Comparison of Two Types YOLOv4-tiny Simplified Networks and Their Crack Detection Performance
CSTR:
Author:
Affiliation:

1.Student Innovation Center, Shanghai Jiao Tong University,Shanghai 200240, China;2.School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Clc Number:

TP391.4

  • Article
  • | |
  • Metrics
  • |
  • Reference [25]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    To meet the demands of crack detection market in domestic tall buildings, taking the shortcomings of the fact that the existing YOLOv4-tiny deep network structure runs slowly on such edge devices as Raspberry Pi into account, two novel simplified YOLOv4-tiny deep network structures, that is, YOLOv4-lite1 and YOLOv4-lite2 were deduced by removing the second residual network, as well as adding a maxpool layer and changing the connection of the last route layer in this paper. The training set, the test set, and the verification set data of crack detection were then generated by using the crack pictures downloaded from the internet, and the training is conducted on a 64-bit Ubuntu16.04 system utilizing the Darknet deep learning framework. At the same time, the actual tests on the RaspberryPI 4B show that the YOLOv4-lite1 structure has a faster running speed, detection rate, and stability compared to the YOLOv4-lite2 structure. Finally, the next step of this related work is pointed out. The innovation of this research lies in further simplifying the YOLOv4-tiny network structure and the connection of the last layer route layer, thus obtaining two new YOLOv4-tiny deep network structures and better detection results.

    Reference
    [1] 蔡青竹.基于人工智能的语音识别分析[J].集成电路应用,2020,37(9): 6.
    [2] 房爱东,张志伟,崔琳,等.基于人工智能的语音识别系统及应用研究[J].宿州学院学报,2019,34(8): 62.
    [3] 傅山,王嘉义,宁华,等. 基于人工智能的人脸识别技术与评估体系研究[J].信息通信技术与政策,2021,47(4):71.
    [4] 冯文宇,朱洪堃,殷佳炜,等. 无人CT智能姿态识别算法研究[J]. 仪器仪表学报, 2020,41(8):188.
    [5] 张欣,齐华.基于YOLOv4的人体异常行为检测算法研究[J].计算机与数字工程,2021,49(4):791.
    [6] 王曼然. 基于红外热像图的变电设备故障检测与识别研究[D].恩施: 湖北民族大学,2020.
    [7] 孙兴达,郝赫,刘远,等.YOLOv4在电力巡检目标检测中的应用[J]. 现代信息科技,2020,4(20):115.
    [8] 袁纵青.基于机器视觉的汽车零部件字符检测系统设计与实现[D].徐州:中国矿业大学,2020.
    [9] 唐小煜,黄进波,冯洁文,等.基于U-net和YOLOv4的绝缘子图像分割与缺陷检测[J].华南师范大学学报(自然科学版),2020,52(6):15.
    [10] 张明琦,范影乐,武薇. 基于初级视通路视觉感知机制的轮廓检测方法[J].自动化学报,2020,46(2):264.
    [11] 王伟杰,姚建涛,张敏燕,等.基于YOLOV4的智能垃圾分类回收机器人[J].智能计算机与应用,2020,10(11):182.
    [12] 王淑青,黄剑锋,张鹏飞,等.基于YOLOv4神经网络的小龙虾质量检测方法[J].食品与机械,2021,37(3):120.
    [13] 席芮,姜凯,张万枝,等.基于改进Faster R-CNN的马铃薯芽眼识别方法[J].农业机械学报,2020,51(4):216.
    [14] 钟嘉俊,贺德强,苗剑,等.基于改进Faster R-CNN的地铁车辆焊缝缺陷检测[J].铁道科学与工程学报,2020,17(4):996.
    [15] 张骏,朱标,吉涛.基于MobileNet-SSD的红外人脸检测算法[J].激光与红外,2021,51(1):107.
    [16] 王焕民,张建柏,裴华艳,等.基于MobileNet-SSD的铁路信号灯检测识别[J].兰州交通大学学报,2020,39(4):66.
    [17] Bochkovskiy A, WAND C Y, LIAO H Y M.YOLOv4: Optimal speed and accuracy of object detection [EB/OL]. [2020-04-23].https://arxiv.org/abs/2004.10934.
    [18] WAND C Y,BOCHKOVSKIY A, LIAO H Y M.Scaled-YOLOv4: Scaling cross stage partial network [EB/OL]. [2020-11-16].https://arxiv.org/abs/2011.08036.
    [19] 万卓,叶明,刘凯.基于改进YOLOv4的电机端盖缺陷检测[J].计算机系统应用,2021,30(3):79.
    [20] 王兵,乐红霞,李文璟,等.改进YOLO轻量化网络的口罩检测算法[J].计算机工程与应用,2021,57(8):62.
    [21] 解尧婷,张丕状.基于改进的YOLOv4输电线路小目标检测[J].国外电子测量技术, 2021,40(2):47.
    [22] 王昕,寇云峰,辛浪,等.手机拍摄行为智能识别优化研究[J].通信技术,2021,54(1):244.
    [23] 符惠桐,王鹏,李晓艳,等.面向移动目标识别的轻量化网络模型[J].西安交通大学学报, 2021 ,55(7):124.
    [24] 蔡舒平,孙仲鸣,刘慧,等. 基于改进型YOLOv4的果园障碍物实时检测方法[J].农业工程学报,2021,37(2):36.
    [25] 张凯,罗欣,孙志刚,等.基于轻量化YOLOv4的发电机定子表面缺陷检测算法[J].计算机与数字工程,2021,49(4):686.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

SONG Libo, FEI Yanqiong. Comparison of Two Types YOLOv4-tiny Simplified Networks and Their Crack Detection Performance[J].同济大学学报(自然科学版),2022,50(1):129~137

Copy
Share
Article Metrics
  • Abstract:281
  • PDF: 630
  • HTML: 64
  • Cited by: 0
History
  • Received:March 12,2021
  • Online: February 17,2022
Article QR Code