The purpose of gesture recognition is to recognize meaningful movements of human bodies, and gesture recognition is an important issue in computer vision. In this paper, we present a multimodal gesture recognition method based on 3D densely convolutional networks (3D-DenseNets) and improved temporal convolutional networks (TCNs). The key idea of our approach is to find a compact and effective representation of spatial and temporal features, which orderly and separately divide task of gesture video analysis into two parts: spatial analysis and temporal analysis. In spatial analysis, we adopt 3D-DenseNets to learn short-term spatio-temporal features effectively. Subsequently, in temporal analysis, we use TCNs to extract temporal features and employ improved Squeeze-and-Excitation Networks (SENets) to strengthen the representational power of temporal features from each TCNs' layers. The method has been evaluated on the VIVA and the NVIDIA Gesture Dynamic Hand Gesture Datasets. Our approach obtains very competitive performance on VIVA benchmarks with the classification accuracies of 91.54%, and achieve state-of-the art performance with 86.37% accuracy on NVIDIA benchmark.
The increasing demand for home fitness solutions underscores the need for interactive displays that enhance user experiences. This study introduces a technology that autonomously adjusts display height using the skeletal information of demonstrators from videos, catering to home fitness needs. A user study involving thirty participants compared fixed height, manual adjustment, and automatic adjustment conditions. Head flexion angles and NASA-TLX survey responses were used for evaluation. Results showed a significant reduction in head flexion angles with automatic adjustment, promoting proper spinal alignment. NASA-TLX responses indicated lower mental, effort, and frustration ratings, along with improved performance and perceived support in the automatic adjustment condition compared to other conditions. These findings confirm that motion-based height adjustment improves posture and enhances the overall interactive experience. This research demonstrates the feasibility of integrating responsive ergonomics into interactive displays and suggests the importance of further personalization, conducting diverse user studies, and refining algorithms to fully leverage the potential of this technology.
In order to reduce the power consumption of digital signal processing (DSP) in a coherent optical communication system, a low complexity equalization scheme in DSP flow of a 400 Gb/s DP-16QAM system has been proposed. This scheme is based on Fermat number transform (FNT), which sequentially performs static equalization (SE) and dynamic equalization (DE) in the transform domain. For different distances, the proposed scheme finds the optimal solution under the condition that transform length and data bit width are mutually restricted under different transmission distances while achieving low complexity and optimal performance. The experimental results show that the adopted transform-domain equalization (TrDE) scheme has much lower computational complexity than the traditional frequency-domain equalization (FDE) and time-domain equalization (TDE) nearly without any performance loss. In the 80, 160, and 240 km scenarios, the number of multiplier is reduced by more than 72%, and the advantage becomes more obvious as the transmission capacity increases.
Abstract Many works focus on multi‐spectral capture and analysis, but multi‐spectral display still remains a challenge. Most prior works on multi‐primary displays use ad‐hoc narrow band primaries that assure a larger color gamut, but cannot assure a good spectral reproduction. Content‐dependent spectral analysis is the only way to produce good spectral reproduction, but cannot be applied to general data sets. Wide primaries are better suited for assuring good spectral reproduction due to greater coverage of the spectral range, but have not been explored much. In this paper we explore the use of wide band primaries for accurate spectral reproduction for the first time and present the first content‐independent multi‐spectral display achieved using superimposed projections with modified wide band primaries. We present a content‐independent primary selection method that selects a small set of n primaries from a large set of m candidate primaries where m > n. Our primary selection method chooses primaries with complete coverage of the range of visible wavelength (for good spectral reproduction accuracy), low interdependency (to limit the primaries to a small number) and higher light throughput (for higher light efficiency). Once the primaries are selected, the input values of the different primary channels to generate a desired spectrum are computed using an optimization method that minimizes spectral mismatch while maximizing visual quality. We implement a real prototype of multi‐spectral display consisting of 9‐primaries using three modified conventional 3‐primary projectors, and compare it with a conventional display to demonstrate its superior performance. Experiments show our display is capable of providing large gamut assuring a good visual appearance while displaying any multi‐spectral images at a high spectral accuracy.
This paper introduces a new virtual tour method which integrates multiprojection techniques, remote cluster rendering and pattern tracking.We use geometric calibration and edge blending to create a seamless and consistent display and utilize remote render cluster to render high-resolution scene in real time through China Next Generation Internet (CNGI).By tracking the hand-held pattern, users can control the 6 degrees of freedom (6DOF) of virtual tour.We implement a virtual tour application referring to "Dunhuang Grottos".The successful demonstration means that we can provide a real-time convenient rendering service for virtual tour in remote museums. I.
This paper presents a fast continuous geometric calibration method for projector-camera system under ambient light. Our method estimates an appropriate exposure time to prevent features in captured image from degradation and adopts ORB descriptor to match features pairs in real-time. The adaptive exposure method has been verified with different exposure values and proved to be effective. We also implement our real-time continuous calibration method on Dual-projection display. The calibration process can be accomplished smoothly within 5 frames.
The orientation- and device-dependent received signal strength (RSS) diversity has become a challenge for improving performance of localization using low-cost Internet of Things (IoT) devices. The existing orientation-compensation methods are based on the principle of database matching; thus, they are susceptible to performance degradation if the testing node orientation does not exist in the training data. To alleviate this issue, the orientation-compensation model (OCM) is proposed to compensate for the orientation-dependent RSS diversity. In contrast to the existing orientation-compensation methods that involve only the device orientation, the proposed method presents the device and anchor (i.e., base station) deflection angles and uses these angles as variables for the OCM. The introduction of these angles can significantly reduce the requirement for device orientations in the training data. Furthermore, based on the characteristics of the OCM and differential RSS (DRSS), this paper proposes an OCM/DRSS integrated data-processing strategy. This strategy is demonstrated to be effective in enhancing localization in IoT applications that have multiple devices with three-dimensional orientation diversity.
Image/video coding has been a remarkable research area for both academia and industry for many years. Testing datasets, especially high-quality image/video datasets are desirable for the justified evaluation of coding-related research, practical applications, and standardization activities. We put forward a test dataset namely USTC-TD, which has been successfully adopted in the practical end-to-end image/video coding challenge of the IEEE International Conference on Visual Communications and Image Processing in 2022 and 2023. USTC-TD contains 40 images at 4K spatial resolution and 10 video sequences at 1080p spatial resolution, featuring various content due to the diverse environmental factors (scene type, texture, motion, view) and the designed imaging factors (illumination, shadow, lens). We quantitatively evaluate USTC-TD on different image/video features (spatial, temporal, color, lightness), and compare it with the previous image/video test datasets, which verifies the wider coverage and more diversity of the proposed dataset. We also evaluate both classic standardized and recent learned image/video coding schemes on USTC-TD with PSNR and MS-SSIM, and provide an extensive benchmark for the evaluated schemes. Based on the characteristics and specific design of the proposed test dataset, we analyze the benchmark performance and shed light on the future research and development of image/video coding. All the data are released online: https://esakak.github.io/USTC-TD.
The one-dimensional optimal system for the Lie symmetry group of the (2+1)-dimensional Wu—Zhang equation is constructed by the general and systematic approach. Based on the optimal system, the complete and inequivalent symmetry reduction systems are presented in the form of table. It is noteworthy that a new Painlevé integrable equation with constant coefficient is in the table besides the classic Boussinesq equation and the steady case of the Wu-Zhang equation.
Abstract Poly(glycerol-dodecanoate) (PGD) has aroused increasing attention in biomedical engineering for its degradability, shape memory and rubber-like mechanical properties, giving it potential to fabricate intelligent implants for soft tissues. Adjustable degradation is important for biodegradable implants and is affected by various factors. The mechanical load has been shown to play an important role in regulating polymer degradation in vivo. An in-depth investigation of PGD degradation under mechanical load is essential for adjusting its degradation behavior after implantation, further guiding to regulate degradation behavior of soft tissue implants made by PGD. In vitro degradation of PGD under different compressive and tensile load has proceeded in this study and describes the relationships by empirical equations. Based on the equations, a continuum damage model is designed to simulate surface erosion degradation of PGD under stress through finite element analysis, which provides a protocol for PGD implants with different geometric structures at varied mechanical conditions and provides solutions for predicting in vivo degradation processes, stress distribution during degradation and optimization of the loaded drug release.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
