[1]赵 侃,汪慧兰,郭娇娇,等.基于 DTA-FSAF 的无人机小目标检测研究[J].计算机技术与发展,2024,34(04):101-108.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 016]
 ZHAO Kan,WANG Hui-lan,GUO Jiao-jiao,et al.Research on Small Object Detection of UAV Based on DTA-FSAF[J].,2024,34(04):101-108.[doi:10. 3969 / j. issn. 1673-629X. 2024. 04. 016]
点击复制

基于 DTA-FSAF 的无人机小目标检测研究()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年04期
页码:
101-108
栏目:
媒体计算
出版日期:
2024-04-10

文章信息/Info

Title:
Research on Small Object Detection of UAV Based on DTA-FSAF
文章编号:
1673-629X(2024)04-0101-08
作者:
赵 侃汪慧兰郭娇娇王桂丽
安徽师范大学 物理与电子信息学院,安徽 芜湖 241002
Author(s):
ZHAO KanWANG Hui-lanGUO Jiao-jiaoWANG Gui-li
School of Physics and Electronic Information,Anhui Normal University,Wuhu 241002,China
关键词:
目标检测小目标检测Feature Selective Anchor-Free无人机标签分配
Keywords:
object detectiontiny object detectionFeature Selective Anchor-FreeUAVlabel assignment
分类号:
TP391. 41;V19
DOI:
10. 3969 / j. issn. 1673-629X. 2024. 04. 016
摘要:
随着无人机的应用越来越广泛,基于无人机下的交通场景目标检测的需求也越来越高。 但是现有算法在无人机视角下检测精度不高,鲁棒性也不够稳定。 为了解决交通场景下无人机视角的车辆和行人的目标检测问题,该文提出DTA-FSAF 的目标检测网络。 首先,将可变形卷积融入骨干网络 ResNet-50 中提高 FSAF 网络( Feature Selective Anchor-Free) 的特征学习能力,采用 PAFPN( Path Aggregation Feature Pyramid Network) 实现多尺度融合,从而提高小目标的检测精度与网络的拟合能力;其次,使用任务对齐检测头减小网络的分类与定位任务在检测小目标时出现的分类与定位任务的错位,从而进一步提高网络的鲁棒性;最后,通过调整 IoU 损失提高网络整体的检测效果。 通过在无人机数据集 VisDrone上进行实验和分析比较可知,相比于其他网络,在不同的交通场景下,DTA-FSAF 网络在满足实时性需求的同时检测精度达到了 41. 3% 。 相比于 FSAF 网络提升了 19. 6% 。 通过实验证明改进算法能有效地在各种复杂交通场景下完成对行人和车辆的目标检测。
Abstract:
With the increasing application of UAV,the demand for object detection in traffic scenes based on UAV is also increasing.However,existing algorithms have low detection accuracy and insufficient robustness from the perspective of UAV. In order to effectivelysolve the object detection problem of vehicles and pedestrians from the perspective of UAV in traffic scenes,we propose the DTA-FSAFnetwork for object detection. Firstly,deformable convolution is integrated into the backbone network ResNet-50 to improve the featurelearning ability of the FSAF ( Feature Selective Anchor-Free) network,and PAFPN ( Path Aggregation Feature Pyramid Network) isused for multi - scale fusion to improve the detection accuracy of small object and the fitting ability of the network. Secondly, taskalignment detection heads are used to reduce the misalignment of classification and positioning tasks in detecting small object,thus furtherimproving the robustness of the network. Finally,the IoU loss is adjusted to improve the overall detection performance of the network.Through experiments and analysis on the drone dataset VisDrone,it is known that compared with other networks,the DTA-FSAF networkcan achieve a detection accuracy of 41. 3% in different traffic scenes while meeting real - time requirements. This is a 19. 6%improvement over the FSAF network. The experimental results demonstrate that the improved algorithm can effectively complete theobject detection of pedestrians and vehicles in various complex traffic scenes.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
 LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(04):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
 LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(04):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
 SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(04):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
 LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(04):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
 JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(04):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
 LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(04):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
 GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(04):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
 ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(04):18.
[9]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673-629X.2018.05.013]
 SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(04):55.[doi:10.3969/j.issn.1673-629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
 ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(04):36.
[11]耿 文,孙 涵.一种 Anchor Free 的无人机检测方法[J].计算机技术与发展,2021,31(01):54.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 010]
 GENG Wen,SUN Han.An Anchor Free Method for Detecting Drones[J].,2021,31(04):54.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 010]

更新日期/Last Update: 2024-04-10