We present MosaicMVS, a novel learning-based depth estimation framework for a mosaic-based omnidirectional multi-view stereo (MVS) camera setup. It uses a regular field of view (FOV) MVS network for an omnidirectional imaging setup with explicit consideration of hypothetical voxel-wise FOV overlaps. The resulting depth predictions are accurate and agree on the omnidirectional multi-view geometry. Unlike existing MVS setups, MosaicMVS camera setup can be easily applied to omnidirectional indoor scenes without having to account for constraints such as intricate epipolar constraints and the distortion of omnidirectional cameras. We validate the effectiveness of our framework on a new challenging indoor dataset in terms of depth estimation, reconstruction, and view synthesis. We also present new evaluation metric to check reconstruction performance using post-processed masks for accurate evaluation without any ground truth depth map or laser-scanned reconstructions. Experimental results show that our framework outperforms the state-of-the-art MVS methods in a large margin in all test scenes.

In the field of video depth estimation, significant strides have been made with deep learning-based multi-view stereo approaches. However, existing studies struggle to produce consistently accurate depth maps that account for both multi-view geometry and temporal consistency from monocular video contents. To overcome this limitation, we introduce CMVDE, an innovative video depth estimation framework that leverages a multi-view geometric-temporal coupling approach in an end-to-end manner. Our proposed geometric consistency module efficiently generates multi-view geometric features by employing mutual cross-view epipolar attention between adjacent video frames. Additionally, it compresses these features using the novel multi-scale feature compressor, producing an effective input tensor for the subsequent module. Moreover, our framework enhances temporal consistency across consecutive video frames with the temporal consistency module based on convolutional LSTM 1 leveraging previous depth information as geometric guidance. Compared to state-of-the-art models, our approach achieves superior performance in depth quality and consecutive consistency on the ScanNet 2 and 7-Scenes 3 datasets, surpassing previous multi-view video depth estimation methods.

Security threats increase as connectivity among vehicles increases. In particular, a lack of authentication, integrity, and confidentiality makes the controller area network (CAN) protocol, which is used in critical domains such as vehicle body and powertrain, vulnerable to threats. In this paper, we propose methods for CAN security enhancement that use a support vector machine (SVM) and the autocorrelation of the received signal to detect a malicious node. Robustness to temperature variation is also considered because autocorrelation is affected by temperature variation. There are two methods based on the degree of uniformity of the temperature distribution. If the temperature is uniformly distributed over the vehicle and the temperature sensor is embedded in the secure node, the first scheme (temperature measurement system) trains data in each segmented temperature range more precisely using multiple classifiers. If not (i.e., a nonuniform temperature distribution or an absence of a temperature sensor), the alternative scheme (all-temperature training system) trains data in all temperature ranges with a single classifier. The performances of the proposed systems are evaluated on a testbed. The proposed method can operate without modifying the CAN protocol because it is based on the characteristics of the physical layer. In addition, security can be enhanced redundantly by the system running independently without authentication protocols.

The number of people with vision impairments using Conversational Agents (CAs) has increased because of the potential of this technology to support them. As many visually impaired people are accustomed to understanding fast speech, most screen readers or voice assistant systems offer speech rate settings. However, current CAs are designed to interact at a human-like speech rate without considering their accessibility. In this study, we tried to understand how people with vision impairments use CA at a fast speech rate. We conducted a 20-day in-home study that examined the CA use of 10 visually impaired people at default and fast speech rates. We investigated the difference in visually impaired people's CA use with different speech rates and their perception toward CA at each rate. Based on these findings, we suggest considerations for the future design of CA speech rate for those with visual impairments.

The number of households using stand-alone conversational agents is rapidly increasing. However, recent research revealed that in some of these households, use of agents decreases over time, and we know little about why. Therefore, we aim to understand how people utilize such devices in their daily lives and to explore the associated obstacles or difficulties. We conducted a long-term (12-week) user study in which we followed eight households, examining their use of Amazon Echo at home. From a series of diaries, surveys, and interviews with eight first-time users, we identified how their experiences changed over time and how conversational agents lose their presence at home. We found that voice interface, physical form, and at-home installation affect users' perceptions and expectations of smart speakers. Based on these findings, we discuss challenges and design opportunities for future at-home conversational agents.