No abstract

Easy access to depth sensors has promoted exploring how point clouds can be leveraged to augment tabletops in the everyday context. However, point-cloud operations are computationally expensive and challenging to perform in real-time, particularly absent dedicated GPU-compute potential. In this paper, we propose mitigating the high computational costs by segmenting candidate-interaction regions near real-time. Focusing on CPU-based architectures, we put forward a modular pipeline that minimizes point-cloud volumes and proposes possible regions of interest for interactive tabletop implementations. While emphasizing a general solution adaptable for variable depth cameras, we also center on modular design for flexible pipeline filters. Our validation is two-fold. First, we employ a popular depth camera and apply the pipeline over a unique scene to establish initial performance measures. Second, we employ the XXXX dataset and report the pipeline’s performance over variable scenes from the dataset. For the unique scene, our initial findings indicate that point-cloud data volumes are reduced by up to 70\%, segmenting candidate-interaction regions under 35 ms. For the XXXX database, data volumes are reduced by an average of 70\%, and on average, candidate-interaction regions are segmented under 35 ms. Going one step further, we condense the approach into an open-source solution and conclude the paper by elaborating on the benefits of the segmenting candidate-interaction regions near real-time.

Multiple approaches have been put forward for augmenting interactive surface environments. However, spatial awareness while incorporating ubiquitous devices as active components in computing environments remains a foremost problem. Also, advances in deep learning algorithms and sensor technology over the last six years motivate furthering established approaches. We present Traceless, a projector-camera unit that enables communication between inanimate tabletop surfaces and personal mobile devices. Traceless uses a novel combination of spatial-density clustering and CNN-based object detection to augment tabletop surfaces with spatial awareness. It also employs Bluetooth to integrate personal mobile devices into augmented tabletop environments. In this paper, we describe the implementation of Traceless and demonstrate its potential for turning mobile devices into active components in a computing environment. We conclude with observations from a pilot study and discuss current limitations and potential future extensions. Our approach highlights the benefits of combining depth perception and deep learning algorithms, contributing a contemporary method with a broad range of applications.

In the research space of interactive surface environments, toolkits have a central role in rapid prototyping. They simplify operating both hardware and software technologies. However, the accelerated development of these technologies discontinues the usability of toolkits, in some cases making toolkits obsolete. One approach to address this challenge is establishing future-proof hardware and software interfaces based on the study of prevailing interactive surface environments. In this paper, we study interactive surface implementations and proposes a metamodeling infrastructure to support the analysis of prevailing implementations toward designing future-proof hardware and software modeling constructs. Our approach employs the unified modeling language and emphasizes the flexible description of existing systems. To evaluate the proposed approach, six existing research prototypes have been used to conduct traces, and the consistency demonstrated is promising. A face validation study with experts has also been conducted. Expert perceptions from the face validation study suggest potential benefit in using the UML-based approach as a shared notation for studying interactive surface environments.