A Method for Dynamic Selection of Optimal Depth Measurements Acquisition with Random Access Range Sensors

It is well established that acquiring large amount of range data with vision sensors can quickly lead to important data management challenges where processing capabilities become saturated and preempt full usage of the information available for autonomous systems to make educated decisions. While sub-sampling offers a naive solution for reducing dataset dimension after acquisition, it does not capitalize on the knowledge available in already acquired data to selectively and dynamically drive the acquisition process over the most significant regions in a scene, the latter being generally characterized by variations in depth and surface shape. This paper discusses the development of a formal improvement measure and a method to automatically establish which regions within the field of view of a range sensor would provide the most improvement to a model of the scene if further acquisitions were concentrated in priority over those regions. The proposed algorithm mainly targets applications using random access range sensors, defined as sensors that can acquire depth measurements at specified azimuth and elevation within their field of view. However, the framework is developed to be independent of the range sensing technology used, and is validated with range data acquired from the popular Kinect multi-modal imaging sensor, as well as Neptec,s LMS laser random access range sensor.