Researchers at Fudan University have developed a 500MP cloud camera system which stitches multiple cameras into a single data stream delivering a resolution 5x higher than the human eye.
The camera was designed by Fudan University and Changchun Institute of Optics, Fine Mechanics and Physics of the Chinese Academy of Sciences and employs 2 specially developed chips to handle the processing load.
The ‘super camera’ features the usual video analytics for security, safety applications, including facial recognition and can be used for real-time monitoring or cloud computing technology for remote access from any authorised NIC-enabled device.
Images of the 500MP system show a housing with what looks to be an array made up of 4 rows of 9 cameras – 36 cameras in all. These are likely to have a 1080p resolution to ensure decent low light performance.
Arrays like this need to be carefully calibrated and installed in stable applications like a stadiums or fixed public areas under cover. Each camera lens in a multi-camera system needs to be individually focused to cover a portion of the area of view.
Challenges of systems like this include expense, the need for professional calibration and recalibration, managing bandwidth and implementing power supply. Management software is another hurdle.
The revelation of Fudan’s 500MP super camera has generated privacy fears in some quarters but locating 4K cameras in choke points is a far more effective and economical means of capturing faces in real time. Meanwhile almost every camera released today features analytics, with many supporting face recognition technology.
#sen.news
