系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (4): 1120-1127.doi: 10.12305/j.issn.1001-506X.2022.04.07

• 电子技术 • 上一篇    下一篇

基于人眼视点图的特征融合小目标检测算法

魏文晓, 刘洁瑜*, 沈强, 李成   

  1. 火箭军工程大学导弹工程学院, 陕西 西安 710025
  • 收稿日期:2021-01-18 出版日期:2022-04-01 发布日期:2022-04-01
  • 通讯作者: 刘洁瑜
  • 作者简介:魏文晓(1997—), 女, 硕士研究生, 主要研究方向为计算机视觉|刘洁瑜(1970—), 女, 教授, 博士, 主要研究方向为惯性导航、计算机视觉|沈强(1989—), 男, 讲师, 博士, 主要研究方向为惯性导航、计算机视觉|李成(1987—), 男, 讲师, 硕士, 主要研究方向为惯性导航、计算机视觉
  • 基金资助:
    陕西省自然科学基础研究计划(2020JQ-491)

Feature fusion small target detection algorithm based on human eye view-point map

Wenxiao WEI, Jieyu LIU*, Qiang SHEN, Cheng LI   

  1. College of Missile Engineering, Rocket Force University of Engineering, Xi'an 710025, China
  • Received:2021-01-18 Online:2022-04-01 Published:2022-04-01
  • Contact: Jieyu LIU

摘要:

针对目前深度学习小目标检测算法在实际应用中存在的漏检率高、精度低等问题, 提出了一种基于人眼视点图的特征融合小目标检测算法。基于多类别单阶检测器(single shot multibox detection, SSD)算法通过不同扩张率的空洞卷积融合, 在基础网络上获得具有类似人眼感受野的浅层特征层; 对附加网络中的特征层进行信息融合, 合并上下文信息, 增加位置信息和全局语义信息, 从而提升小目标检测精度。通过PASCAL VOC 2007数据集验证, 结果表明, 该算法较传统SSD算法检测精度提升了3.7%, 较改进的小目标检测算法Bi-SSD精度提升了0.8%, 验证了选择更有表征能力的特征层是有效提升小目标检测精度的方法。

关键词: 小目标检测, 单阶检测器算法, 空洞卷积空间金字塔, 特征金字塔融合

Abstract:

Aiming at the high missed detection rate and low accuracy of the current deep learning small target detection algorithm in practical applications, this paper proposes a feature fusion small target detection algorithm based on the human eye view-point map. Based on the single shot multibox detection (SSD) algorithm, through the convolution fusion of holes with different expansion rates, a shallow feature layer similar to the receptive field of the human eye is obtained on the basic network. The feature layer in the additional network performs information fusion, merges context information, adds position information and global semantic information, thereby improving the accuracy of small target detection. Validated by PASCAL VOC 2007 data set, the results show that the detection accuracy of this algorithm is improved by 3.7% compared with the traditional SSD algorithm, and the accuracy of the improved small target detection algorithm Bi-SSD is increased by 0.8%. It is verified that selecting a feature layer with more characterization ability is an effective method to improve the accuracy of small target detection.

Key words: small target detection, single shot multibox detection (SSD) algorithm, hollow convolutional spatial pyramid, feature pyramid fusion

中图分类号: