自然场景下的挖掘机实时监测方法  

Method for the real-time monitoring of the excavator in natural scene

作　　者：毛亮 薛月菊 朱婷婷 魏颖慧 何俊乐 朱勋沐 Mao Liang;Xue Yueju;Zhu Tingting;Wei Yinghui;He Junle;Zhu Xunmu(College of Electronic Engineering,South China Agricultural University,Guangzhou 510642,China;Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area,Shenzhen Polytechnic,ShenZhen 518055,China;Gosuncn Technology Group Co.,Ltd.,Guangzhou 510530,China)

机构地区：[1]华南农业大学电子工程学院,广州510642 [2]深圳职业技术学院粤港澳大湾区人工智能应用技术研究院,深圳518055 [3]高新兴科技集团股份有限公司中央研究院,广州510530

出　　处：《农业工程学报》2020年第9期214-220,共7页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家科技支撑计划(2015BAD06B03-3)。

摘　　要：为实时监测违法用地现象,对作业挖掘机等施工机械进行实时监测至关重要。针对自然场景下由于背景复杂、光照不均匀及遮挡等导致作业挖掘机难以准确检测出的问题,该文采用类似SSD(Single Shot Detector)方法的网络结构,提出一种自然场景下的挖掘机实时监测方法。该方法采用堆叠DDB(Depthwise Dense Block)模块组成基础网络,实现浅层特征提取,并与高层特征融合,提高网络模型的特征表达能力;在MobileNetV2网络的基础上进行改进,设计BDM(Bottleneck Down-Sampling Module)模块构成多尺度特征提取网络,使模型参数数量和计算量减少为SSD的68.4%。构建不同视角和场景下的挖掘机目标数据集,共计18537张,其中15009张作为训练集,3528张作为测试集,并在主流Jetson TX1嵌入式硬件平台进行网络模型移植和验证。试验表明,该文方法的m AP(Mean Average Precision)为90.6%,其检测精度优于SSD和Mobile Net V2SSD的90.2%;模型大小为4.2 MB,分别减小为SSD和Mobile Net V2SSD的1/25和1/4,每帧检测耗时145.2 ms,相比SSD和MobileNetV2SSD分别提高了122.7%和28.2%,可以较好地部署在嵌入式硬件平台上,为现场及时发现违法用地作业提供有效手段。In order to monitor illegal land use in real time,video surveillance technology was used to monitor the vulnerable areas of illegal land use.Excavator was one of the most important construction machinery in the engineering construction,an automatic real-time detection of excavator could provide important information for non-contact field monitoring of illegal land.But it was difficult to accurately detect the excavator due to the complex background,uneven illumination and partial occlusion in natural scene,This paper proposed a real-time excavator detection algorithm in natural scene based on the SSD-like(Single Shot Detector).Specifically,the lightweight network DDB(Depthwise Dense Block)was used as the basic network to extract shallow feature and fuse with high-level features in the excavator objection model to enhance the feature representation capability.Meanwhile,the BDM(Bottleneck Down-sampling Module)which was designed based on the lightweight network MobileNetV2 was used as the multi-scale feature extraction network to reduce the parameter quantity and computation.The data sets included 18537 images of excavators with different shooting angles and natural scenes,15009 images were used as training set and 3528 images were chosen as test set randomly.To enhance the diversity of training data,data set expansion methods such as rotation and image were adopted.Based on the Caffe deep learning framework,the proposed model in this paper was trained with end-to-end approximate joint methods and the model weight was fine-tuned by using SGD(Stochastic Gradient Descent)algorithm.The DDB module of the network was initialized with the weights pre-trained on the PASCAL VOC dataset,and the training time and resources were further reduced by transferring learning.Then the model pre-trained on the large data sets was transplanted to excavator object detection by transfer learning.The proposed method was transplanted and performed on the mainstream Jetson TX1 embedded hardware platform,and experiments on the actual data se

关 键 词：农业机械 监测 模型 SSD MobileNetV2 自然场景 挖掘机 嵌入式硬件 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]