New algorithm enhances video shots in almost pitch-black environments

Nocturnal Vision, a Swedish startup, has a new algorithm that can be integrated into mobile phone cameras, allowing them to capture high-quality video in extremely low-light situations.

Inspired by the dung beetle that can see in the dark, the algorithm pools information from about seven frames before and after a shot to brighten, reduce noise and sharpen the video stream. It can work in real time as scenes are shot, or can be applied to video in post-processing. However, because it requires multiple frames, it won’t work with single-exposure still images.

Professor Eric Warrant from Lund University in Sweden has led the research. The work was derived from the field of bio-mimetics, or bio-inspiration. Bio-inspiration is about constructing technological solutions using nature as a model, that is, imitating solutions that nature has itself invented with the help of the laws of evolution. Research on nocturnally active insects, specifically the dung beetle, originally inspired the work.

Currently, the technology is not completely perfected. It uses so much processing power that even devices with a Snapdragon processor aren’t powerful enough to run it, and it also leaves those wanting to shoot quick still pictures out of luck.

Nocturnal Vision is working to perfect the chip and hopes to be able to integrate the algorithm into mobile phones and other night cameras within several years. Toyota is a partner and major investor in the technology.