PMID- 35888875
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220731
IS  - 2072-666X (Print)
IS  - 2072-666X (Electronic)
IS  - 2072-666X (Linking)
VI  - 13
IP  - 7
DP  - 2022 Jun 30
TI  - An Efficient YOLO Algorithm with an Attention Mechanism for Vision-Based Defect 
      Inspection Deployed on FPGA.
LID - 10.3390/mi13071058 [doi]
LID - 1058
AB  - Industry 4.0 features intelligent manufacturing. Among them, the vision-based 
      defect inspection algorithm is remarkable for quality control in parts 
      manufacturing. With the help of AI and machine learning, auto-adaptive instead of 
      manual operation is achievable in this field, and much progress has been made in 
      recent years. In this study, considering the demand of inspection features in 
      industrialization, we made further improvement in smart defect inspection. An 
      efficient algorithm using Field Programmable Gate Array (FPGA)-accelerated You 
      Only Look Once (YOLO) v3 based on an attention mechanism is proposed. First, 
      because of the relatively fixed camera angle and defect features, an attention 
      mechanism based on the concept of directing the focus of defect inspection is 
      proposed. The attention mechanism consists of three improvements: (a) image 
      preprocessing, which is to tailor images for selectively concentrating on the 
      defect relevant things. Image preprocessing mainly includes cutting, zooming and 
      splicing, named CZS operations. (b) Tailoring the YOLOv3 backbone network, which 
      is to ignore invalid inspection regions in deep neural networks and optimize the 
      network structure. (c) Data augmentation. First, two improvements can be made to 
      efficiently reduce deep learning operations and accelerate the inspection speed, 
      but the preprocessed images are similar and the lack of diversity will reduce 
      network accuracy. So, (c) is added to mitigate the lack of considerable amounts 
      of training data. Second, the algorithm is deployed on a PYNQ-Z2 FPGA board to 
      meet the industrialization production requirements for accuracy, efficiency and 
      extensibility. FPGA can provide a low-latency, low-cost, high-power-efficiency 
      and flexible architecture that enables deep learning acceleration for industrial 
      scenarios. A Xilinx Deep Neural Network Development Kit (DNNDK) converted the 
      improved YOLOv3 to Programmable Logic (PL), which can be deployed on FPGA. The 
      conversion process mainly consists of pruning, quantization and compilation. 
      Experimental results showed that the algorithm had high efficiency, inspection 
      accuracy reached 99.2%, processing speed reached 1.54 Frames per Second (FPS), 
      and power consumption was only 10 W.
FAU - Yu, Longzhen
AU  - Yu L
AUID- ORCID: 0000-0002-6594-6679
AD  - College of Economics and Management, Qingdao University of Science and 
      Technology, Qingdao 266000, China.
FAU - Zhu, Jianhua
AU  - Zhu J
AUID- ORCID: 0000-0003-4297-1836
AD  - College of Economics and Management, Qingdao University of Science and 
      Technology, Qingdao 266000, China.
FAU - Zhao, Qian
AU  - Zhao Q
AD  - Department of Creative Informatics, Kyushu Institute of Technology, Fukuoka 
      804-8550, Japan.
FAU - Wang, Zhixian
AU  - Wang Z
AD  - College of Economics and Management, Qingdao University of Science and 
      Technology, Qingdao 266000, China.
LA  - eng
GR  - 2020B0101050001/the R&D Project in Key Areas of Guangdong Province/
PT  - Journal Article
DEP - 20220630
PL  - Switzerland
TA  - Micromachines (Basel)
JT  - Micromachines
JID - 101640903
PMC - PMC9323378
OTO - NOTNLM
OT  - FPGA
OT  - YOLO
OT  - attention
OT  - defect inspection
OT  - vision
COIS- The authors declare no conflict of interest.
EDAT- 2022/07/28 06:00
MHDA- 2022/07/28 06:01
PMCR- 2022/06/30
CRDT- 2022/07/27 01:32
PHST- 2022/06/03 00:00 [received]
PHST- 2022/06/28 00:00 [revised]
PHST- 2022/06/28 00:00 [accepted]
PHST- 2022/07/27 01:32 [entrez]
PHST- 2022/07/28 06:00 [pubmed]
PHST- 2022/07/28 06:01 [medline]
PHST- 2022/06/30 00:00 [pmc-release]
AID - mi13071058 [pii]
AID - micromachines-13-01058 [pii]
AID - 10.3390/mi13071058 [doi]
PST - epublish
SO  - Micromachines (Basel). 2022 Jun 30;13(7):1058. doi: 10.3390/mi13071058.