两项检测中,相比于Mask R-CNN检测框架,所提方法在不同的交并比阈值下的平均准确率分别提高了约2.4%和3.8%。尤其对于中等尺寸目标的检测准确率有较大的提高,分别为7.7%和8.5%,具有较强的稳健性。
Abstract
The Mask R-CNN (mask region-based convolutional neural network) object detection method is proposed based on the improved feature pyramid. The experimental results show that compared with the Mask R-CNN detection structure, the mean average precision (mAP) under different Intersection-over-Union (IoU) thresholds increases by 2.4% and 3.8% in the detection of object edge and bounding box, respectively. In particular, the detection accuracy of medium size objects is greatly improved by 7.7% and 8.5%, respectively, which indicates strong robustness.
任之俊, 蔺素珍, 李大威, 王丽芳, 左健宏. 基于改进特征金字塔的Mask R-CNN目标检测方法[J]. 激光与光电子学进展, 2019, 56(4): 041502. Zhijun Ren, Suzhen Lin, Dawei Li, Lifang Wang, Jianhong Zuo. Mask R-CNN Object Detection Method Based on Improved Feature Pyramid[J]. Laser & Optoelectronics Progress, 2019, 56(4): 041502.
PDF全文
