Chip Contour Detection Based on Real-time Image Sensing and Recognition

被引:1
|
作者
Chang, Bao-Rong [1 ]
Tsai, Hsiu-Fen [2 ]
Hsieh, Chia-Wei [1 ]
Chen, Mo-Lan [3 ]
机构
[1] Natl Univ Kaohsiung, Dept Comp Sci & Informat Engn, 700 Kaohsiung Univ Rd, Kaohsiung 811, Taiwan
[2] Kaohsiung Med Univ, Dept Fragrance & Cosmet Sci, 100 Shih Chuan 1st Rd, Kaohsiung 80708, Taiwan
[3] NXP Semicond Taiwan Ltd, 10 Jing 5th Rd, Kaohsiung 811, Taiwan
关键词
deep learning; Jetson Nano; object tracking; real-time image sensing and recognition; GSEH; YOLOv5; attention mechanism; SENet; GhostNet;
D O I
10.18494/SAM3378
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
In this study, the GSEH-YOLOv5 (GhostNet and SENet included in Head-YOLOv5) algorithm is used to realize real-time object tracking and image sensing and recognition on the Jetson Nano embedded platform. The purpose is to instantly detect the appearance contour of the chip inside the chip slot. As soon as our system detects the damaged chip, a warning is generated, and the correct location of the damaged chip in the chip slot is labeled. After that, the operator immediately removes the damaged chip to prevent the next chip from being damaged. Finally, we also analyze and compare the performance between the improved GSEH-YOLOv5 algorithm and the traditional YOLOv5 algorithm to verify that the proposed method has the better performance.
引用
收藏
页码:1077 / 1089
页数:13
相关论文
共 50 条
  • [1] Real-Time Digital Image Stabilization Based on Contour
    周渝斌
    赵跃进
    [J]. Journal of Beijing Institute of Technology, 2003, (S1) : 62 - 65
  • [2] Real-time Pupil Detection based on Contour Tracking
    Gu, Ke-ke
    Dong, Yue-fang
    Zhou, Zhe
    Liu, Min
    Chen, Shi
    Fu, Wei-wei
    [J]. CURRENT TRENDS IN COMPUTER SCIENCE AND MECHANICAL AUTOMATION (CSMA), VOL 2, 2017, : 31 - 40
  • [3] Real-Time φ-OTDR Vibration Event Recognition Based on Image Target Detection
    Yang, Nachuan
    Zhao, Yongjun
    Chen, Jinyang
    [J]. SENSORS, 2022, 22 (03)
  • [4] Real-Time Contour Image Vectorization on GPU
    Xiong, Xiaoliang
    Feng, Jie
    Zhou, Bingfeng
    [J]. COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VISIGRAPP 2016, 2017, 693 : 35 - 50
  • [5] Demo: Real-time contour-based pedestrian detection
    Rauter, Michael
    Shao, Dan
    Beleznai, Csaba
    [J]. 2012 SIXTH INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS (ICDSC), 2012,
  • [6] A real-time image denoising chip
    Chen, Pei-Yin
    Lien, Chih-Yuan
    Lin, Yi-Ming
    [J]. PROCEEDINGS OF 2008 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-10, 2008, : 3390 - 3393
  • [7] Real-time gesture recognition system based on contour signatures.
    Peixoto, P
    Gonçalves, J
    Araújo, H
    [J]. 16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL I, PROCEEDINGS, 2002, : 447 - 450
  • [8] Contour-based image compression for fast real-time coding
    Vasilyev, S
    [J]. ASTRONOMICAL DATA ANALYSIS SOFTWARE AND SYSTEMS VIII, 1999, 172 : 133 - 136
  • [9] Real-time damage detection based on pattern recognition
    Santos, Joao
    Cremona, Christian
    Silveira, Paulo
    Calado, Luis
    [J]. STRUCTURAL CONCRETE, 2016, 17 (03) : 338 - 354
  • [10] A contour method for real-time range image parsing
    Chauvin, N
    Marti, G
    Konolige, K
    [J]. 1998 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS - PROCEEDINGS, VOLS 1-3: INNOVATIONS IN THEORY, PRACTICE AND APPLICATIONS, 1998, : 1528 - 1533