Suspect Tracking through Person ReIdentification

The ability to identify the same person from multiple camera views without the explicit use of facial recognition is receiving commercial and academic interest. The current status-quo solutions are based on attention neural models. In this paper, we propose Attention and CL loss, which is a hybrid o

Project Title

Suspect Tracking through Person ReIdentification

Project Area of Specialization

Artificial Intelligence

Project Summary

The ability to identify the same person from multiple camera views without the explicit use of facial recognition is receiving commercial and academic interest. The current status-quo solutions are based on attention neural models. In this paper, we propose Attention and CL loss, which is a hybrid of center and Online Soft Mining (OSM) loss added to the attention loss on top of a temporal attention-based neural network. The proposed loss function applied with bag-of-tricks for training surpasses the state of the art on the common person Re-ID datasets, PRID 2011. Video-based person reID is an important task, which has received much attention in recent years due to the increasing demand in surveillance and camera networks. A typical video-based person reID system consists of three parts: an image-level feature extractor (e.g. CNN), a temporal modeling method to aggregate temporal features and a loss function. Although many methods on temporal modeling have been proposed, it is hard to directly compare these methods, because the choice of feature extractor and loss function also have a large impact on the final performance. We comprehensively implement temporal modeling method for person reID. The evaluation is done on the PRID dataset, and our methods outperform state-of-the-art methods by a large margin.

Project Objectives

Re-ID aims to detect whether a person-of-interest has appeared in another location at a different time captured by a different camera, or even the same camera at a different time instant captured by the same camera. An image, a video sequence, or even a text description might be used to illustrate a person’s enquiry. The aim of the project is to use technology to allow assistance for surveillance and bring automation to security systems to efficiently and accurately identify events.

• Aim to identify a person from multiple camera views.

• To improve the time efficiency.

• Labor saving.

Project Implementation Method

The challenge of retrieving a certain person in different photos or videos, maybe captured from different cameras in different surroundings, is addressed by Person re-Identification (re-ID). It has gotten more attention in recent years as a result of rising public safety demands and quickly expanding surveillance camera networks. It has a wide range of practical uses; for example, in a huge scene, it can save a lot of people and material resources. However because to various uncontrollable difficult environment aspects such as time-varying light conditions, human position changes and partial occlusion, it remain a challenge.

Implementation: 
- Resnet50

- Bag of Tricks

- Attention Model

- PRID2011 Dataset

- Self Generated Dataset

Benefits of the Project

Automate monitoring system. 

Identify a person from multiple camera views.

Improve the time efficiency.

Labor saving.

Technical Details of Final Deliverable

Web Portal integrted with Re-Identification System

Final Deliverable of the Project

Software System

Core Industry

Security

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com