Deep person re-identification in UAV images

Aleksei Grigorev,Seungmin Rho,Feng Jiang,Jianxin Xiong,Zhihong Tian,Shaohui Liu

doi:10.1186/s13634-019-0647-z

Abstract

The person re-identification is one of the most significant problems in computer vision and surveillance systems. The recent success of deep convolutional neural networks in image classification has inspired researchers to investigate the application of deep learning to the person re-identification. However, the huge amount of research on this problem considers classical settings, where pedestrians are captured by static surveillance cameras, although there is a growing demand for analyzing images and videos taken by drones. In this paper, we aim at filling this gap and provide insights on the person re-identification from drones. To our knowledge, it is the first attempt to tackle this problem under such constraints. We present the person re-identification dataset, named DRone HIT (DRHIT01), which is collected by using a drone. It contains 101 unique pedestrians, which are annotated with their identities. Each pedestrian has about 500 images. We propose to use a combination of triplet and large-margin Gaussian mixture (L-GM) loss to tackle the drone-based person re-identification problem. The proposed network equipped with multi-branch design, channel group learning, and combination of loss functions is evaluated on the DRHIT01 dataset. Besides, transfer learning from the most popular person re-identification datasets is evaluated. Experiment results demonstrate the importance of transfer learning and show that the proposed model outperforms the classic deep learning approach.

Highlights

Person re-identification problem has attracted the attention of the computer vision community due to its significant role in modern surveillance systems
The existed datasets are composed of images captured from static CCTV cameras, those cameras are part of the existed surveillance systems, and the datasets were collected under real-life conditions
The CUHK-SYSU dataset is richer in terms of the image backgrounds, occlusion, light conditions, etc. Such difference is critical for the transfer learning, and according to Table 1 for the same margin, the fine-tuning on the DRHIT01 datasets produces significantly different results

Summary

Introduction

Person re-identification (re-id) problem has attracted the attention of the computer vision community due to its significant role in modern surveillance systems. The impressive performance of deep convolutional neural networks (CNN) in the image classification task made deep CNN one of the most significant tools for computer vision It has caused the performance push and has inspired researchers to collect and release more complicated re-id datasets. Re-id has been mostly studied in default constraints, where images or videos were collected by static CCTV cameras Such cameras lack mobility and typically requires a big amount of time to set up Accompanied by deep learning, research on person reid has already achieved impressive performance on the most popular re-id benchmark datasets. The existed datasets are composed of images captured from static CCTV cameras, those cameras are part of the existed surveillance systems, and the datasets were collected under real-life conditions It does not cover all use-cases, under which person re-identification may be required.

Methods

Results

Conclusion