一种基于通道重排的轻量级目标检测网络

doi:10.3969/j.issn.1006-2475.2020.02.019

计算机与现代化

一种基于通道重排的轻量级目标检测网络

（中国电子科技集团公司第十五研究所，北京100083）

收稿日期:2019-06-28 出版日期:2020-03-03 发布日期:2020-03-03
作者简介:徐晗智（1994-），男，辽宁葫芦岛人，硕士研究生，研究方向：机器学习和计算机视觉，E-mail: xhz1528@163.com；艾中良（1971-），男，河北石家庄人，研究员，硕士，研究方向：网络安全，大数据，人工智能，E-mail: aizhongliang@hotmail.com；张志超（1990-），男，河南信阳人，高级工程师，博士，研究方向：人工智能，计算机视觉，FPGA编程，E-mail: beyond9017@163.com。
基金资助:
国防科技创新特区基金资助项目（18-H863-01-ZT-005-009-01）

A Lightweight Target Detection Network Based on Channel Rearrangement

The 15th Research Institute of CETC， Beijing 100083, China)

Received:2019-06-28 Online:2020-03-03 Published:2020-03-03

摘要/Abstract

摘要： Tiny YOLO和YOLOv3-tiny作为2种轻量级目标检测算法以其突出的速度表现而闻名。本文以这2种网络模型为基础，结合分组卷积并改进通道重排算法，改进了原来的损失函数，构建了一种新的更快的网络模型，通过改进YOLOv3的损失函数而增加其检测准确度。在PASCAL VOC数据集和COCO数据集上分别训练并且测试，该网络模型每秒处理的速度超过265张图片，Map值达到55.8%，准确度超过Tiny YOLO且与YOLOv3-tiny相仿。

关键词: 目标检测, 网络模型, 损失函数, 通道重排

Abstract: Tiny YOLO and YOLOv3-tiny are two lightweight target detection algorithms known for their outstanding speed performance. Based on these two network models, combining packet convolution and improved channel rearrangement algorithm and the original loss function， this paper constructs a new faster network model which improves the detection accuracy by improving the loss function of YOLOv3. The PASCAL VOC and COCO datasets were trained and tested respectively. The speed of the network model was faster than 265 pictures per second, and the accuracy was higher than Tiny YOLO and similar to YOLOv3-tiny.

Key words: target detection, network model, loss function, channel shuffle

中图分类号:

TP319.41

徐晗智，艾中良，张志超 . 一种基于通道重排的轻量级目标检测网络[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2020.02.019.

XU Han-zhi， AI Zhong-liang， ZHANG Zhi-chao . A Lightweight Target Detection Network Based on Channel Rearrangement [J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2020.02.019.

参考文献

［1］ SZEGEDY C, TOSHEV A, ERHAN D. Deep neural networks for object detection［C］// Proceedings of 2013 Advances in Neural Information Processing Systems(NIPS). 2013:2553-2561.
［2］ MERLIN P M, FARBER D J. A parallel mechanism for detecting curves in pictures［J］. IEEE Transactions on Computers, 1975,24(1):96-98.
［3］〖JP3〗SINGLA N. Motion detection based on frame difference method［J］. International Journal of Information & Computation Technology, 2014,4(15):1559-1565.
［4］ VIOLA P A, JONES M J. Rapid object detection using a boosted cascade of simple features［C］// Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001:511-518.
［5］ HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2018,PrePrints, DOI: 10.1109/TPAMI.2018.2844175.
［6］ REDMON J， DIVVALA S， GIRSHICK R， et al.You only look once: Unifled, real- time object detection［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. IEEE, 2016:779-788.
［7］ HOU Q B, CHENG M M, HU X W, et al. Deeply supervised salient object detection with short connections［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2017:5300-5309.
［8］ ERHAN D, SZEGEDY C, TOSHEV A, et al. Scalable object detection using deep neural networks［C］// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2014:2155-2162.
［9］ LIU W， ANGUELOV D， ERHAN D， et al. SSD： Single shot multibox detector［C］// Proceedings of the 14th European Conference on Computer Vision（ECCV）. Springer, 2016:21-37.
［10］GIRSHICK R. Fast R-CNN［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. IEEE, 2015:1440-1448.
［11］HOWARDA G, ZHU M L, CHEN B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications［J］. Computer Vision and Pattern Recognition, 2017: arXiv:1704.04861.
［12］ZHANG X Y, ZHOU X Y, LIN M X, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices［J］. Computer Vision and Pattern Recognition, 2017: arXiv:1707.01083.
［13］IOFFE S, SZEGEDYC. Batch normalization: Accelerating deep network training by reducing internal covariate shift［C］// Proceedings of the 32nd International Conference on Machine Learning(PMLR). 2015:448-456.
［14］张小锋,刘红铮. 基于卷积神经网络的花朵图片分类算法［J］. 计算机与现代化, 2018(9):52-55.
［15］张洪涛,路红英,刘腾飞,等. 基于深度学习的显著性检测方法模型——SCS［J］. 计算机与现代化, 2018(4):48-55.
［16］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. 2014:580-587.
［17］LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2015:3431-3440.
［18］UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al. Selective search for object recognition［J］. International Journal of Computer Vision, 2013,104(2):154-171.
［19］REDMON J， FARHADI A. Yolov3: An incremental improvement［J］. Computer Vision and Pattern Recognition, 2018: arXiv:1804.02767.
［20］JIA Y Q, SHELHAMER E, DONAHUE J, et al. Caffe: Convolutional architecture for fast feature embedding［C］// Proceedings of the 22nd ACM International Conference on Multimedia. 2014:675-678.
［21］HORN B K P, SCHUNCK B G. Determining optical flow［J］. Artificial Intelligence, 1981,17(1-3):185-203.
［22］REN S Q， HE K M， 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.
［23］DAI J F， LI Y， HE K M， et al. R-FCN: Object detection via region-based fully convolutional networks［C］// Proceedings of the 2016 Advances in Neural Information Processing System(NIPS). MIT, 2016:379-387.

[1]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[2]	欧嘉城, 曾安, 金亮. 基于CP-YOLOX的冷冻电镜图像蛋白质目标检测算法[J]. 计算机与现代化, 2023, 0(11): 113-119.
[3]	闫子贤, 董宝良, 唐思谜. 针对复杂背景下低分辨率舰船目标的改进YOLOv7算法[J]. 计算机与现代化, 2023, 0(11): 120-126.
[4]	顾成伟, 丁勇, 李登华. 基于计算机视觉的工业厂区人员安全警戒系统[J]. 计算机与现代化, 2023, 0(09): 20-26.
[5]	刘昱杉, 刘卫康, 刘庆华, 者甜甜, 王家晨. 基于YOLOX结合DeepSort的船载车辆行人检测算法[J]. 计算机与现代化, 2023, 0(08): 60-67.
[6]	欧阳飞, 吴旭, 向东升. 基于改进YOLOX的垃圾分类检测方法[J]. 计算机与现代化, 2023, 0(08): 68-73.
[7]	胡睿杰, 车逗. 红外小目标检测方法综述[J]. 计算机与现代化, 2023, 0(08): 79-86.
[8]	罗伟, 刘思远, 徐健祥, 董天培. 基于改进YOLOv5s的太阳能电池缺陷检测算法[J]. 计算机与现代化, 2023, 0(07): 119-126.
[9]	叶力鸣, 陈蔚文. 一种结合语义分割和目标检测的级联式绝缘子缺陷检测方法[J]. 计算机与现代化, 2023, 0(06): 82-88.
[10]	王艺成, 张国良, 张自杰, . 基于改进YOLOv5的小目标检测方法[J]. 计算机与现代化, 2023, 0(05): 100-105.
[11]	邱地发, 于淑芳, 刘锦辉, 毕梦昭. 基于YOLOv5s的遥感图像的车辆小目标检测[J]. 计算机与现代化, 2023, 0(05): 122-126.
[12]	郭之栋, 刘筠, 杨凡, 周昕, 陈亮亮. 基于机器视觉的智慧交通灯控制系统[J]. 计算机与现代化, 2023, 0(04): 101-105.
[13]	范新南, 陈馨洋, 史朋飞, 孙奂儒, 鹿亮, 周仲凯. 水下声呐图像轻量级目标检测模型[J]. 计算机与现代化, 2023, 0(03): 16-22.
[14]	陈卓, 乔贵方, 柴鑫波, 杜一君, 沈重霖, 王远浩. 基于改进知识蒸馏的多天候车辆检测方法[J]. 计算机与现代化, 2023, 0(02): 50-57.
[15]	盛江岸, 陈淑荣. 融合双重注意力机制的戴口罩人脸识别方法[J]. 计算机与现代化, 2023, 0(02): 72-77.

一种基于通道重排的轻量级目标检测网络

A Lightweight Target Detection Network Based on Channel Rearrangement

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价