FAQ | SafetyRadar by VITech Lab

How do I get started with SafetyRadar?
Get the demonstration, try the software.You may choose to try the demo version of the solution right now. Or start from free consultation, where we will answer all your questions and demonstrate the software.
Talk to VITech Lab sales & tech team If the demo version looks good to start from, let's discuss how we may proceed to further cooperation. It means we will take into account all your requests and do our best to fit your objectives.
Run a pilot project The demo sounds good, but a real-life launch on your company's worksites is better. During the pilot project, you may try all the features, review the software performance, and make the final decision. Surely, during the PoC we also may choose individual customization and support services.
Get the full-pledged deploymentHere we scale the solution to all needed cameras and worksites and fine-tune the SafetyRadar to make it maximum comfortable for you and your safety team.

What are the deployment options?
Option 1: SaaS on AWS MarketplaceThis option provides the fastest start, as you just need to connect your cameras and start using the solution.
Option 2: CloudThis is also the way to start quickly and fits you if you need to take into consideration the specific security requirements, and use your private cloud. The solution is ready to use and is deployed in the public cloud to minimize IT infrastructure costs and to accelerate time to market. Subscription can be issued through AWS Marketplace or direct contract minimum for 1 year.
Option 3: On-premise (local)This variant fits you, if you want a solution to work locally, and you have the appropriate server hardware for the platform launch and performance. On-prem deployment is for organizations that have to comply with special security rules, or for those that need to operate offline most of the time.

What pricing plans are available?
Firstly, you pay for only what makes value for you. Thus you choose the features and components you need, and we make the individual calculations for you. As the result, you pay only for what works for your case! The final price is determined by:● the number of monitored PPE classes;● the number of cameras you want to perform the detection;● the deployment and connection option you choose.The installation payment is one-time.
No hidden fees are included! We provide transparent terms and billing as we want SafetyRadar to be financially efficient for you.
Request an individual calculation here!

Can I request additional features or any other customization?
Of course! Safety solution customization is one of the ways to enhance your competitive position, boost the HR brand, and provide better care for employees and visitors.
Here are some ideas of what can be customized:● the types of detected PPE items;● monitoring of PPE colors, form and configurations;● adding social distancing or temperature measurement;● adding facial recognition and access control.
Do you have any special request? We are at your service.Contact us and let's make it live!

Do you provide any technical support?
Yes, you may choose an individual support format the fits you best. The basic support and consultations are included. Ask our manager about it!
If you need more, reach out for Advanced Support Services, which include:● system monitoring;● collection of the additional dataset;● model retraining for enhancements once every 3 months;● hot and priority fixing bugs and system problems;● advanced training.
Please, contact us to learn more.

What are the basic technical requirements?
Technical requirements for an ML model server and web-interface server:For ML server:● Server with Docker and NVIDIA drivers installed● GPU: NVIDIA K80/P100/V100/A100/T4 or similar ● CPU: Intel Xeon min 2.0 GHz ● RAM: min 16 GB● Storage: min 100GB● EDGE platforms like NVIDIA EGX A100 or NVIDIA JetsonFor web-interface server:● Storage: min 1TB (SSD)● CPU: Intel Xeon min 1.3 GHz ● RAM: min 8 GB
Requirements for cameras and monitored objects:Please note, that VITech Lab does not provide the needed hardware, we use your existing cameras. If this is a kind of a barrier, we have partners who can provide you with cameras.● Resolution - from 2 MP● Video resolution - from 1920 × 1080 pixels● Video Format - H.264● Max FOV: 80 degrees● Color● The size of the analyzed object - a minimum 5% of the camera image size.
The ML model speed is up to 20 fps (V100-based server). It also depends on the cameras’ image resolution and the number of people on each image.
Another important thing about speed is that 1 server can work with 10 cameras in real-time, while one stream processing runs at a speed of 10 fps (V100-based server). The number of processed threads can be increased by reducing the processing speed.

How does the solution work on AWS Marketplace?
● The solution consists of two components:1. The ML model itself, which analyzes images from live stream from client’s surveillance cameras on the worksites;2. The Web interface, which transfers images from cameras to the ML model for analysis. The interface is user-friendly, so it serves as the main workplace environment for an end user. It provides an ability to:● control the cameras; ● observe the process of video stream analysis in real-time;● get and configure notifications about detected non-compliance cases: ● get access to all the detected violations, automatically saved to an archive;● manage users and accesses.The architecture on AWS Marketplace is depicted on the right.
The detailed instruction on how to deploy the model is here, on the AWS Blog.

How do you guarantee security for my data?
If you choose to deploy the solutions in the cloud, using your AWS Marketplace account, then be sure that AWS Marketplace itself meets high security level and has the appropriate certificates. In such case we do not have access to your data. For more details visit: https://aws.amazon.com/en/compliance/, https://aws.amazon.com/en/security/
If you choose an option where the solution is deployed locally, then all your data is kept locally, and we also do not have the access to it.
Moreover, we sign an NDA agreement, so as to secure all possible informational exchanges, data and terms of cooperation.

How do I get started with SafetyRadar?