Computer Vision Principles in Smart Buildings

To enable a smart monitoring ecosystem in a Smart Building environment, the first step would be to have the smart cameras enabled which typically come with embedded Edge based cameras to capture live stream of images/videos. Once an image gets captured it ideally needs to start a series of processes for detecting objects within the image and then further classify the image verifying their identities.

Object Detection is a complex process that involves Deep Learning customized consoles and libraries and today most commonly used platform happens to Tensorflow. Tensorflow easily integrates with cloud infrastructures and also supports Serverless topology (such as AWS Lambda). To simulate the data models and have them synced with IoT stream, integration API’s are usually developed on Python.

Once we are able to set up the data model using Tensorflow Libraries and have the engine integrated with the Smart Devices, we will now have to train the data models to ensure trusted and fair output results, from the continuous data influx stream from the Edge camera devices.

Training the Data Models is a continuous process that involves steps such as Verifying the API installation libraries, Downloading fresh stream of Live Images, creating xml files for each image, convert the xml’s into csv’s, run the python files, test against the data modeling libraries from TensorFlow, map the output against graphical interface and continue testing.

Typical Output looks like the following:

Once this is accomplished and we are able to detect various objects within an image file, the next step would then be to verify identities of the people among the objects detected. This is where we apply Image Classification metrics.

To append an identity to the image of a human detected, we would typically use Facial Recognition as a technology. For optimal results, we need to at least 100 images of each human object that gets detected and we can then look to create customized data structures for each and create a repository for real time comparison of images detected and then classified against the repository for optimizing output results. The image classification logic can be again written using Python.

As discussed, a combination of IoT/Edge mapped with AI layered with Object Detection and Image Classification can create a highly sophisticated Smart People Flow Monitoring system within a Smart Building premise.

The rise of Computer Vision, within Smart buildings ecosystems ensures automation and transformation, also leading to effective cost overheads reduction and enhanced Security thro’ DX adoption amalgamating benefits of IoT and AI.

Typical areas where Computer Vision tend to benefit in a Smart Building includes avenues of Smart People Flow Automation, Enhanced Security, Reduction of Manual Intervention, Preventive Alerts mechanism for crisis control etc.

Specifically, in the Usecase above we looked at garnering a front-end Computer Vision AI agent that can interact with IoT/ Edge based Smart Cameras, and can invoke process automation and people flow control backend logic, to provide real time alerts and monitoring in a Smart Building Ecosystem.

We looked at using Tensorflow Based CNN and DL libraries for layered AI Data Modeling, consuming and training the image data models to come up with customized outputs for specific object detection and classifying identity of the people using Facial Recognition APIs and libraries providing real time-based people flow monitoring.

Typical technology stacks involved with this included AI and ML libraries, Coding development on Python, Facial Recognition based frameworks managed seamlessly in real time.

Essentially the core benefits with our Computer Vision AI based service agent from a Smart Building perspective includes:
Improved Security
Personalized People Flow Identification
Real Time People Tracking and Monitoring
Round the Clock Availability & Attention
Prompt alerts on potential crisis scenarios for People Safety

Likewise, we will look to extend to other AI use cases using other industrial facets from a Smart City planning perspective, such as Smart Surveillance, Office Front Desk Automation, etc. leveraging the power of technologies such as Computer Vision, NLP, Robotic Process Automation and others.

    Leave a Reply

    Your email address will not be published. Required fields are marked*