| 改进多层尺度特征融合的目标检测算法 |
| |
| 引用本文： | 李康康,于振中,范晓东,宋思远.改进多层尺度特征融合的目标检测算法[J].计算机工程与设计,2022,43(1):157-164. |
| |
| 作者姓名： | 李康康 于振中 范晓东 宋思远 |
| |
| 作者单位： | 江南大学 物联网工程学院,江苏 无锡 214122;江南大学 物联网工程学院,江苏 无锡 214122;哈工大机器人国际创新研究院 智能装备研究所,安徽 合肥 230601;哈工大机器人国际创新研究院 智能装备研究所,安徽 合肥 230601 |
| |
| 基金项目： | 江苏省自然科学基金项目(BK20130159)。 |
| |
| 摘 要： | 为提高小目标检测任务的准确率和稳定性,解决SSD(single shot MultiBox detector)算法在小目标识别和定位过程中准确率较低的问题,基于SSD算法提出一种改进方法.在原始的SSD卷积网络结构上进行修改和优化,通过特征图之间的特征融合,重构卷积预测特征图上的物体特征信息.考虑到网络复杂度增加带来的...
|
| 关 键 词： | 深度学习 目标识别与定位 卷积网络 SSD算法 特征融合 |
Improved multi-scale feature fusion target detection algorithm |
| |
| LI Kang-kang,YU Zhen-zhong,FAN Xiao-dong,SONG Si-yuan.Improved multi-scale feature fusion target detection algorithm[J].Computer Engineering and Design,2022,43(1):157-164. |
| |
| Authors: | LI Kang-kang YU Zhen-zhong FAN Xiao-dong SONG Si-yuan |
| |
| Affiliation: | (School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China;Institute of Intelligent Equipment,HRG International Institute for Research and Innovation,Hefei 230601,China) |
| |
| Abstract: | To increase the accuracy and stability of target detection task and solve the problem of low accuracy in the process of small target detection and location,an improved method was proposed based on SSD(single shot MultiBox detector)algorithm.The original convolutional network structure was optimized and improved,the object features on different predictive feature maps were increased through feature fusion between feature maps.Considering the influence of the change of data distribution brought by the increase of network complexity,the batch normalized BN(BatchNorm)layer was added.Experimental results on PASCAL VOC2007 dataset and Supplies Dataset show that the mAP of the improved algorithm is improved by 10.4%,15.1%respectively,compared with the original SSD.In view of the parameter increase brought by network convergence,the detection speed of the improved algorithm is not affected too much,which meets the real-time requirements of the algorithm. |
| |
| Keywords: | deep learning target identification and positioning convolution network SSD algorithm characteristics fusing |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
