A Comparison of Embedded Deep Learning Methods for Person Detection

TL;DR

This paper compares various deep learning models for person detection in indoor retail environments, highlighting their speed and accuracy, and identifies YOLO v3-416 as a suitable model for embedded systems.

Contribution

It provides a comprehensive performance comparison of state-of-the-art deep learning detectors for indoor person detection using a proprietary dataset.

Findings

Tiny YOLO-416 and SSD are the fastest detectors.

Faster-RCNN and R-FCN are the most accurate detectors.

YOLO v3-416 offers a good balance of accuracy and speed for embedded platforms.

Abstract

Recent advancements in parallel computing, GPU technology and deep learning provide a new platform for complex image processing tasks such as person detection to flourish. Person detection is fundamental preliminary operation for several high level computer vision tasks. One industry that can significantly benefit from person detection is retail. In recent years, various studies attempt to find an optimal solution for person detection using neural networks and deep learning. This study conducts a comparison among the state of the art deep learning base object detector with the focus on person detection performance in indoor environments. Performance of various implementations of YOLO, SSD, RCNN, R-FCN and SqueezeDet have been assessed using our in-house proprietary dataset which consists of over 10 thousands indoor images captured form shopping malls, retails and stores. Experimental results indicate that, Tiny YOLO-416 and SSD (VGG-300) are the fastest and Faster-RCNN (Inception ResNet-v2) and R-FCN (ResNet-101) are the most accurate detectors investigated in this study. Further analysis shows that YOLO v3-416 delivers relatively accurate result in a reasonable amount of time, which makes it an ideal model for person detection in embedded platforms.