Real-time Person Re-identification at the Edge: A Mixed Precision Approach

08/19/2019
by   Mohammadreza Baharani, et al.
0

A critical part of multi-person multi-camera tracking is person re-identification (re-ID) algorithm, which recognizes and retains identities of all detected unknown people throughout the video stream. Many re-ID algorithms today exemplify state of the art results, but not much work has been done to explore the deployment of such algorithms for computation and power constrained real-time scenarios. In this paper, we study the effect of using a light-weight model, MobileNet-v2 for re-ID and investigate the impact of single (FP32) precision versus half (FP16) precision for training on the server and inference on the edge nodes. We further compare the results with the baseline model which uses ResNet-50 on state of the art benchmarks including CUHK03, Market-1501, and Duke-MTMC. The MobileNet-V2 mixed precision training method can improve both inference throughput on the edge node, and training time on server 3.25× reaching to 27.77fps and 1.75×, respectively and decreases power consumption on the edge node by 1.45×, while it deteriorates accuracy only 5.6% in respect to ResNet-50 single precision on the average for three different datasets. The code and pre-trained networks are publicly available at https://github.com/TeCSAR-UNCC/person-reid.

READ FULL TEXT

page 6

page 7

research
06/04/2020

FastReID: A Pytorch Toolbox for Real-world Person Re-identification

We present FastReID, as a widely used object re-identification (re-id) s...
research
03/28/2018

Features for Multi-Target Multi-Camera Tracking and Re-Identification

Multi-Target Multi-Camera Tracking (MTMCT) tracks many people through vi...
research
06/16/2021

Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight

This paper addresses unsupervised person re-identification (Re-ID) using...
research
05/31/2021

Large-Scale Spatio-Temporal Person Re-identification: Algorithm and Benchmark

Person re-identification (re-ID) in the scenario with large spatial and ...
research
08/12/2020

Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds

With the development of deep learning technologies, attribute recognitio...
research
05/22/2018

Resource Aware Person Re-identification across Multiple Resolutions

Not all people are equally easy to identify: color statistics might be e...
research
12/08/2020

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

The main difficulty of person re-identification (ReID) lies in collectin...

Please sign up or login with your details

Forgot password? Click here to reset