While typical optical cameras can be blinded by bright light and unable to make out details in the dark, NTU’s development – called Celex – is said to record the slightest movements and objects in real time by monitoring changes in light intensity between scenes at nanosecond intervals. Integral circuitry allows the camera to do instant analysis of the captured scenes, highlighting important objects and details.
Assistant professor Chen Shoushun from NTU’s School of Electrical and Electronic Engineering, said: “Our camera can be a great safety tool for autonomous vehicles, since it can see very far ahead like optical cameras but without the time lag needed to analyse and process the video feed.
“With its continuous tracking feature and instant analysis of a scene, it complements existing optical and laser cameras and can help self-driving vehicles and drones avoid unexpected collisions.”
A typical camera sensor has several millions pixels, which are sensor sites that record light information and are used to form a resulting picture.
High-speed video cameras that record up to 120frame/s, which are processed so that self-driving vehicles can ‘see’ and analyse their environment.
In more complex environments, video processing is slower and this creates a lag between ‘seeing’ and the corresponding actions.
NTU’s camera records changes in the light intensity of individual pixels, reducing data output. Because it doesn’t have to capture the whole scene, processing speed is increased.
A built-in processor can analyse the flow of data to differentiate between the foreground objects and the background, allowing self-driving vehicles to react more quickly to oncoming vehicles or obstacles.
