Intelligent security inspection systems

May '19 - Jul '19

nuctech logo

Baggage Re-Identification for Smart Security Inspection:

  • Updated existing model from verification scheme (Siamese nets) to the latest embedding scheme after implementing 5 models in PyTorch and evaluating performance on baggage datasets with hyperparam search.

  • Achieved 0.76 accuracy of CMC rank-1 on image retrieval from a 500-baggage gallery, improving baseline by 80.9% in accuracy and about 10x in speed.

Framework Development:

  • Migrated research framework from C/Caffe to Python/PyTorch and developed additional features including activation visualization, checkpointing, and metrics platform integration.

This site is a migration from my old personal page and is still under active construction. - Jan 2021

Modifications © Tianyu Zhang 2021. Original source © R. Miles McCain 2020. Content is licensed CC BY-SA 4.0, a Free Culture License. The source code is available under GPLv3.