计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (6): 196-203.DOI: 10.3778/j.issn.1002-8331.2111-0075

• 图形图像处理 • 上一篇    下一篇

特征平衡的无人机航拍图像目标检测算法

徐坚,谢正光,李洪均   

  1. 1.南通大学 信息科学技术学院,江苏 南通 226019
    2.南京大学 计算机软件新技术国家重点实验室,南京 210023
  • 出版日期:2023-03-15 发布日期:2023-03-15

Feature-Balanced UAV Aerial Image Target Detection Algorithm

XU Jian, XIE Zhengguang, LI Hongjun   

  1. 1.School of Information Science and Technology, Nantong University, Nantong, Jiangsu 226019, China
    2.State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China
  • Online:2023-03-15 Published:2023-03-15

摘要: 无人机航拍图像目标较小、图像视角变化大,导致目标检测效果不佳。针对此问题,设计了一种适用于无人机小目标检测的网络。该网络中的可变形卷积模块可以提高多视角目标的特征提取能力,以解决航拍图像目标视角变化剧烈致使目标特征难以提取的问题;特征平衡金字塔模块可以增强网络中底层小目标特征,以解决航拍图像中的小目标因特征易丢失而造成其检测效果差的问题;同时利用像素重组构建底层大尺度特征以解决特征平衡金字塔模块的底层特征卷积运算量大的问题;交叉自注意力机制获取目标上下文信息,改善严苛条件下的漏检错检问题。公开数据集上的仿真结果表明,在保证实时检测的情况下所提算法的平均准确度优于主流检测算法。

关键词: 无人机目标检测, 特征平衡金字塔, 交叉自注意力, 像素重组

Abstract: Small target and large change of image angle in UAV aerial image result in poor object detection effect. To solve this problem, a network for UAV small target detection is designed. The problem that the target feature is difficult to extract due to the sharp change of the aerial image target’s perspective can be solved by the deformable convolution module in the network which improve the feature extraction ability for multi-view targets. The features of the low-level small targets in the network can be enhanced by the feature balance pyramid module, so as to solve the problem of poor detection effects of small targets in aerial images on account of their easy loss of features. At the same time, pixel un-shuffle is used to construct the bottom-level large-scale features to solve the problem of the large-scale convolution of the bottom-level features of the feature balance pyramid module. Cross self-attention mechanism is used for obtaining the object context information so that the problem of missed detection and error detection under severe conditions can be solved. Simulation results on public data sets show that the average accuracy of the proposed algorithm is better than that of the mainstream detection algorithms under the condition of real-time detection.

Key words: unmanned aerial vehicle(UAV) object detection, feature balance pyramid, cross self-attention, pixel un-shuffle