loading page

PCBDet: An Efficient Deep Neural Network Object Detection Architecture for Automatic PCB Component Detection on the Edge
  • +3
  • Brian Li,
  • Steven Palayew,
  • Francis Li,
  • Saad Abbasi,
  • Saeejith Nair,
  • Alexander Wong
Brian Li
University of Waterloo Faculty of Engineering

Corresponding Author:b384li@uwaterloo.ca

Author Profile
Steven Palayew
DarwinAI
Author Profile
Francis Li
DarwinAI
Author Profile
Saad Abbasi
University of Waterloo Faculty of Engineering
Author Profile
Saeejith Nair
University of Waterloo Faculty of Engineering
Author Profile
Alexander Wong
University of Waterloo Faculty of Engineering
Author Profile

Abstract

There can be numerous electronic components on a given PCB, making the task of visual inspection to detect defects very time-consuming and prone to error, especially at scale. There has thus been significant interest in automatic PCB component detection, particularly leveraging deep learning. However, deep neural networks typically require high computational resources, possibly limiting their feasibility in real-world use cases in manufacturing, which often involve high-volume and high-throughput detection with constrained edge computing resource availability. As a result of an exploration of efficient deep neural network architectures for this use case, we introduce PCBDet, an attention condenser network design that provides state-of-the-art inference throughput while achieving superior PCB component detection performance compared to other state-of-the-art efficient architecture designs. Experimental results show that PCBDet can achieve up to 2× inference speed-up on an ARM Cortex A72 processor when compared to an EfficientNet-based design while achieving ∼2-4% higher mAP on the FICS-PCB benchmark dataset.
04 Jun 2023Submitted to Electronics Letters
05 Jun 2023Submission Checks Completed
05 Jun 2023Assigned to Editor
11 Jun 2023Reviewer(s) Assigned
03 Oct 2023Review(s) Completed, Editorial Evaluation Pending
16 Oct 2023Editorial Decision: Revise Major
10 Nov 20231st Revision Received
13 Nov 2023Submission Checks Completed
13 Nov 2023Assigned to Editor
13 Nov 2023Review(s) Completed, Editorial Evaluation Pending
13 Nov 2023Reviewer(s) Assigned
20 Nov 2023Editorial Decision: Accept