Chinese scientists from Shanghai-based Fudan University and the Changchun Chinese Academy of Sciences have announced that they have created a 500-megapixel, cloud camera system.
According to information released by Fudan University, the camera can capture an extremely detailed image of a face in a stadium full of people and integrate with AI and cloud computing systems to identify that person in an instant. The camera also shoots video, so it can capture extremely high-resolution video images.
The new 500-megapixel camera developed by Fudan University and the Changchun Chinese Academy of Sciences
Zeng Xiaoyang, head of the research team behind the camera and a professor at Fudan University discussed the new camera and said: "It's a contradiction for traditional cameras to see clearly and widely.”
“When 20 million pixels are allocated to 10,000 people, each person has only 20 pixels, so it is impossible to see the human body clearly.”
Consumer cameras typically don’t go above 50 megapixels and the average for most cameras is in the 20 ~ 25 megapixel range. For consumers who believe that “bigger is better,” Hasselblad makes a consumer camera that shoots 400-megapixel photos. However, few consumers buy cameras in this range and megapixel count increases by manufacturers are slowing down as consumers realize that having more megapixels doesn’t mean better photos.
But according to Professor Zeng of Fudan University, the newly developed 500-megapixel, cloud camera system is different. Cameras that take photos with large megapixel counts stitch multiple images together to make a single photo, a process that takes time and processing power.
|Fudan University’s Professor Zeng Xiaoyang displays the new camera system|
Professor Zeng said, “When pixels reach the level of 500 million, especially when video images are needed, the camera system will become very large and a real-time video mosaic is basically impossible to achieve. Our cloud camera has a resolution of 500 million pixels, a hundred times that of 4K."
Related to video, the camera development team has shot video with the same ultra-high resolution, but in order to integrate the camera with AI and cloud computing systems, large amounts of data have to transfer between the systems, and as a result, wireless transmission produces a bottleneck,
Researchers at the Changchun Chinese Academy of Sciences said that the new camera isn’t just capturing images, but is being designed to recognize faces and the systems still needs to evolve so that the camera’s ability to recognize and track down targets in real time needs to be improved.
Researchers at both Fudan University and the Changchun Chinese Academy of Sciences acknowledged that the new camera system creates new risks to privacy risks and that the use of this kind of technology will need to be standardized through a legal framework.