Bosch video sensors with embedded neural network-based video analytics - developed specifically for ITS applications - will detect safety risks such as heavy traffic on a highway as well as congestion on an interchange. The camera will trigger alerts to partner devices for V2X communications – broadcasting safety messages to on-board units in connected vehicles. In addition to these demonstrations, the cameras can also alert on pedestrian presence, slow vehicles, stopped vehicles – and vehicles travelling the wrong way.
The built-in analytics detector uses technology based on neural network AI that attempts to mimic the human brain to learn from large amounts of data and recognise patterns to tackle complex tasks more accurately.
It improves detection capabilities in congested scenes for precise counting of overlapping vehicles at traffic lights or in traffic jams. But it will ignore disturbances caused by headlights, extreme weather, sun glare, vibration, and shake – delivering accurate detection for real-time use cases and statistical data reporting.
At the Bosch stand, video sensors will also classify objects in the traffic scene as motorcycles, cars, trucks, and buses, and feed the data, including vehicle counts by lane, class, direction, and speed into dashboards.
The Bosch ITS Data Service dashboards display the information in an easily consumable and actionable format for informed decision-making. The Data Service can also be accessed using an API for importing data into existing reporting solutions.