Bosch Security and Safety Systems Czech Republic
Camera Trainer enabled by machine learning
Video Analytics

Cameras with built-in machine learning capabilities

Camera Trainer

The next step in video security

There is no ‘one size fits all’ when it comes to protecting people and property. That’s why we’ve taken the next step with Camera Trainer. The more a video security camera can know and learn, the more accurately and application-specifically it can perform.

Machine learning technology

Machine learning technology

Machine learning technology

We’ve taken the next step in video security with cameras that incorporate built-in machine learning capabilities. Camera Trainer enables you to tailor built-in Video Analytics to detect the things that matter most to you. The camera retains information on new user-defined objects and situations, or any subsequent changes. It then refers to these new learnings when processing scenes and can be combined with pre-determined alarm rules and object filters for even more accuracy and flexibility.

Machine learning technology
Customized applications

Customized applications

Customized applications

Camera Trainer substantially improves the level of security for people and property, but also opens up new customized applications and uses. For example, video cameras can be taught to recognize and detect stationary objects or certain situations instead of being triggered by motion alone. With this, video metadata is further enriched since Camera Trainer can deliver data when objects are present, but also once they have been removed, therefore providing more informative data. This can be translated into improved security or efficiencies, new business opportunities, or even new revenue streams. When a video security system can be taught, it supports you in meeting specific security and business intelligence requirements.

Customized applications
Camera Trainer use cases

Camera Trainer use cases

Camera Trainer use cases

Intelligent Video Analytics already offers the ability to detect objects, such as people, cars, bikes and trucks. With Camera Trainer it is possible to go beyond merely the detection of these pre-defined objects. For example, video cameras can be taught to recognize people with a shopping cart.

Another advantage of the new video analytics feature is that it is now feasible to reliably separate those vehicles clustered together in front of traffic lights, regardless of movement. Or how long a vehicle has been parked in a bay. If parking spots are either full or empty. With Camera Trainer, an object no longer needs to move to create a change in a situation, because the camera can be trained to also analyze stationary situations and compare them over different points in time.

Now, imagine the benefits of translating all of this insightful information into instant alerts and business intelligence. You could be optimizing your business processes or improving customer satisfaction, with maximum security awareness for your people and property.

Camera Trainer use cases
How to setup Camera Trainer

How to setup Camera Trainer

How to setup Camera Trainer

Camera Trainer is available on all Intelligent Video Analytics cameras with firmware version 7.10 or higher. There is a no-charge activation with license needed and setup must be done with Configuration Manager 6.20 or higher. (Download via Bosch Download Area) There is no additional integration effort needed and it’s fully supported by ONVIF.

Do an online training via the Bosch Security Academy and get to know how this technology works in more detail.

How-to videos are available on YouTube.

How to setup Camera Trainer

More information

Learn more about cameras with built-in machine learning capabilities

Camera Trainer technical note

Learn more about cameras with built-in machine learning capabilities