DeepDish on a diet

Danish, Matthew; Verma, Rohit; Brazauskas, Justas; Lewis, Ian; Mortier, Richard

doi:10.1145/3517206.3526273

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the results of such implementations perform well in terms of accuracy and speed, thier power usage limits their viability in large scale projects. In response, the DeepDish [1], [2] project implemented Multi-Object Tracking using low power solutions to maintain reasonable accuracy while reducing power consumption.…”

Section: Introductionmentioning

confidence: 99%

Anonymising Video Data Collection at the Edge Using DeepDish

Pan

Kolcun

Mortier

2023

2023 IEEE 24th International Conference on High Performance Switching and Routing (HPSR)

Self Cite

View full text Add to dashboard Cite

Increase in popularity of various deep learning methodologies has led to a huge increase in demand for training data. These training data often contain video featuring people but these videos often cannot be used due to privacy concerns as people are identifiable. We present an extension to the DeepDish object tracking system running on a Raspberry Pi. DeepDish performs object detection in the Raspberry Pi itself, avoiding the need to ship raw video data off the device. Our extension adds online face detection and blurring to preserve privacy. We implement and evaluate four different face detection algorithms, achieving 83% accuracy using YuNet, while increasing the latency by 75%. We then implement and evaluate three different object tracking algorithms to reduce the latency increase by running the simpler object tracking algorithm, reducing the number of calls to the expensive face detection algorithm. The result is a significant decrease in latency at the cost of a small decrease in accuracy. We also implemented and compared three different face obfuscation algorithms, one of which achieves differential privacy.

show abstract

Section: Introductionmentioning

confidence: 99%