The World’s First All On-Device, Deep Neural Net, and Realtime Video Recognition App

Assistive technologies such as Amazon Alexa, Apple Siri or Google Lens have revolutionized the way we interact with computers and truly assist us in our daily life. But, they are still not perfect since users data has to travel out from their smartphone to providers’ cloud and this increases the risk of getting hacked, scandalized or abused. All these systems work based on deep learning which is computationally heavy and requires GPU servers. Sensifai launched a real-time, deep-neural, end-to-end, on-device video recognizer using Huawei Kirin980 chipsets that elevates AI capabilities of Huawei flagship smartphones to a whole new level. It is the world’s first all on-device, deep-neural, and real-time video recognition system that recognizes or detects objects, scenes, and activities. Sensifai also instantly segments the present objects in the video stream or enhance the image or video in real-time. To achieve this success, Sensifai employs Huawei neural processing unit (NPU) on the Kirin 980 chipset which is the world's first 7nm process mobile phone SoC chipset and it enjoys a dual NPU design. Sensifai’s embedded video recognition system recognizes over 3000 different concepts including objects, scene, human actions, and different environmental attributes. The app works in real-time, processing 30 frames per second on a live video feed from the smartphone camera with a power consumption of less than 150mA. In the next generation of the Sensifai’s technology, the app will be able to recognize up to 10,000 different real-world concepts. Since the new technology is highly energy efficient, small and light as compared to their GPU-based counterparts, it can be a breakthrough enabling many industries to run real-time image, audio and video processing tasks in the device. For example, the automobile industry can use this technology in their driver assistant or self-driving cars, robots can interact with the surrounding environment and human in a natural way, drones can perform visual pattern recognition, and assistants such as Alexa or Siri can do the speech recognition right on the device instead of transmitting user data to the cloud. Sensifai’s on-device AI forms the future of assistive technologies and empowers many applications! Sensifai brings privacy to users while processing both audio and visual data. Feel the power of Sensifai for yourself. …download the Sensifai app on the Google app store! Get it on Google Play On-Device, Deep Neural Net