V-REP offers, next to proximity sensors, another type of sensors: vision sensors. Vision sensors, which are viewable objects, operate in a very similar way as camera objects: they will render the objects that are in their field of view and trigger detection if specified thresholds are over- or under-shot. Vision sensors, which can detect renderable entities, should be used over proximity sensors mainly when color, light or structure plays a role in the detection process (e.g. infrared sensors, or, more generally, sensors sensible to light (cameras, etc.)). However, depending on the graphic card the application is running on, or on the complexity of the scene objects, vision sensors might be a little bit slower than proximity sensors. Following illustrates applications using vision sensors:
[(1) industrial robot observed by 2 vision sensors, (2) Line tracer vehicle equipped with 3 vision sensors]
Make sure not to mix-up vision sensors with cameras. Following are the main differences:
The implemented vision sensor functionality uses a special feature of your graphic card called FBO (Frame Buffer Object). Vision sensors can only operate while a simulation is running; this means that a vision sensor's image content is only visible during simulation.
Vision sensors are added to the scene with [menu bar --> Add --> Vision sensor].