Over the last years, three-dimensional (3-D) imaging has been applied to human action and gesture recognition, usually in the form of depth maps from RGB-D sensors. An alternative which has not been explored is 3-D integral imaging, aside from a recent preliminary study which shows that it can be an effective sensory modality with some advantages over the conventional monocular imaging. Since integral imaging has also been shown to be a powerful tool in other visual tasks (e.g., object reconstruction and recognition) under challenging conditions (e.g., low illumination, occlusions), and its passive long-range operation brings benefits over active close-range devices, a natural question is whether these advantages also hold for gesture recognition. Furthermore, occlusions are present in many real-world scenarios in gesture recognition, but it is an elusive problem which has scarcely been addressed. As far as we know, this letter analyzes for the first time the potential of integral imaging for gesture recognition under occlusions, by comparing it to monocular imaging and to RGB-D sensory data. Empirical results corroborates the benefits of 3-D integral imaging for gesture recognition, mainly under occlusions.

Non-verbal communication plays a particularly important role in a wide range of scenarios in Human-Robot Interaction (HRI). Accordingly, this work addresses the problem of human gesture recognition. In particular, we focus on head and eye gestures, and adopt an egocentric (first-person) perspective using eyewear cameras. We argue that this egocentric view may offer a number of conceptual and technical benefits over scene- or robot-centric perspectives. A motion-based recognition approach is proposed, which operates at two temporal granularities. Locally, frame-to-frame homographies are estimated with a convolutional neural network (CNN). The output of this CNN is input to a long short-term memory (LSTM) to capture longer-term temporal visual relationships, which are relevant to characterize gestures. Regarding the configuration of the network architecture, one particularly interesting finding is that using the output of aninternal layer of the homography CNN increases the recognition rate with respect to using the homography matrix itself. While this work focuses on action recognition, and no robot or user study has been conducted yet, the system has been designed to meet real-time constraints. The encouraging results suggest that the proposed egocentric perspective is viable, and this proofof-concept work provides novel and useful contributions to the exciting area of HRI.