Security Company
SURVEILLANCE & MONITORING
Faster response time with rapid resource deployment
surveillance security drone for on premise monitoring
Client Required an aerial surveillance system to compliment existing fixed location cctv infrastructure, with a growing working area conventional systems get expensive while having limitations.
Traditionally, traffic surveillance and security requirements for large areas were met by installing fixed CCTV cameras in strategic locations, providing the maximum possible coverage with the available infrastructure options. This kind of set up necessitates a high capital outlay in terms of equipment and supporting infrastructure adjustments, while often not providing a100% coverage capability.
In addition, the cost of maintaining such a large base of discrete and sparsely deployed components provides additional non-value adding costs that then need to be accounted for by the organization.
Case study
Unmanned aerial vehicles have become cheaper because many control functions can be implemented in software rather than having to depend on expensive hardware. This even allows multiple UAVs to be used for a single application. In this case, the UAVs must have communication facilities so that they can communicate with each other. This can easily be achieved by equipping an UAV with a wireless mesh node. In this scenario, the UAV swarm can be considered to be a highly mobile wireless mesh network.
Implementation: Autonomous/Self Flying Drone Swarm
An autonomous drone can fly by itself, without the need of a remote control, in some intelligent way: by following a person or an object of interest, for example, and also avoid obstacles. Imagine how could it be if you could go for a run, or go skiing, skating, swimming, and the drone would follow you, like a pet, filming all your adventures.
For the solution we focused on object detection, using recent breakthroughs in deep learning, sensors pickup movement and a drone is coordinated to the scene, this is achieved through person detection and following using Object detection using Fast R-CNN and BrainScript and cnkt.exe, backend solution hosted securely on azure AKS.
Project Architecture and Technologies
The Internet of Things is the convergence of artificial intelligence, cloud, and edge computing. Containerize cloud workloads—such as Azure Cognitive Services, Machine Learning, Stream Analytics, and Functions—and run them locally on devices from a Raspberry Pi to an industrial gateway using Azure IoT Edge.
container
Docker is a computer program that performs operating-system-level virtualization, also known as "containerization".
orchestration
Kubernetes, pronounced "Kū-bər-NəT-ēz" is an open-source container-orchestration system for automating deployment, scaling and management of containerized applications
Cloud
Microsoft Azure is a cloud computing service created by Microsoft for building, testing, deploying, and managing applications and services through a global network of Microsoft-managed data centers.
Support
Microsoft Cognitive Toolkit, previously known as CNTK and sometimes styled as The Microsoft Cognitive Toolkit, is a deep learning framework developed by Microsoft Research
