A Learning Package of Computer Vision in AI Topic using Edge-AI Device for STEM Education

This study proposes a computer vision learning kit for artificial intelligence (AI) using an edge-AI machine and Python programming language. The learning set consists of three parts: a wireless car, e-book, and 14 VDO clips. A wireless car frame is exquisitely crafted using a 3D printer with PLA plastic. It has one support wheel and two wheels. Each wheel is driven by an electronic driving board for DC motors. They are controlled by Python programming, which interfaced with a single-board computer (SBC), Raspberry Pi4, as an Edge-AI. To avoid obstacles, the vision process employs a real-time camera and infrared-light sensors. To run a wireless car in automatically advanced mode, the pre-trained models from a convolutional neural network (CNN) and computer vision algorithms are used. Furthermore, the learning book is divided into 14 chapters that correspond to 14 VDO clips. All clips are published online on YouTube channel for self-study. Several content examples include electronic sensors, Python programming, face recognition, and real-time object detection with deep learning. The benefits of the training set are compact size and ease to replicate and carry. The learning package has an overall rating of 4.38 out of 5, provided by six expert lecturers from the Department of Teacher Training in Electrical Engineering, King Mongkut’s University of Technology North Bangkok (KMUTNB). The training collection is also evaluated by 29 senior students. Finally, the findings show that the learning kit increased student enthusiasm and facilitated comprehension.