Smart feature detection device for cloud based video recognition system
Takeshi Ikenaga, T. Suzuki · 2014
Potential of a cloud system combining a smart device and cloud servers is increasing. One of the representative examples is "Siri" which offers a friendly web knowledge navigator based on natural language user interface. Since latest portable devices equip not only a microphone but also a high resolution camera, this kind of cloud based framework is also promising to create various kinds of video based recognition systems. There are two essential components for it: a smart device with a high-resolution camera which is responsible for detecting feature from input video and cloud servers which execute recognition or data search using big data as shown in Fig. 1. This paper describes some key technologies of implementing a smart device for a cloud based recognition system. First, a low complexity SIFT (Scale-invariant feature transform) [1] based key point extraction algorithm and its hardware engine capable of operating at full-HD 60fps video [2] are described. As a technique to reduce network bandwidth, a keypoint of interest (KOI) detection algorithm based on spatio-temporal feature considering mutual dependency and camera motion [3] is also discussed. Finally, some promising application examples are shown.