• What can Live Sense SDK do?

    Live Sense SDK, a multi platform solution powered by AI, enables apps and devices to detect real-time hazards and road signs to help drivers make informed decisions. It can detect objects, on the road, in the surrounding space, and in real-time using just the edge processing on the device that can plug into any type of vehicle, regardless of internet connectivity. A complete list of features can be found here.

  • Which regions are supported by Live Sense SDK?

    Live Sense core functionality of object detection and classification works for any road surface globally.

  • Can Live Sense recognize road signs from all over the world?

    The latest version recognizes the most common road signs today, including speed limits, stop signs and hazard signs. For a detailed list, refer to this developer guide. Our current SDK version most accurately identifies speed limit signs posted in regions where the signs are similar to signs in North America, Europe, Oceania, SEA and Brazil. Contact HERE support if you would like to have Live Sense increase its coverage.


  • Will the Live Sense drain my battery?

    Live Sense SDK uses the CPU, GPU and processor to run the AI models and to process the detections. We recommend to plug in your device if you plan to use it for longer periods.

  • Can it detect objects/signs in low light conditions or during rain?

    The performance of the SDK depends on how good the lighting condition is and how clear the sign is. The SDK does function in low light or at night provided the object or sign is illuminated well.


  • Invalid App ID or App Code

    1) Ensure that you have set License Key, App ID and App Code while authenticating your app.

    2) Ensure that you are using the correct App ID and App Code values that can be obtained from the developer portal in the project details.

  • License Expired

    Contact the access support if your license key has expired.

  • What should be the minimum confidence value for the models?

    The confidence is defined as the surety or accuracy with which a certain object / sign is recognized by a machine learning model. Low confidence value might lead to more false positives where the model recognizes incorrect objects. Very high confidence value means the model will recognize objects / signs very much identical to those used for its training and might ignore few similar kinds. We recommend to have a minimum confidence value of 0.6 (60%) for our models. A detailed list of each model and its recommended confidence value can be found in Models.

  • AI model does not detect any object

    1) Check the minimum confidence value. It should be set to a value between 0.6 and 0.9.

    2) Point your camera to the images given in Example App section based on which model is being tested.

    3) Try to run the camera in both landscape and portrait orientation.

Licensing and Terms

Please find our complete guide to licensing here.

results matching ""

    No results matching ""