基于混合结构卷积神经网络的目标快速检测算法

doi:10.19678/j.issn.1000-3428.0049051

摘要/Abstract

摘要：

为提高基于卷积神经网络（CNN）目标检测算法的检测速度，提出一种基于混合结构CNN的目标快速检测算法。采用基于CNN的Faster R-CNN目标检测框架，对其CNN进行优化。基于多层感知器结构，提出CR-mlpconv卷积层结构。在网络浅层采用C.ReLU策略，同时结合CR-mlpconv层结构和C.ReLU策略，合理设计层参数，构成卷积神经网络。将该卷积神经网络融合到Faster R-CNN检测框架中，实现目标快速检测。实验结果表明，在检测精度的适当影响范围内，该算法能够减少网络模型参数并降低网络模型的内存消耗，提高网络的实时性。

关键词: 目标快速检测, Faster R-CNN框架, 卷积神经网络, 特征提取, 混合结构, 低通道

Abstract:

In order to improve the detection speed of the Convolutional Neural Network (CNN) target detection algorithm,a target fast detection algorithm based on hybrid structure CNN is proposed.CNN is optimized by CNN-based Faster R-CNN target detection framework.Based on the multilayer perceptron structure,a CR-mlpconv convolutional layer structure is proposed.The C.ReLU strategy is adopted in the shallow layer of the network,and the CR-mlpconv layer structure and the C.ReLU strategy are combined to design the layer parameters reasonably to form CNN.CNN is merged into the Faster R-CNN detection framework to achieve rapid target detection.Experimental results show that compared with the Faster R-CNN+ZFnet algorithm,the algorithm can reduce the network model parameters,reduce the memory consumption of the network model,and improve the real-time performance of the network.

Key words: target fast detection, Faster R-CNN framework, Convolutional Neural Network(CNN), feature extraction, hybrid structure, low channel

中图分类号:

TP391

林封笑,陈华杰,姚勤炜,张杰豪. 基于混合结构卷积神经网络的目标快速检测算法[J]. 计算机工程, 2018, 44(12): 222-227.

LIN Fengxiao,CHEN Huajie,YAO Qinwei,ZHANG Jiehao. Target Fast Detection Algorithm Based on Hybrid Structure Convolutional Neural Network[J]. Computer Engineering, 2018, 44(12): 222-227.

http://www.ecice06.com/CN/Y2018/V44/I12/222

参考文献

［1］TAIGMAN Y,YANG M,RANZATO M,et al.Deepface:closing the gap to human-level performance in face verifica-tion［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1701-1708.
［2］姚相坤,万里红,霍宏,等.基于多结构卷积神经网络的高分遥感影像飞机目标检测［J］.计算机工程,2017,43(1):259-267.
［3］易生,梁华刚,茹锋.基于多列深度3D卷积神经网络的手势识别［J］.计算机工程,2017,43(8):243-248.
［4］LECUN Y,BENGIO Y,HINTON G.Deep learning［J］.Nature,2015,521(7553):436-444.
［5］王兆凯,李亚星,冯旭鹏,等.基于深度信念网络的个性化信息［J］.计算机工程,2016,42(10):201-206.
［6］GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:580-587.
［7］GIRSHICK R.Fast R-CNN［C］//Proceedings of IEEE Inter-national Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:1440-1448.
［8］REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
［9］REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:779-788.
［10］DENTON E,ZAREMBA W,BRUNA J,et al.Exploiting linear structure within convolutional networks for efficient evaluation［C］//Proceedings of International Conference on Neural Information Processing Systems.Cambrige,USA:MIT Press,2014:1269-1277.
［11］KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks［C］//Proceedings of International Conference on Neural Information Processing Systems.New York,USA:ACM,2012:1097-1105.
［12］ZEILER M D,FERGUS R.Visualizing and understanding convolutional networks［C］//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2014:818-833.
［13］SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition［EB/OL］.［2017-09-17］.https://arxiv.org/abs/1409.1556v6.
［14］SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press:2015:1-9.
［15］HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:770-778.
［16］FORREST N I,SONG H,MATTHEW W M,et al.SqueezeNet:alexnet-level accuracy with 50x fewer parameters and <0.5 MB model size［EB/OL］.［2017-09-17］.https://arxiv.org/pdf/1602.07360.pdf.
［17］HOWARD A G,ZHU M,CHEN B,et al.MobileNets:efficient convolutional neural networks for mobile vision applications［EB/OL］.［2017-09-17］.https://arxiv.org/pdf/1704.04861.pdf.
［18］LIN M,CHEN Q,YAN S.Network in network［EB/OL］.［2017-09-17］.https://arxiv.org/pdf/1312.4400v3.pdf.
［19］SHANG W,SOHN K,ALMEIDA D,et al.Understanding and improving convolutional neural networks via concatenated rectified linear units［EB/OL］.［2017-09-17］.https://arxiv.org/pdf/1603.05201.pdf.
［20］李传朋,秦品乐,张晋京.基于浓度卷识神经网络的图像去噪研究［J］.计算机工程,2017,43(3):253-260.

[1]	马娜, 温廷新, 贾旭, 李晓会. 复杂光照条件下自适应的车脸重识别模型[J]. 计算机工程, 2023, 49(8): 275-282, 290.
[2]	曹坪, 杨怀志, 薄一军, 尤嘉, 张淳杰, 李丹勇. 面向低质量裂缝图像的多知识蒸馏分类[J]. 计算机工程, 2023, 49(7): 204-213.
[3]	白明昌. 基于折叠路径聚合的属性网络节点嵌入方法[J]. 计算机工程, 2023, 49(7): 76-84.
[4]	代祖华, 刘园园, 狄世龙. 语义增强的图神经网络方面级文本情感分析[J]. 计算机工程, 2023, 49(6): 71-80.
[5]	戴浩磊, 黄永慧, 周郭许. 基于超图正则化非负张量链分解的聚类分析[J]. 计算机工程, 2023, 49(6): 81-89.
[6]	沈学利, 田桂源, 姜彦吉, 马琳琳. 基于双阶段Conv-Transformer的时频域语音增强算法[J]. 计算机工程, 2023, 49(6): 123-130.
[7]	宋羽凯, 谢江. 基于多任务学习的轻量级语音情感识别模型[J]. 计算机工程, 2023, 49(5): 122-128.
[8]	丁子轩, 俞雷, 张娟, 李想, 王新宇. 基于深度残差自适应注意力网络的图像超分辨率重建[J]. 计算机工程, 2023, 49(5): 231-238.
[9]	衡红军, 苗菁. 语义与句法信息加强的二元标记实体关系联合抽取[J]. 计算机工程, 2023, 49(4): 77-84.
[10]	李培育, 张雅丽. 基于改进SRGAN模型的人脸图像超分辨率重建[J]. 计算机工程, 2023, 49(4): 199-205.
[11]	耿磊, 傅洪亮, 陶华伟, 卢远, 郭歆莹, 赵力. 基于动态卷积递归神经网络的语音情感识别[J]. 计算机工程, 2023, 49(4): 125-130,137.
[12]	陈治旭, 靳雁霞, 芦烨, 杨晶, 刘亚变, 史志儒. 基于子图卷积神经网络的多精度服装建模方法[J]. 计算机工程, 2023, 49(4): 174-181.
[13]	杨晶晶, 谢海燕, 薛妮妮, 张傲明. 基于双通道残差网络的水下图像去噪研究[J]. 计算机工程, 2023, 49(4): 188-198.
[14]	徐康, 李霏, 姬东鸿. 结合依存图卷积与文本片段搜索的方面情感三元组抽取[J]. 计算机工程, 2023, 49(4): 61-67.
[15]	关日鹏, 况立群, 焦世超, 熊风光, 韩燮. 多模态特征融合与词嵌入驱动的三维检索方法[J]. 计算机工程, 2023, 49(4): 101-107,113.

选择文件类型/文献管理软件名称

选择包含的内容