摘要
针对视频数据利用低效和光测设备目标识别能力较弱的问题,提出一种使用海量视频数据建立数据库进而构建红外目标识别系统的方法。首先设计快速红外目标检测算法,提取目标并分类建立数据库;然后结合特定任务建立一组较匹配且结构不同的卷积神经网络,并提出基于测试准确度均值统计分析和参数规模的选型策略,选出泛化能力较好且结构简单的卷积神经网络以及适当的训练轮数;最后加载优选模型及其参数作为分类器,与检测器结合实现红外目标特征事件实时检测分类。仿真结果表明,目标分类准确率均值可达95%以上,速率约为50 pixel/s。卷积神经网络结构的设计和选型策略有效,构建的系统可以满足红外目标识别的精度和实时性要求。
To improve the low efficiency of video data utilization and the weak target recognition ability of optical measuring equipment,we propose a method to establish a database with massive amounts of video and then construct an infrared target recognition system.Firstly,a fast infrared target detector to extract the target region from video frames and establish a database by classifying these subimages is designed.Secondly,according to a specific task,a cluster of convolutional neural networks with different structures is designed,and a selection strategy based on a mean value statistical analysis of test accuracy and parameter scale is designated.Consequently,we obtain a simple network with good generalization ability and a reasonable number of training epochs.Finally,the optimized model and its parameters are loaded as a classifier,which is combined with the detector to perform real-time detection and classification of infrared target events.Simulation results show that the average target classification accuracy can exceed 95%and the rate is approximately 50 FPS.The design scheme and selection strategy from the convolutional neural network structure is effective,and the constructed system exhibits real-time infrared target recognition while meeting accuracy requirements.
作者
刘可佳
马荣生
唐子木
梁捷
刘斌
LIU Ke-jia;MA Rong-sheng;TANG Zi-mu;LIANG Jie;LIU Bin(Troops 63726 of PLA,Yinchuan 750004,China)
出处
《光学精密工程》
EI
CAS
CSCD
北大核心
2021年第4期822-831,共10页
Optics and Precision Engineering
基金
军内科研项目资助(No.2015SY25B0002)。
关键词
海量视频
卷积神经网络
选型策略
红外目标识别
massive video
Convolutional Neural Network(CNN)
selection strategy
infrared target recognition