[1]陶晓力,刘宁钟,沈家全.基于深度信息融合的航拍车辆检测[J].计算机技术与发展,2019,29(09):117-121.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 023]
　TAO Xiao-li,LIU Ning-zhong,SHEN Jia-quan.Aerial Vehicle Detection Based on Depth Information Fusion[J].,2019,29(09):117-121.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 023]
点击复制

基于深度信息融合的航拍车辆检测()
分享到：

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

卷:
29
期数:
2019年09期
页码:
117-121
栏目:
应用开发研究
出版日期:
2019-09-10

文章信息/Info

Title:
Aerial Vehicle Detection Based on Depth Information Fusion
文章编号:
1673-629X(2019)09-0117-05
作者:
陶晓力; 刘宁钟; 沈家全
南京航空航天大学 计算机科学与技术学院,江苏 南京 211106
Author(s):
TAO Xiao-li; LIU Ning-zhong; SHEN Jia-quan
School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
车辆检测; 无人机; 卷积神经网络; 超特征图; 小目标检测
Keywords:
vehicle detection; UAV; convolutional neural network; hyper feature map; small target detection
分类号:
TP31
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 09. 023
摘要:
随着汽车数量的快速增长以及无人机飞控技术的迅速发展,基于无人机航拍的车辆检测技术越来越有用武之地。传统的基于滑动窗口以及手工设计特征的车辆检测不仅计算量巨大,鲁棒性也不够好。 卷积神经网络在目标检测方面发挥了显著的优势,但是常见的网络对于航拍遥感图像中的小目标检测效果一般。 文中基于 faster-RCNN 在 VGG16 网络上使用通道合并融合的方式设计了超特征图,通过结合浅层特征以及深层特征的方式提取小目标的特征以提高检测的召回率。 同时修改 RPN 层的包围框的大小以提高检测的准确性。 在慕尼黑车辆数据集以及自己收集的数据上进行了测试,通过对比实验可知,该方法使得车辆检测的效果有了明显提升,在两个数据集上分别达到了 72.3%和 80.5%的 mAP。
Abstract:
With the rapid development of automotive and UAV technology, vehicle detection technology based on UAV aerial photography is becoming more and more useful. Traditional vehicle detection based on sliding windows and manual design features is not only computationally intensive but also not robust enough. Convolutional neural network plays a significant advantage in target detection,but common networks have a general effect on small targets in aerial remote sensing images. In this paper,we design the hyper feature map on the VGG16 network using channel merge and fusion based on faster-RCNN. The features of small targets are extracted by combining shallow features and deep features to improve the recall rate. At the same time,the size of the bounding box of the RPN layer is modified to improve the accuracy of detection. We test the model on the Munich vehicle dataset and the data collected. The experiment shows that the proposed method has significantly improved the effectiveness of vehicle detection compared to existing methods,reaching 72.3% and 80.5% of mAP on the two datasets.

相似文献/References:

[1]方宏 杜正春.车辆检测线远程监控系统的研制[J].计算机技术与发展,2009,(12):185.
　FANG Hong,DU Zheng-chun.Development of Remote Monitoring System of Vehicle Inspection Lane[J].,2009,(09):185.
[2]张明恒 王华莹 郭烈.基于改进K—Means算法的车辆识别方法[J].计算机技术与发展,2012,(05):53.
　ZHANG Ming-heng,WANG Hua-ying,GUO Lie.Method of Vehicle Detection Based on Improved K-Means Algorithm[J].,2012,(09):53.
[3]张晓军,陆兴华.加入不确定扰动的无人机飞行轨迹跟踪控制[J].计算机技术与发展,2018,28(01):182.[doi:10.3969/ j. issn.1673-629X.2018.01.039]
　ZHANG Xiao-jun,LU Xing-hua.Flight Trajectory Tracking Control Algorithm for Unmanned AerialVehicle with Uncertain Disturbance[J].,2018,28(09):182.[doi:10.3969/ j. issn.1673-629X.2018.01.039]
[4]吴玉枝,吴志红,熊运余.基于卷积神经网络的小样本车辆检测与识别[J].计算机技术与发展,2018,28(06):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
　WU Yu-zhi,WU Zhi-hong,XIONG Yun-yu.Vehicle Detection and Recognition of a Few Samples Based on Convolutional Neural Network[J].,2018,28(09):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
[5]王俊明,曹科才,肖斌,等. 基于Paparazzi Lisa/M2.0的无人机自主飞行设计[J].计算机技术与发展,2016,26(05):197.
　WANG Jun-ming,CAO Ke-cai,XIAO Bin,et al. Design of Autonomous Flight for UAV Based on Paparazzi Lisa/M2.0[J].,2016,26(09):197.
[6]王传钦[],曹江涛[],姬晓飞[]. 基于视频分析技术的车距测量及预警系统设计[J].计算机技术与发展,2016,26(09):87.
　WANG Chuan-qin[],CAO Jiang-tao[],JI Xiao-fei[]. Design of a Vehicle Distance Measurement and Early Warning System Based on Video Analysis Techniques[J].,2016,26(09):87.
[7]陆兴华. 采用波束域加权的大迎角飞行姿态控制算法[J].计算机技术与发展,2017,27(01):117.
　LU Xing-hua. High Angle of Attack Flight Attitude Control Algorithm Based on Beam Domain Weighting[J].,2017,27(09):117.
[8]陆兴华.基于波束空间二维谱峰搜索的无人机控制算法[J].计算机技术与发展,2017,27(12):52.[doi:10.3969/ j. issn.1673-629X.2017.12.012]
　LU Xing-hua.Unmanned Aerial Vehicle Control Algorithm Based on Two Dimensional Spectrum Peak Searching for Beam Space[J].,2017,27(09):52.[doi:10.3969/ j. issn.1673-629X.2017.12.012]
[9]陶晓力,武 建,杨 坤.基于无人机视觉的桥梁裂缝检测[J].计算机技术与发展,2018,28(03):174.[doi:10.3969/ j. issn.1673-629X.2018.03.037]
　TAO Xiao-li,WU Jian,YANG Kun.Bridge Crack Detection Based on Unmanned Aerial Vehicle Vision[J].,2018,28(09):174.[doi:10.3969/ j. issn.1673-629X.2018.03.037]
[10]张晨,刘宁钟.基于无人机视觉的道路违法搭建检测[J].计算机技术与发展,2018,28(07):140.[doi:10.3969/ j. issn.1673-629X.2018.07.030]
　ZHANG Chen,LIU Ning-zhong.llegal Construction Detection of Road Based on Unmanned Aerial Vehicle Vision[J].,2018,28(09):140.[doi:10.3969/ j. issn.1673-629X.2018.07.030]

更新日期/Last Update: 2019-09-10