基于深度学习网络的星表非结构化岩石目标辨识方法研究  

On Star Catalog Unstructured Rock Target Identification Method Based on Deep Learning Network

作　　者：黄璐 毛晓艳[1] 杜航 谢心如 胡海东[1] HUANG Lu;MAO Xiaoyan;DU Hang;XIE Xinru;HU Haidong(Beijing Institute of Control Engineering,Beijing 100094,China)

机构地区：[1]北京控制工程研究所,北京100094

出　　处：《空间控制技术与应用》2021年第6期27-33,共7页Aerospace Control and Application

基　　金：国家重点研发计划资助项目(2018AAA0102700)。

摘　　要：目标检测技术广泛应用于交通、医疗、安保和航天等领域.目前,目标检测技术面临目标微弱、背景复杂、目标被遮挡等挑战[1].针对星表非结构化模拟地形采集的图像中岩石和石块小目标检测识别率低、误识别率高的问题,研究了当下效果最好、模型轻量化的YOLOv5目标检测算法,在其基础上进行改进优化器与优化检测框重复检测效果的一种满足实时性要求的岩石目标检测算法.具体通过引入空标签负样本、结合随机梯度下降法SGD(stochastic gradient descent)优化模型和非极大值抑制参数调节方法,提升YOLOv5网络模型的特征描述能力和分类准确率.利用在地面试验场采集的复杂地形图像作为数据集,并采用mAP(mean average precision)、画面每秒传输帧数(FPS)、准确率和召回(P-R)曲线等作为性能指标,对所提出的目标检测网络进行了试验验证.结果表明本文提出的改进网络拥有更高的准确率和更低的虚警率,同时保持原有算法的实时性.Target detection technology is widely used in transportation,medical treatment,security,aerospace and other fields.At present,target detection technology faces challenges such as weak target,complex background and blocked target[1].Aiming at the problems of low detection and recognition rate and high false recognition rate of small rock and stone targets in the images collected from unstructured simulated terrain of star catalog,the YOLOv5 target detection algorithm with the best effect and lightweight model is studied.On the basis of it,a rock target detection algorithm meeting the real-time requirements is improved via improving the optimizer and optimizing the repeated detection effect of detection frame.In particular,the feature description ability and classification accuracy of YOLOv5 network model are improved by introducing empty labels as negative sample,combining SGD optimization model and non-maximum suppression parameter adjustment method.Using complex terrain images collected in ground test sites as data sets,and using mAP,FPS and P-R curves as performance indexes,the proposed target detection network is verified by experiments.The experimental results show that the improved network proposed in this paper has higher accuracy and lower false reputation rate,while maintaining the real-time performance of the original algorithm.

关 键 词：行星地形 岩石检测 深度学习 卷积神经网络 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]