Deep learning-based target tracking and classification for low quality videos using coded aperture cameras

Chiman Kwan, Bryan Chou, Jonathan Yang, Akshay Rangamani, Trac Tran, Jack Zhang, Ralph Etienne-Cummings

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

Compressive sensing has seen many applications in recent years. One type of compressive sensing device is the Pixel-wise Code Exposure (PCE) camera, which has low power consumption and individual control of pixel exposure time. In order to use PCE cameras for practical applications, a time consuming and lossy process is needed to reconstruct the original frames. In this paper, we present a deep learning approach that directly performs target tracking and classification in the compressive measurement domain without any frame reconstruction. In particular, we propose to apply You Only Look Once (YOLO) to detect and track targets in the frames and we propose to apply Residual Network (ResNet) for classification. Extensive simulations using low quality optical and mid-wave infrared (MWIR) videos in the SENSIAC database demonstrated the efficacy of our proposed approach.

Original languageEnglish (US)
Article number3702
JournalSensors (Switzerland)
Volume19
Issue number17
DOIs
StatePublished - Sep 1 2019
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Keywords

  • Compressive sensing
  • MWIR
  • Optical
  • Pixel-wise code exposure camera
  • Resnet
  • Target classification
  • Target tracking
  • YOLO

Fingerprint

Dive into the research topics of 'Deep learning-based target tracking and classification for low quality videos using coded aperture cameras'. Together they form a unique fingerprint.

Cite this