This work-in-progress paper will detail one of ENEE101’s newest modules, computer vision. ENEE101 is the introductory course to electrical and computer engineering (ECE) at the University of Maryland (UMD). This course provides first-year students with a glimpse into the broad field of ECE through high-level hands-on labs, with the goal of increasing student retention rates and boosting performance in sophomore-year courses; preliminary results have shown an upward trend in major retention and a downward trend in failures. Faculty-proposed modules cover a wide range of sub-disciplines in ECE, including optical communications, internet of things, and computer vision. Computer vision has become a popular topic in academia and industry due to its applications in machine learning, artificial intelligence, image recognition, self-driving cars, and more. Through our computer vision module for ENEE101, we seek to answer the following question: how can freshmen students, with almost no prior knowledge of even basic programming, actively learn and engage with computer vision? Our solution is to present students with three hands-on labs using the familiar Microsoft Kinect hardware along with open source computer vision software libraries. The labs we introduce cover depth sensing, hand tracking, facial recognition, and body detection. Each topic covers a single day of lab where the students are taught the basics of each concept and complete a C++ template with simple but elegant solutions, built and executed with Microsoft Visual Studio. The goal is to expose students to complex computer vision topics through easily understandable, real-life scenarios to help students realize the impactful applications of computer vision. By achieving this goal, we better prepare students for lives as scientists and engineers.
Are you a researcher? Would you like to cite this paper?
Visit the ASEE document repository at
for more tools and easy citations.