Stereoscopic vision technology uses two synchronized cameras to generate a depth map. Depth map allows to detect any object and to get its accurate size, location and distance. Monocular vision object detection technology relies on deep neural networks (DNN) object recognition. Using DNN for object recognition will always encounter corner cases where there is an unknown object to the trained network. Our stereoscopic technology provides a hybrid detection solution of both classified and non classified objects.
Our unique solution allows camera modules, both visible-light and thermal infrared, to be placed independently apart supporting large baselines without being limited by stringent mechanical constraints or requiring manual calibration, enabling greater detection accuracy at long distances.
Our advanced stereoscopic vision technology supports large baselines that enable high accuracy at long ranges and don’t require stringent mechanical requirements. The flexible installation allows for quick and virtually unlimited placement options as long as there is some overlapping of the fields of view. Combined with our auto-calibration capabilities, we are able to compensate for deviations due to external factors, such as slight movement, vibrations or temperature changes.
Supporting large baselines enables high accuracy at long ranges
No stringent mechanical requirements
can be installed virtually anywhere on a vehicle if there are overlapping FOVs
Compensates for deviation of external factors, such as small vibrations or temperature changes
* Depends on selected optics and baseline