HERE Launches AI-based Live Sense SDK

BW Online Bureau Oct 09, 2019

HERE Technologies has announced the availability of the HERE Live Sense SDK, a new software development kit (SDK), currently in beta, designed to give drivers real-time insight in order to be able to make informed decisions on upcoming obstacles, road infrastructure or driving conditions, without cloud processing or the need for connectivity.

Through the power of artificial intelligence (AI) and Machine Learning (ML), HERE Live Sense SDK turns devices with front-facing cameras, such as smartphones, dashcams or vehicle cameras, into highly intelligent vehicle sensors. By continuously scanning the driver’s environment, devices can then detect objects on the road, such as other vehicles, pedestrians or cyclists, road infrastructures such as traffic lights and road signs and potential hazards such as potholes, road closures or construction zones.

Based on what has been detected ahead, HERE Live Sense SDK provides information through both audio and visual notifications, which will help the driver make an informed decision of which action needs to be taken next. All of this happens in real-time on the device itself, without the need for data processing in the cloud or for connectivity. HERE Live Sense SDK also has the ability to detect changes in reality versus the onboard map to keep drivers informed of a change in speed limit, for example.

“ Today there are still millions of commercial and passenger cars on the roads without the necessary technology to keep drivers informed about potential hazards. The HERE Live Sense SDK will help to change that”, said Angel Mendez, Chief Operating Officer at HERE Technologies. “It detects objects, behavioral changes and road conditions that can lead to such situations and notifies drivers in time to take action.”

HERE Live Sense SDK uses multiple AI/ML detection models, including:

Road Basics: Detection and classification of objects on the road.
Road Alerts: Recognition and notification of braking vehicles, pedestrians and bicycle detection.
Road Hazards: Detection and classification of unexpected hazards along the way, with changing conditions, including road closures not yet detected on the map, construction zones and road works.
Road Signs: Detection and classification of speed limits and other signs.

As an SDK, these models can be implemented into an application or hardware device, providing customers with AI capabilities. It is now available in beta for Android and will soon be available for iOS.