计算机科学 ›› 2020, Vol. 47 ›› Issue (5): 161-165.doi: 10.11896/jsjkx.190300062
乔梦雨, 王鹏, 吴娇, 张宽
QIAO Meng-yu, WANG Peng, WU Jiao, ZHANG Kuan
摘要: 在实际陆战场环境中,作战人员无法随身携带GPU等大型计算设备,因此较难计算规模较大的神经网络参数,进而导致目标识别网络无法实时工作。现有的轻量级神经网络虽然解决了实时性的问题,但是不能满足准确率的要求。为此,文中提出了一种基于轻量级卷积神经网络的目标识别算法(E-MobilNet)。为了提升网络学习的效果,以现有深度学习的主要目标检测框架MobileNet-V2为基础,插入一种ELU函数作为激活函数。首先,使用扩张卷积来增加通道数,以获得更多的特征;接着,通过ELU函数激活输出特征,这样可以缓解线性部分的梯度消失,并且使非线性部分对输入变化的噪声更鲁棒;然后,通过残差连接的方式组合高层特征与低层特征的输出;最后,将全局池化的输出结果输入Softmax分类函数。实验数据表明,在同样的测试集和测试环境下,与现在主流的轻量级深度学习目标识别算法相比,E-MobileNet识别的准确率和每秒检测的帧率都有所提升。实验数据充分说明,使用ELU激活函数和全局池化层减少了参数的数量,增强了模型的泛化能力,提升了算法的鲁棒性,在保证神经网络模型轻量级的基础上有效地提高了目标的识别准确率。
中图分类号:
[1]李未.人工智能新时代的群体智能[N].中国信息化周报,2017-09-18(007). [2]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125. [3]CAI M C,LV S K.Preliminary probing into intelligent warfare and it supporting technology system[J].National Defense Science and Technology,2017(1):94-98. [4]HUANG J M.Aiming at Intelligent Innovative Command Concept [N].PLA Newspaper,2018-09-27 (007). [5]WANG Y.Research on Battlefield Target Identification and Si-tuation Intention Forecasting[D].Wuxi:Jiangnan University,2015[6]CHEN H Y,SU C Y.An Enhanced Hybrid MobileNet[C]//2018 9th International Conference on Awareness Science and Technology (iCAST).IEEE,2018:308-312. [7]RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet LargeScale Visual Recognition Challenge[J].International Journal of Computer Vision,2015,115(3):211-252. [8]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems.2012:1097-1105. [9]PAL M,FOODY G M.Feature selection for classification of hyperspectral data by SVM[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(5):2297-2307. [10]SHIN H C,ROTH H R,GAO M,et al.Deep convolutional neural networks for computer-aided detection:CNN architectures,dataset characteristics and transfer learning[J].IEEE Transactions on Medical Imaging,2016,35(5):1285-1298. [11]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//European Conference on Computer Vision.Cham:Springer,2016:21-37. [12]ZHANG X,ZHOU X,LIN M,et al.Shufflenet:An extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:6848-6856. [13]JU M,LUO H B,WANG Z B.Improved YOLO V3 Algorithm and Its Application in Small Target Detection[J].Acta Optica Sinica,2019,39(7):0715004. [14]SANDLER M,HOWARD A,ZHU M,et al.Mobilenetv2:Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:4510-4520. [15]LEMLEY J,BAZRAFKAN S,CORCORAN P.Deep Learning for Consumer Devices and Services:Pushing the limits for machine learning,artificial intelligence,and computer vision[J].IEEE Consumer Electronics Magazine,2017,6(2):48-56. [16]MHASKAR H,LIAO Q,POGGIO T.When and why are deep networks better than shallow ones?[C]//Thirty-First AAAI Conference on Artificial Intelligence.2017. [17]WANG G,CHEN J Y,GAO F,et al.Research on the Infrastructure Target Detection of Remote Sensing Image Based on Deep Learning[J].Radio Engineering,2018,48(3):219-224. [18]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [19]CHOLLET F.Xception:Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1251-1258. [20]JIANG A B,WANG W W.Research on optimization of ReLU activation function[J].Sensors and Microsystems,2018,37 (2):50-52. [21]SHANG W,SOHN K,ALMEIDA D,et al.Understanding and improving convolutional neural networks via concatenated rectified linear units[C]//International Conference on Machine Learning.2016:2217-2225. [22]SCHWING A G,URTASUN R.Fully connected deep structurednetworks[J].arXiv:1503.02351,2015. [23]LIN M,CHEN Q,YAN S.Network in network[J].arXiv:1312.4400,2013. [24]EVERINGHAM M,VAN GOOL L,WILLIAMS C K I,et al.The pascal visual object classes (voc) challenge[J].InternationalJournal of Computer Vision,2010,88(2):303-338. [25]CAO H Z.Research on Image Classification Based on Improved Convolution Neural Network[D].Nanning:Guangxi Normal University,2017. |
[1] | 王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011 |
[2] | 郝强, 李杰, 张曼, 王路. 基于改进YOLOv3的空间非合作目标部件识别算法 Spatial Non-cooperative Target Components Recognition Algorithm Based on Improved YOLOv3 计算机科学, 2022, 49(6A): 358-362. https://doi.org/10.11896/jsjkx.210700048 |
[3] | 高荣华, 白强, 王荣, 吴华瑞, 孙想. 改进注意力机制的多叉树网络多作物早期病害识别方法 Multi-tree Network Multi-crop Early Disease Recognition Method Based on Improved Attention Mechanism 计算机科学, 2022, 49(6A): 363-369. https://doi.org/10.11896/jsjkx.210500044 |
[4] | 魏勤, 李瑛娇, 娄平, 严俊伟, 胡辑伟. 基于边云协同的人脸识别方法研究 Face Recognition Method Based on Edge-Cloud Collaboration 计算机科学, 2022, 49(5): 71-77. https://doi.org/10.11896/jsjkx.210300222 |
[5] | 李京泰, 王晓丹. 基于代价敏感激活函数XGBoost的不平衡数据分类方法 XGBoost for Imbalanced Data Based on Cost-sensitive Activation Function 计算机科学, 2022, 49(5): 135-143. https://doi.org/10.11896/jsjkx.210400064 |
[6] | 赵人行, 徐频捷, 刘瑶. 基于深度卷积残差网络的心电单导联房颤检测方法 ECG-based Atrial Fibrillation Detection Based on Deep Convolutional Residual Neural Network 计算机科学, 2022, 49(5): 186-193. https://doi.org/10.11896/jsjkx.220200002 |
[7] | 韩红旗, 冉亚鑫, 张运良, 桂婕, 高雄, 易梦琳. 基于共同子空间分类学习的跨媒体检索研究 Study on Cross-media Information Retrieval Based on Common Subspace Classification Learning 计算机科学, 2022, 49(5): 33-42. https://doi.org/10.11896/jsjkx.210200157 |
[8] | 高心悦, 田汉民. 基于改进U-Net网络的液滴分割方法 Droplet Segmentation Method Based on Improved U-Net Network 计算机科学, 2022, 49(4): 227-232. https://doi.org/10.11896/jsjkx.210300193 |
[9] | 张红民, 李萍萍, 房晓冰, 刘宏. 改进YOLOv3网络模型的人体异常行为检测方法 Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model 计算机科学, 2022, 49(4): 233-238. https://doi.org/10.11896/jsjkx.210300251 |
[10] | 瞿中, 陈雯. 基于空洞卷积和多特征融合的混凝土路面裂缝检测 Concrete Pavement Crack Detection Based on Dilated Convolution and Multi-features Fusion 计算机科学, 2022, 49(3): 192-196. https://doi.org/10.11896/jsjkx.210100164 |
[11] | 苗启广, 辛文天, 刘如意, 谢琨, 王泉, 杨宗凯. 面向智慧教育行为分析的图卷积骨架动作识别方法 Graph Convolutional Skeleton-based Action Recognition Method for Intelligent Behavior Analysis 计算机科学, 2022, 49(2): 156-161. https://doi.org/10.11896/jsjkx.220100061 |
[12] | 郭琳, 李晨, 陈晨, 赵睿, 范仕霖, 徐星雨. 基于通道注意递归残差网络的图像超分辨率重建 Image Super-resolution Reconstruction Using Recursive ResidualNetwork Based on ChannelAttention 计算机科学, 2021, 48(8): 139-144. https://doi.org/10.11896/jsjkx.200500150 |
[13] | 许华杰, 张晨强, 苏国韶. 基于深层卷积残差网络的航拍图建筑物精确分割方法 Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network 计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096 |
[14] | 暴雨轩, 芦天亮, 杜彦辉, 石达. 基于i_ResNet34模型和数据增强的深度伪造视频检测方法 Deepfake Videos Detection Method Based on i_ResNet34 Model and Data Augmentation 计算机科学, 2021, 48(7): 77-85. https://doi.org/10.11896/jsjkx.210300258 |
[15] | 和青芳, 王慧, 程光. 自适应小数据集乳腺癌病理组织分类研究 Research on Classification of Breast Cancer Pathological Tissues with Adaptive Small Data Set 计算机科学, 2021, 48(6A): 67-73. https://doi.org/10.11896/jsjkx.201000188 |
|