SMART AND COMPACT SECURITY CAMERA SYSTEM

Background

Many existing commercial/industrial security solutions make use of expensive and complex security camera systems. Design and develop a cost effective IoT-based add-on system that enhances the capability of various existing legacy sensors such as motion detectors, so that they can be integrated to provide a secured and affordable smart commercial/industrial security service that can be standalone, or used in tandem with camera systems. Alternatively, design and develop a cost effective IoT-based complete security system that is based on multiple sensor inputs, and can be deployed in a commercial/industrial setting.

Requirements

We have curated information and resources which might be useful for you to prepare your proposal. Use of the resources provided does not offer you any advantage in the challenge and you are free to use any other technologies that you deemed more suitable or better than what's provided here.

  UWB Radar

Impulse UWB technology is traditionally used as long range UWB radar, primarily for military applications.

This technology offering is short range and high resolution radar using frequency range and emission power which is certified for commercial use.     

  Crowd Density Monitoring System

This is a platform in the cloud where crowd monitoring projects can be setup and configured. Camera integrated Raspberry Pi units are used as the built-in camera can be configured through a web portal to take photos periodically.

  Automatic Detection of Aggression in Crowds

Using our powerful video analytics algorithm on CCTV footage, aggression in crowds and large spaces can automatically be detected with high accuracy. Alerts are automatically generated as soon as aggression is detected, allowing for a direct response to prevent the situation from escalating.

  WALA Cam

As compared to today’s conventional lenses, which are rotationally symmetrical and have inflexible design constraints, DynaOptic’s lenses are rotationally asymmetrical and possess more design flexibility.

  Computer vision platform to solve real problems directly on compute-constrained embedded devices.

Pilot AI is a drop-in neural network solution for computer vision applications.

 

  DeepView ML Toolkit and RunTime Inference Engine

DeepView is a graphical Toolkit and hardware accelerated Run-Time inference engine specifically developed to help embedded engineers design, train and deploy Convolutional Neural Networks (CNNs) on embedded platforms.

  Deploying Convolutional Neural Network on Cortex-M with CMSIS-NN

Learn how to deploy a trained Neural Network (NN) model (using Caffe as an example) on those constrained platforms with the Arm CMSIS-NN software library. We will walk through following steps:

  STRAIT: Secure and Privacy-Customisable Data Transmission for Internet-of-Things

The growth of smart, autonomous and connected devices in our everyday lives is also punctuated by the vulnerability of these systems towards malicious attacks, capturing sensitive private data or sending fraudulent, unauthenticated information.

  YOLO: Real-Time Object Detection

You only look once (YOLO) is a state-of-the-art, real-time object detection system. On a Pascal Titan X it processes images at 30 FPS and has a mAP of 57.9% on COCO test-dev.

  CMSIS-NN Models and Scripts

Scripts to quantize trained Caffe models to 8-bits and convert them to binary format for the OpenMV camera. See ARM ML-examples

 

  OpenMV Camera Module

The OpenMV Cam is a small, low power, microcontroller board which allows you to easily implement applications using machine vision in the real-world.

  Ultra-low power, 3GPP Release-14 enabled NB-IoT SoC

MT2625 is an NB-IoT R14 enabled SoC that will enable ultra-low power and cost effective IoT devices for a wealth of applications ranging through home, civic, industrial or mobile use. It’s highly integrated design incorporates an NB-IoT modem DSP, antenna RF and base-band analogue front-end.

  LTE BG96 Cat.M1/NB1 & EGPRS Module

BG96 is a series of LTE Cat M1/Cat NB1/EGPRS module offering a maximum data rate of 300Kbps downlink and 375Kbps uplink.

Additional Info

To submit an application, please click on the APPLY button after logging into your user account.

Do remember to attach the application form in your submission.

Challenge

IOT INNOVATION CHALLENGE 2018

Organisation

Aztech

Proposal submissions are open from 1 Nov 2018 10:00AM to 18 Jan 2019 12:00AM