Skip to main content
overrideBackgroundColorOrImage= overrideTextColor= overrideTextAlignment= overrideCardHideSection= overrideCardHideByline= overrideCardHideDescription= overridebuttonBgColor= overrideButtonText= overrideTextAlignment=
data-content-type=""
Current Projects
Robotic Vision Lab's current research focus is on building artificial intelligence systems and embedded vision sensors to solve real-world engineering problems. Below are three ongoing research projects in the Robotic Vision Lab. Please visit Robotic Vision Lab website for more details.
overrideBackgroundColorOrImage= overrideTextColor= overrideTextAlignment= overrideCardHideSection= overrideCardHideByline= overrideCardHideDescription= overridebuttonBgColor= overrideButtonText= overrideTextAlignment=
Many functions in our daily life require identity verification. Traditional identity verification methods, including passwords, ID cards, or other physical devices, all have their apparent weaknesses or inconvenience. Biometric-based identity verification techniques are popular and more secure than traditional methods but cannot prevent passive verification or provide liveness assurance. We have developed a new identity verification technique, called Concurrent Two-Factor Identification Verification (C2F-IV). It analyzes spatial facial features and facial motions concurrently to verify identity. It requires only a short video of the frontal face expressing a unique user-produced facial motion. Provisional Patent Application Number: 63135136.
A golf swing requires full-body coordination and much practice to perform the complex motion precisely and consistently to make an effective swing. We are developing a unique motion analysis method to evaluate body motion. The primary goal is to evaluate how close the user’s body motion is to a reference or ideal motion. Using a deep neural network, we can analyze a golf swing video, determine if it was an effective or ineffective swing, and provide feedback about the specific body parts that need improvement. This evaluation result can be used as real-time feedback to help train the muscle memory to improve the performance and consistency. The same concept could be applied to other sports such as baseball and tennis or physical therapy. It could also be used as a tool to evaluate performance objectively for sports such as gymnastics and high diving.
AI Football Coach
Artificial Intelligence for Football Strategy Analysis
Annotation and analysis of sports videos is a challenging task that, once accomplished, could provide various benefits to coaches, players, and spectators. In particular, American Football could benefit from such a system to provide assistance in statistics and game strategy analysis. Manual analysis of recorded American football game videos is a tedious and inefficient process. We have developed an algorithm to automatically locate and label individual football players from a single overhead image of a football play immediately before the play begins. Our next steps include player tracking and strategy analysis.