Canon launches software that reduces noise through deep learning technology to improve the quality of video captured by ultra-high-sensitivity cameras

Supports advanced surveillance by improving the visibility even in challenging environments such as long-range and night-time monitoring

MS-500 - part of the ultra-high-sensitivity camera series

Sydney, AUSTRALIA – 17 April 2024: Canon Australia today announces the launch of the “Video Enhancement Software Version 1.0¹” for the ultra-high-sensitivity camera series², which improves video visibility through noise reduction processing using deep learning technology.

In areas with extremely high security levels, such as seaports, public infrastructure facilities, and national borders, advanced surveillance systems help to accurately capture objects day and night. For night monitoring and long-range surveillance, the noise generated in the dark environments or haze affects the clarity of the video and increases the risk of missing abnormalities. Canon has been strengthening its lineup of ultra-high-sensitivity camera series that can cope capturing challenging environments, including the recently launched MS-500.

The new software makes it possible to enhance video captured by these cameras using noise reduction processing with deep learning technology. By improving visibility, it achieves higher quality video surveillance and contributes to quicker detection of abnormal situations. Canon continues to expand its advanced surveillance solutions in combination with the ultra-high-sensitivity camera series.

High-speed and precision noise reduction processing is enabled by proprietary deep learning image processing
The new software update applies Canon's unique deep learning image processing technology developed by the characteristics of Canon's image sensor and optical system. Additionally, it utilises Canon’s vast image database and knowledge of image processing acquired over the course of many years. It is possible to further reduce noise generated under low light environments which cannot be avoided by the camera alone. The software reduces computational load to speed up the processing while maintaining the accuracy of data.

The high-performance Video Enhancement Software has three video compensation functions:

Noise Reduction
In very dark scenes, situations with large contrast in bright and dark areas or scenes with haze, visibility of the subject can be impaired. For video images captured in such scenarios, the Video Enhancement Software performs processing to reduce noise and optimise contrast, and outputs clearer images that are easier to identify the subject.

Dark and Bright Area Compensation
The Dark and Bright Area Compensation process increases the luminance level range of the dark and bright areas to reduce blocked up shadows and blown highlights. For example, during long-range night surveillance of a building fire or during the daytime when vessels become backlit due to sunlight or reflected light from the sea surface.

Haze Compensation
This function reduces the effect of haze and corrects the contrast of the video so that subjects are easier to recognise.

Pricing and availability
The new Video Enhancement Software Version 1.0 is scheduled to be available to purchase from accredited Canon dealers from April 2024. A box PC equipped with a Graphics Processing Unit (GPU) is required to use the software.

¹ Software can be purchased from an accredited Canon dealer when available and requires a box PC equipped with a Graphics Processing Unit (GPU).

² ME20F-SH, ME20F-SHN & MS-500.