Deep-learning-based object detection localizes trained object classes and identifies them with a surrounding rectangle (bounding box). Touching or partially overlapping objects are also separated, enabling object counting.
HALCON also gives users the option to have these rectangles aligned according to the orientation of the object, resulting in a more precise detection, as rectangles then match the shape of the object more closely.
For object detection, it’s necessary to provide labeled data in form of bounding box coordinates. The trained model is capable of detecting different object instances of different type including their locations on the image with a certain confidence. Per instance the model returns a bounding box and a corresponding predicted class.