摘要
针对经典无锚框目标检测算法FCOS(Fully Constitutional One-Stage Object Detection)难以充分提取目标特征,位置与内容信息结合能力不足,正负样本区分不充分导致性能减弱等问题,提出了一种改进型FCOS目标检测算法。该方法首先在ResNet50特征提取网络中加入可变形卷积模块与全局注意力模块,提高特征信息捕获能力;然后,将FPN特征金字塔与深层链路层相结合,构成多尺度特征融合模块,提升特征提取效果。最后,加入自适应划分正负样本模块,增强检验框的准确性以达到提高回归精度的效果,从而提升检测结果。为了测试算法的检测效果,分别使用了COCO数据集与VOC数据集进行实验。与原FCOS算法相比,所提算法在两个数据集上的平均精度分别提高了2.3%和1.8%,其中,对COCO数据集中的小目标检测的效果有明显提升。
An enhanced FCOS object detection algorithm is proposed to address the problems that the classical anchorless frame object detection algorithm FCOS(fully constitutional one-stage object detection)has difficulty in extracting target information,insufficient ability to combine location and content information,and weak performance due to insufficient differentiation between positive and negative sample.The method first adds a deformable convolution module and a global attention module to the ResNet50feature extraction network to improve the feature information capture capability.Then,the FPN feature pyramid is combined with the deep link layer to form a multi-scale feature fusion module to improve the feature extraction effect.Finally,the adaptive division of positive and negative samples module is added to enhance the accuracy of the test frame to achieve the effect of improving the regression accuracy.In order to test the detection effect of the algorithm,the COCO dataset and VOC dataset are used for experiments.Compared with the original FCOS algorithm,the average accuracy of the proposed algorithm on the two datasets improves by 2.3%and 1.8%,respectively.Among them,there is a significant improvement for the detection of small targets in the COCO dataset.
作者
陈金令
程茂凯
徐紫涵
CHEN Jin-ling;CHENG Mao-kai;XU Zi-han(School of Electrical Information,Southwest Petroleum University,Chengdu 610500,China)
出处
《计算机科学》
CSCD
北大核心
2022年第S02期467-472,共6页
Computer Science
基金
四川省重点研发计划(重大科技专项)(2022YFS0020)
南充市市校科技战略合作专项(22SXQT0292)
关键词
目标检测
可变形卷积
全局注意力
多尺度特征
特征金字塔
正负样本
Target detection
Deformable convolution
Global attention
Multi-scale features
Feature pyramid
Positive and negative samples
作者简介
通信作者:陈金令,chengjl2002@163.com,born in 1975,Ph.D,professorate senior engineer.His main research interests include deep learning and image processing.
