Irida Labs’ software now available on Cadence Tensilica Vision DSPs

Measurements indicate at least ten times lower power consumption compared to a CPU implementation and five times lower power consumption compared to a GPU implementation.

Irida Labs’ IRIS-EnLight low-light video software enhances videos and images taken in challenging lighting conditions and slow shutter speeds. The software enhances the image and video contrast and intensity to restore the original colour content of the scene. It also features a scheme that reduces noise resulting from low-light perception of the image sensor.

In addition, IRIS-NoiseSweeper software has also been ported to the Tensilica Vision DSP to provide premium video quality and cleaner still-images. The software is targeted at image noise reduction for high-resolution still images. The technology features an automated noise profile estimation that reduces calibration needs and shortens development time. It operates in a single frame and eliminates any motion-blurring phenomena associated with multi-frame techniques.

The Tensilica family of imaging/vision DSPs was designed for the complex algorithms in imaging, video and computer vision applications including innovative multi-frame image capture, video pre- and post-processing, object and face recognition, low-light enhancement and many other complex tasks.

Vassilis Tsagaris, CEO, Irida Labs, commented: “Embedded vision and machine learning is becoming more and more popular in a number of different markets like mobile, automotive and surveillance. The wide adoption of embedded vision depends on the use of computationally complex algorithms in challenging low-power environments. Our partnership with Cadence enables us to deliver high-performance power-efficient computer vision solutions to the market, and is also very promising for our machine-learning -based visual perception solutions.”