ML+X Forum: Advancing Healthcare and Agriculture through Computer Vision

Join the ML+X community on Tuesday, April 9th, from 12-1 pm, to discuss and share insights surrounding computer vision methods applied to healthcare and agriculture. Register by April 7th (lunch provided) to guarantee your lunch ticket and join the discussion!

1. An ultrasound-based method to measure knee kinematics enabled by deep learning, Matthew Blomquist
   Ultrasound can improve the accuracy of measuring human motion by enabling direct visualization of the bones. However, prior studies using ultrasound to measure bone motion have required manual post-processing, which limits the ability to measure motion in real-time and/or in large groups of people. Thus, we set out to develop a deep learning network to take in ultrasound images and output the change in bone motion between sequential images. In this forum, we will discuss the different models that have been tested, the numerous obstacles that we have encountered, and the future goals/directions of our study.
2. Plant breeding in the age of computer vision, Will de la Bretonne
   For the past 10,000 years farmers have been faced with an elusive question: what seeds should be saved from this year's harvest to plant next year? In the past several hundred years this question has developed into the field of plant breeding where the goal is to use quantitative genetics to continuously improve crop varieties. At the core of plant breeding is the measurement of traits, some of which include yield, flowering time, biomass, and plant height. Currently, we manually collect all of these traits however with recent advances in drone technologies there is an opportunity to automate most of this work. We are interested in developing a computer vision system to automate the extraction of as many traits as possible from aerial imagery. We’ll discuss our current solution, pitfalls, and future goals of our study.
   
   

Finding the Orchard View room: The Orchard View room is located on the 3rd floor of Discovery Building — room 3280. To get to the third floor, take the elevator located next to the Aldo’s Cafe kitchen (see photo). If you cannot attend in-person, we invite you to stream the event via Zoom: https://uwmadison.zoom.us/j/92639425571?pwd=Z0tCaWZxK0dDcWs2dm51dXZpcy9mQT09 ( Passcode: 111195).

Join the ML+X google group: The ML+X community has a google group it uses to send reminders about its upcoming events. If you aren't already a member of the google group, you can use this link to join. Note that you have to be signed into a google account to join the group. If you have any trouble joining, please email faciltator@datascience.wisc.edu

Have an ML project or project proposal you want to share with the community? Presenting at ML+X is an excellent opportunity to get feedback on your methods and connect with other ML practitioners across Madison. If interested, please fill out this google form indicating which date(s) work for your schedule. If you have any questions about presenting, please email Chris Endemann (endemann@wisc.edu).