Sep 19, 2018 | By Thomas
Understanding of movement is fundamental for all living species, regardless of whether it's figuring out what angle to throw a ball at, or seeing the motion of predators and prey. But simple videos can't actually give us the full picture. As traditional videos and photos for studying motion are two-dimensional, they thus don't show us the underlying 3D structure of the person or subject of interest.
Image courtesy of MIT CSAIL
Now researchers at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Lab, Google Research, and the University of California Berkley, have come up with an artificially intelligent (AI) system to show how a human body moves.
The system, dubbed MoSculp, uses an algorithm that can take 2D videos and turn them into 3D printed "motion sculptures." It could enable a much more detailed study of motion for professional athletes, dancers, or anyone who wants to improve their physical skills.
"Imagine you have a video of Roger Federer serving a ball in a tennis match, and a video of yourself learning tennis," says PhD student Xiuming Zhang. "You could then build motion sculptures of both scenarios to compare them and more comprehensively study where you need to improve."
Image: Jason Dorfman/MIT CSAIL
Here’s how it works in practice: After a video’s loaded into the system, MoSculp overlays the detected keypoints on input frames and confirms them with a few randomly selected frames. (A built-in correction tool lets users make adjustments if necessary.) After correcting for “temporally inconsistent detections,” it generates the motion sculpture and loads it into a custom interface.
It is a multistep process and all MoSculp needs is a video sequence. Here’s how it works: After a video’s loaded into the system, MoSculp first automatically detects 2D key points on the subject's body, for example, the hip, knee, and ankle of a ballerina while she's doing a complex dance sequence. Then, it takes the best possible poses from those points to be turned into 3D "skeletons."
Image: Jason Dorfman/MIT CSAIL
After stitching these skeletons together, the system generates a motion sculpture that can be 3D printed, showing the smooth, continuous path of movement traced out by the subject. Users can navigate around the sculpture and customize their figures to focus on different body parts, assign different materials to distinguish among parts, and even customize lighting, and then print it using a 3D printer.
During trials, the researchers found that over 75 percent of subjects felt that MoSculp provided a more detailed visualization for studying motion than the standard photography techniques.
The system works best for larger movements, like throwing a ball or taking a sweeping leap during a dance sequence. It also works for situations that might obstruct or complicate movement, such as people wearing loose clothing or carrying objects.
Currently, MoSculp only uses single-subject videos, but the team hopes to expand to multiple people. In the future, they believe it could be used to study things like social disorders, interpersonal interactions, and team dynamics.
Lead author Xiuming Zhang with one of the team's "motion sculptures". Photo: Jason Dorfman/MIT CSAIL
“Dance and highly skilled athletic motions often seem like ‘moving sculptures’, but they only create fleeting and ephemeral shapes,” said Courtney Brigham, communications lead at Adobe. “This work shows how to take motions and turn them into real sculptures with objective visualizations of movement, providing a way for athletes to analyze their movements for training, requiring no more equipment than a mobile camera and some computing time.”
The team will present their paper (“MoSculp: Interactive Visualization of Shape and Time“) on the system next month at the User Interface Software and Technology (UIST) conference in Berlin, Germany.
Posted in 3D Printing Application
Maybe you also like:
- Two Plymouth students create 3D printed PINK prosthetic breasts to help cancer survivors
- ETH Zurich prints tough, lightweight structures using FDM 3D printers and liquid-crystal-polymers
- LLNL explores machine learning to prevent defects in metal 3D-printed parts in real time
- AMT launches PostPro3D automated surface smoothing machine for 3D printed parts
- Hailey Dawson, 8-year-old with 3D printed hand throws 1st pitch at all 30 MLB parks
- Johnson & Johnson acquires 3D printed spinal implant maker Emerging Implant Technologies
- LEGO and Stanley Black & Decker back Evolve Additive Solutions with $19M funding
- Lockheed Martin teams With Deakin University to exploit FORTIS Exoskeleton
- Awesome 3D printed Millennium Falcon took 10 days to complete
- WASP releases modular Crane WASP infinity 3D printer for construction
3Ders.org provides the latest news about 3D printing technology and 3D printers. We are now seven years old and have around 1.5 million unique visitors per month.
