摘要
为弥补CornerNet中小目标语义信息弱的缺陷,提出隔级融合特征金字塔的方法,提高小目标平均准确率。对骨干网络后半部分融合后的4个特征图进行提取,将尺寸较小的特征图进行2次卷积,得到2个新的特征图;运用上下融合、隔级融合和旁路连接的思想,生成融合后的特征图并将其组成特征金字塔。将改进后的算法与当前主流CornerNet、Faster RCNN、RetinaNet算法在MS COCO数据集上进行比较,结果表明,改进后算法在对小目标进行检测时,小目标平均准确率有较大提高。隔级融合特征金字塔在CornerNet上能有效融合高低层特征图,使融合后的特征图有较强的语义信息,提高CornerNet网络的小目标平均准确率。
To improve the problem of the weak semantic information of the small target in CornerNet,a method of the hierarchical fusion feature pyramid is proposed to increase the average accuracy of the small target.The method first extracts the four feature maps after the fusion of the second half of the backbone network,then convolves the feature maps with a smaller size twice to obtain two new feature maps,and finally uses the ideas of the upper and lower fusion,interlevel fusion,and bypass connection to generate a fused feature map and form it into a feature pyramid.The result shows that the average accuracy for small targets obtained by our algorithm has been greatly improved compared with those by current mainstream algorithms,such as CornerNet,Faster RCNN,and RetinaNet on the MS COCO dataset,which demonstrates great superiority.The inter-level fusion feature pyramid can effectively fuse high-level and low-level feature maps on CornerNet,so that the fused feature maps have strong semantic information,and improve the average accuracy of the small targets of the CornerNet network.
作者
赵文清
孔子旭
赵振兵
ZHAO Wenqing;KONG Zixu;ZHAO Zhenbing(School of Control and Computer Engineering,North China Electric Power University,Baoding 071003,China;School of Electrical and Electronic Engineering,North China Electric Power University,Baoding 071003,China;Engineering Research Center of the Ministry of education for Intelligent Computing of complex energy system,Baoding 071003)
出处
《智能系统学报》
CSCD
北大核心
2021年第1期108-116,共9页
CAAI Transactions on Intelligent Systems
基金
国家自然科学基金项目(61871182)
中央高校基本科研业务费面上项目(2020MS153)。
