Robohub.org
 

Dynamic target tracking camera system keeps its eye on the ball


by
18 June 2013



share this:
13-0049-r

This camera system can track very fast moving objects, keeping them in the center of the screen at all times. Currently under development by the Ishikawa Oku Lab. at the University of Tokyo, this latest version captures Full HD video and can be used outdoors.

“Ordinarily, to change the direction a camera faces, you move the camera mechanically. But in this system, it’s not the camera that moves, it’s the mirrors. This makes it possible to change where you’re looking really quickly. In this demonstration, we’re tracking a table tennis ball. The ball moves extremely fast, but this system can keep compensating for the ball’s motion, so the ball stays in the middle of the image.”

This device consists of two mirrors for pan and tilt, and a group of lenses. The Saccade mirrors can be controlled at high speed, on the order of milliseconds. The mirrors move independently, so this system doesn’t lose its high-speed response even if it’s connected to a large, heavy camera.

Also, by connecting a projector instead of a recording device, images can be projected onto a fast-moving object. This could also be used in AR applications, showing interactive content on moving objects.

“Using a rotating mirror is a common method, but usually, the mirror is in front of the camera, so a very large mirror is needed. But a feature of this system is, it can even capture wide-angle images with a small mirror. That’s because the system contains special optics called a pupil shift system.”

“Another important point is, this system does very fast image processing to recognize the subject. It captures and processes an image every 1/1000th of a second. In this way, it can track the subject stably and continuously, simply by feeding back the subject’s position, without particularly predicting its behavior.”

“For example, this system can record, in great detail, the instant a player hits a home run, including how the bat bends and the ball reacts, and the ball’s subsequent path. Or in soccer, it can record things like penalty kicks in amazing detail. We think this will make it possible to shoot sports in a really compelling way.”

“Right now, we’re actually taking this outdoors to where sports are played, to check how accurately it works. We hope it will be usable for actual broadcasting in about two years.”



tags: ,


DigInfo TV is a Tokyo-based online video news platform dedicated to producing original coverage of cutting edge technology, research and products from Japan.
DigInfo TV is a Tokyo-based online video news platform dedicated to producing original coverage of cutting edge technology, research and products from Japan.





Related posts :



Robot see, robot do: System learns after watching how-tos

  14 May 2025
Researchers have developed a new robotic framework that allows robots to learn tasks by watching a how-to video

AI-powered robots help tackle Europe’s growing e-waste problem

  12 May 2025
EU-funded researchers have developed adaptable robots that could transform the way we recycle electronic waste, benefiting both the environment and the economy.

Robot Talk Episode 120 – Evolving robots to explore other planets, with Emma Hart

  09 May 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Emma Hart from Edinburgh Napier University about algorithms that 'evolve' better robot designs and control systems.

Robot Talk Episode 119 – Robotics for small manufacturers, with Will Kinghorn

  02 May 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Will Kinghorn from Made Smarter about how to increase adoption of new tech by small manufacturers.

Multi-agent path finding in continuous environments

  01 May 2025
How can a group of agents minimise their journey length whilst avoiding collisions?

Interview with Yuki Mitsufuji: Improving AI image generation

  29 Apr 2025
Find out about two pieces of research tackling different aspects of image generation.

Robot Talk Episode 118 – Soft robotics and electronic skin, with Miranda Lowther

  25 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Miranda Lowther from the University of Bristol about soft, sensitive electronic skin for prosthetic limbs.

Interview with Amina Mević: Machine learning applied to semiconductor manufacturing

  17 Apr 2025
Find out how Amina is using machine learning to develop an explainable multi-output virtual metrology system.



 

Robohub is supported by:




Would you like to learn how to tell impactful stories about your robot or AI system?


scicomm
training the next generation of science communicators in robotics & AI


©2025.05 - Association for the Understanding of Artificial Intelligence


 












©2025.05 - Association for the Understanding of Artificial Intelligence