Where's The Bear (WTB)?

Automating Wildlife Image Processing Using IoT
and Edge Cloud Systems

Project Overview

WTB is a research project that investigates the design and implementation of an end-to-end, distributed, Internet of Things (IoT) system for wildlife monitoring. WTB

  • Is a multi-tier (public/private cloud, edge, sensing) system that integrates recent advances in machine learning based image processing to automatically classify animals in images from remote, motion-detection camera traps.
  • Uses non-local, resource-rich, public/private cloud systems to train machine learning models, and ``in-the-field,'' resource-constrained edge systems to perform classification near the IoT sensing devices (cameras).
  • Trains models using only empty images synthesized with randomly placed animal images from Google Images.
  • Relieves scientists and citizen scientists of the burden of manual image classification and saves time and bandwidth for image transfer off-site by automatically filtering the images on-site based on characteristics of interest.
  • Is deployed at the UCSB Sedgwick Reserve, a 6000 acre site for environmental research and used to aggregate, manage, and analyze over 1.12M images.

Team

Support

  • NSF ACI-1541215 (Aristotle)
  • NSF CNS-1703560 (DatGeo)
  • NSF CCF-1539586 (SmartFarm)

Publications and Presentations (Edge Computing and Analytics)

  • WTB News Story
  • WTB Presentation; Paper; Poster
  • R. Wolski, C. Krintz, F. Bakir, G. George, and W-T. Lin, CSPOT: Portable, Multi-scale Functions-as-a-Service for IoT (PDF), ACM Symposium on Edge Computing (SEC), Nov 2019
  • F. Bakir, R. Wolski, C. Krintz, and G. Sankar Ramachandran, Devices-as-Services: Rethinking Scalable Service Architectures for the Internet of Things (PDF), USENIX HotEdge, July 2019
  • M. Zhang, C. Krintz, R. Wolski, and M. Mock, Seneca: Fast and Low Cost Hyperparameter Search for Machine Learning Models (PDF), IEEE Cloud, July 2019
  • K. Carson, J. Thomason, M. Mock, R. Wolski and C. Krintz, Mandrake: Implementing Durabilty for Edge Clouds (PDF), IEEE Edge, July 2019
  • W-T. Lin, F. Bakir, C. Krintz, R. Wolski, and M. Mock, Data repair for Distributed, Event-based IoT Applications (PDF), ACM International Conference On Distributed and Event-Based Systems, June 2019
  • A. Rosales Elias, N. Golubovic, R. Wolski, and C. Krintz, Where's The Bear? -- Automating Wildlife Image Processing Using IoT and Edge Cloud Systems (PDF), ACM Conference on IoT Design and Implementation, April, 2017; was UCSB TR2016-07
  • The UCSB Lab for Research on Adaptive Computing Environments (RACELab)
  • Related project: UCSB Smartfarm
  • Related project: Next Generation Cloud Systems