Long-Distance Gesture Recognition using Dynamic Neural Networks
This addresses a practical problem for human-machine interaction in scenarios like controlling robots or drones from afar, though it is incremental as it builds on existing gesture recognition methods.
The paper tackles the problem of gesture recognition at long distances, where existing methods fail due to small gesture size in input data, and proposes a dynamic neural network that selects gesture-containing regions to improve focus and efficiency, achieving state-of-the-art performance on the LD-ConGR dataset in accuracy and compute efficiency.
Gestures form an important medium of communication between humans and machines. An overwhelming majority of existing gesture recognition methods are tailored to a scenario where humans and machines are located very close to each other. This short-distance assumption does not hold true for several types of interactions, for example gesture-based interactions with a floor cleaning robot or with a drone. Methods made for short-distance recognition are unable to perform well on long-distance recognition due to gestures occupying only a small portion of the input data. Their performance is especially worse in resource constrained settings where they are not able to effectively focus their limited compute on the gesturing subject. We propose a novel, accurate and efficient method for the recognition of gestures from longer distances. It uses a dynamic neural network to select features from gesture-containing spatial regions of the input sensor data for further processing. This helps the network focus on features important for gesture recognition while discarding background features early on, thus making it more compute efficient compared to other techniques. We demonstrate the performance of our method on the LD-ConGR long-distance dataset where it outperforms previous state-of-the-art methods on recognition accuracy and compute efficiency.