Low-Latency In Situ Image Analytics With FPGA-Based Quantized Convolutional Neural Network

Maolin Wang, Kelvin C.M. Lee, Bob M.F. Chung, Sharat Chandra Varma B, Ho Cheung Ng, Justin Wong, Ho Cheung Shum, Kevin K Tsia, Hayden Kwok-Hay So

Research output: Contribution to journalArticlepeer-review

5 Downloads (Pure)

Abstract

Real-time in-situ image analytics impose stringent
latency requirements on intelligent neural network inference
operations. While conventional software-based implementations
on GPU-accelerated platforms are flexible and have achieved
very high inference throughput, they are not suitable for latencysensitive
applications where real-time feedback are needed. Here
we demonstrate that high-performance reconfigurable computing
platforms based on field-programmable gate array (FPGA)
processing can successfully bridge the gap between low-level
hardware processing and high-level intelligent image analytics algorithm
deployment within a unified system. The proposed design
performs inference operations on a stream of individual images
as they are produced, and has a deeply pipelined hardware design
that allows all layers of a quantized convolutional neural network
(QCNN) to compute concurrently with partial image inputs.
Using the case of label-free classification of human peripheral
blood mononuclear cell (PBMC) sub-types as a proof-of-concept
illustration, our system achieves an ultra-low classification latency
of 34.2 μs with over 95% end-to-end accuracy by using a
QCNN while the cells are imaged at throughput exceeding
29 200 cells/sec. Our QCNN design is modular and is readily
adaptable to other QCNNs with different latency and resource
requirements.
Original languageEnglish
Number of pages13
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
Publication statusPublished - 12 Jan 2021

Keywords

  • Low latency inference
  • Reconfigurable computing
  • FPGA
  • Cell image classification
  • QCNN
  • Multi-ATOM
  • Real-time Image Analytics
  • Neural network
  • Optical Cytometry

Fingerprint Dive into the research topics of 'Low-Latency In Situ Image Analytics With FPGA-Based Quantized Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this