We present the design of a courseware program created for a university outreach summer school, aimed at promoting STEM education among upper K-12 students. This course addresses a real-world challenge: learning to fly a radiocontrolled Unmanned Aerial Vehicle (UAV), which can be both difficult and costly due to the high likelihood of crashes during training. To mitigate this issue, the program focuses on developing a virtual reality (VR) environment that allows students to train as UAV pilots in a safe, crash-free setting, reducing risks and costs associated with real-world practice.

We present a courseware design and implementation for pre-engineering university summer school outreach program intended for 6thto 12thgrade pupils (K-12). The course focuses on building hardware and software for three IoT devices of increasing complexity and in doing so introduces various important computer science and engineering concepts. Device design constraints allow for very low cost of the built prototypes (5 - 10 € per device). We used NodeMCU with ESP8266 as a hardware platform. Lua as a part of NodeMCU firmware was used as a programming language due to simple syntax, possible interactive use, and compact source code that consisted of about 150 lines of code on average for each device. Pupils were provided with source code templates and encouraged to supplement the code with missing parts. The approach was scaled to primary and secondary schools’ curricula by organizing and evaluating a continuing education course for teachers in pre-university education.

Cartesian moments are frequently used global geometrical features in computer vision for object pose estimation and recognition. We derive a closed form expression for 3-D Cartesian moment of order p+q+r of a superellipsoid in its canonical coordinate system. We also show how 3-D Cartesian moment of a globally deformed superellipsoid in general position and orientation can be computed as a linear combination of 3-D Cartesian moments of the corresponding nondeformed superellipsoid in canonical coordinate system. Additionally, moments of objects that are compositions of superellipsoids can be computed as simple sums of moments of individual parts. To demonstrate practical application of the derived results we register pairs of range images based on moments of recovered compositions of superellipsoids. We use a standard technique to find centers of gravity and principal axes in pairs of range images while third-order moments are used to resolve the four-way ambiguity. Experimental results show expected improvement of recovered rigid transformation based on moments of recovered superellipsoids as compared to the registration based on moments of raw range image data. Besides object pose estimation the presented results can be directly used for object recognition with moments and/or moment invariants as object features.

We present an approach to reliable and efficient recovery of part-descriptions in terms of superquadric models from range data. We show that superquadrics can directly be recovered from unsegmented data, thus avoiding any presegmentation steps (e.g. in terms of surfaces). The approach is based on the recover-and-select paradigm. We present several experiments on real and synthetic range images, where we demonstrate the stability of the results with respect to viewpoint and noise.