Providing complete edge AI security by leveraging standard surveillance equipment

Abstract

By using Edge AI, video streams from regular cameras can be analyzed in real time at the network edge and used to make critical security decisions. They can detect if triggered events are true intrusions or just false alarms, and they can instantly send notifications directly to your mobile phone with recorded video and pictures.

Partner: Wesmart | Region: Israel

Introduction

For most homes and businesses, surveillance cameras play an ever-present role in security. The cameras are used to record all activities and provide a historical video record of those accounts. However, with the increased demand for enhanced security, real-time analysis has become a requirement. To complicate the situation, the additional enhancements necessitate a security system to provide precise event triggers and real-time alarm notifications. Therefore, the new security systems must incorporate technical solutions to allow for real-time identification of threats on a 24/7/365 basis and in various environments.

An instance of a complete solution includes the use of video streaming from standard surveillance cameras using Edge AI to analyze in real-time at the network edge and perform critical security functions. Through the use of advanced technology, the system can determine whether the type of event trigger is a security risk or a false alarm, thereby triggering an instant notification to the identified mobile phone with relevant video and image information. The particular development of such a system does come with added benefits, no additional cost for a security system, no additional installation of expensive sensors, and no additional high maintenance costs. 

System Requirements

This project was initiated as a result of real market needs to leverage existing, standard, inexpensive security, and surveillance equipment and systems for the development of smart security systems running special AI software. In this particular instance, the customer was looking for ways to boost personal security to offer a highly reliable, low-cost security surveillance system for its end users. The solutions needed to meet specific requirements, including: 

• Integration with standardized surveillance equipment
• Compliance with international standards
• Real-time image analysis, identification, alert warning, and notification
• System reliability and field-tested performance
•  Improved service quality
•  Cost-effective system
•  Certified products and stable production and supply
• Warranty and after-sale customer support

System Description

Devices on the first two layers operate in the same network. The analytical software receives real-time streaming protocol (RTSP) streams from cameras and uses the power of the MIC-710AIL to detect suspicious events via its deep neural network processing. A highly intelligent and sophisticated software pipeline was developed for exploiting the many accelerated technologies offered by NVIDIA for their embedded devices, and this allowed them to reliably process four camera streams, simultaneously, in real-time. The cloud part of the system provided the means to store and carry through all the notifications sent by the edge camera devices. This layer also has a website that allows clients to add users to the system, set up cameras, and select any camera for a region of interest (ROI) close-up scan. The fourth layer, in addition to its main function, allows to fine-tune notification behaviors for each camera (motion detection, face recognition, light sensitivity, event schedules, etc.).

Project Implementation

• MIC-710AI or MIC-710AIL (AI inference system with NVIDIA Jetson Nano)
• AI Trained model
• WeSmart surveillance solution
• Edge camera
  

Devices on the first two layers operate in the same network. The analytical software receives real time streaming protocol (RTSP) streams from cameras and uses the power of the Advantech MIC-710AI with NVIDIA Jetson Nano to detect suspicious events via its deep neural network processing. A highly intelligent and sophisticated software pipeline was developed for exploiting the many accelerated technologies offered by NVIDIA for their embedded devices, and this allowed them to reliably process four camera streams, simultaneously, in real time. The cloud part of the system provided the means to store and carry through all the notifications sent by the edge camera devices. This layer also has a website which allows clients to add users to the system, setup cameras, and select any camera for a region of interest (ROI) close up scan. The fourth layer, in addition to its main functionality allows refined definition to fine-tune notification behaviors for each camera (motion detection, face recognition, light sensitivity, event schedules, etc.).

Conclusion

With private households and business increasing their reliance on surveillance systems on security systems for personal and asset protection, leveraging existing infrastructure is even more important. This has led to a need to incorporate the use of Edge AI with proven hardware technology.

As a result, Advantech provided the customer with a complete product package that included all the elements required to build an upgraded system. The solution utilized existing surveillance components allowing the customer to simply focus on the software development side of the project. To be more specific, the reliance on Advantech products and services proved to be one of the most important aspects of the design, delivering cost savings, quality assurance, strong after-sales technical and service support. 

It’s the right choice for complete edge AI security solutions.