English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

There can be numerous electronic components on a given PCB, making the taskof visual inspection to detect defects very time-consuming and prone to error,especially at scale. There has thus been significant interest in automatic PCBcomponent detection, particularly leveraging deep learning. However, deepneural networks typically require high computational resources, possiblylimiting their feasibility in real-world use cases in manufacturing, whichoften involve high-volume and high-throughput detection with constrained edgecomputing resource availability. As a result of an exploration of efficientdeep neural network architectures for this use case, we introduce PCBDet, anattention condenser network design that provides state-of-the-art inferencethroughput while achieving superior PCB component detection performancecompared to other state-of-the-art efficient architecture designs. Experimentalresults show that PCBDet can achieve up to 2$\times$ inference speed-up on anARM Cortex A72 processor when compared to an EfficientNet-based design whileachieving $\sim$2-4\% higher mAP on the FICS-PCB benchmark dataset.

PCBDet: An Efficient Deep Neural Network Object Detection Architecture for Automatic PCB Component Detection on the Edge