Search

Real-time high-accuracy optical flow estimation is crucial for various real-world applications. While recent learning-based optical flow methods have achieved high accuracy, they often come with significant computational costs. In this paper, we propose a highly efficient optical flow method that balances high accuracy with reduced computational demands. Building upon NeuFlow v1, we introduce new components including a much more light-weight backbone and a fast refinement module. Both these modules help in keeping the computational demands light while providing close to state of the art accuracy. Compares to other state of the art methods, our model achieves a 10x-70x speedup while maintaining comparable performance on both synthetic and real-world data. It is capable of running at over 20 FPS on 512x384 resolution images on a Jetson Orin Nano. The full training and evaluation code is available at https://github.com/neufieldrobotics/NeuFlow_v2.

The current methods of video-based 3D human pose estimation have achieved significant progress; however, they continue to confront the significant challenge of depth ambiguity. To address this limitation, this paper presents the spatio-temporal GraphFormer framework for 3D human pose estimation in video, which integrates body structure graph-based representations with spatio-temporal information. Specifically, we develop a spatio-temporal criss-cross graph (STG) attention mechanism. This approach is designed to learn the long-range dependencies in data across both time and space, integrating graph information directly into the respective attention layers. Furthermore, we introduce the dual-path modulated hop-wise regular GCN (MHR-GCN) module, which utilizes modulation to optimize parameter usage and employs spatio-temporal hop-wise skip connections to acquire higher-order information. Additionally, this module processes temporal and spatial dimensions independently to learn their respective features while avoiding mutual influence. Finally, we demonstrate that our method achieves state-of-the-art performance in 3D human pose estimation on the Human3.6M and MPI-INF-3DHP datasets.

Micro-pattern gas detectors (MPGD) find wide-ranging applications in particle physics experiments, industry, and medical services, owing to their large area, fine spatial resolution, and relatively low material content within the sensitive region. However, the demand for a large number of readout channels poses a bottleneck, limiting the application of MPGD to achieve higher accuracy and more extensive area. This requirement also presents significant challenges regarding system integration, power consumption, cooling, and cost. Previous studies have shown that, under sparse effective hits, a channel multiplexing method based on position encoded can address this issue. Nonetheless, improving the compression ratio and addressing the high event rate problem remain key challenges requiring further investigation. In this research, we have developed two types of high compression ratio multiplexing methods and their mathematical models. It is shown that a maximum of $n \times (n-1)/2 - (n - 2)/2 + 1$ detector channels can be read out with n electronics channels if n is even. Using these methods, several multiplexing boards were designed and implemented. Considering the real condition of the detectors, we achieved an multiplexing board with 64 readout electronics reading out 1024 detector channels, marking the highest compression ratio in current research. Moreover, these multiplexing circuits were utilized and verified in our cosmic-ray muon imaging facilities, demonstrating their advantage of reducing the required number of front-end electronics cards., Comment: This is the first submitted version to the IEEE-TNS

Muon imaging technology is an innovative imaging technique that can be applied in volcano imaging, heavy nuclear material detection, and archaeological research. The Micromegas detector is a promising choice for muon imaging due to its high spatial resolution and large area. However, the large number of readout channels poses a challenge for electronics. In this paper, a compact front-end electronics (FEE) for reading Micromegas detectors is presented. The electronics use a current-based readout chip, ADAS1128, which integrates 128 current amplifiers for multi-channel charge measurement. After noise and calibration tests, detector energy resolution tests were performed using 5.9 keV X-rays. The X-ray full energy peak and Ar escape peak can be observed; the energy resolution of the full energy peak is about 20.23%@5.9 keV. Additionally, a muon image system was set up to verify the imaging capacity of Micromegas detectors. Test results show that the spatial resolution of the system is better than 200 {\mu}m. The muon image system can reconstruct the boundaries for objects with a size of 2 cm.

Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based optical flow methods have achieved high accuracy, they often come with heavy computation costs. In this paper, we propose a highly efficient optical flow architecture, called NeuFlow, that addresses both high accuracy and computational cost concerns. The architecture follows a global-to-local scheme. Given the features of the input images extracted at different spatial resolutions, global matching is employed to estimate an initial optical flow on the 1/16 resolution, capturing large displacement, which is then refined on the 1/8 resolution with lightweight CNN layers for better accuracy. We evaluate our approach on Jetson Orin Nano and RTX 2080 to demonstrate efficiency improvements across different computing platforms. We achieve a notable 10x-80x speedup compared to several state-of-the-art methods, while maintaining comparable accuracy. Our approach achieves around 30 FPS on edge computing platforms, which represents a significant breakthrough in deploying complex computer vision tasks such as SLAM on small robots like drones. The full training and evaluation code is available at https://github.com/neufieldrobotics/NeuFlow.

3D human pose estimation and mesh recovery have attracted widespread research interest in many areas, such as computer vision, autonomous driving, and robotics. Deep learning on 3D human pose estimation and mesh recovery has recently thrived, with numerous methods proposed to address different problems in this area. In this paper, to stimulate future research, we present a comprehensive review of recent progress over the past five years in deep learning methods for this area by delving into over 200 references. To the best of our knowledge, this survey is arguably the first to comprehensively cover deep learning methods for 3D human pose estimation, including both single-person and multi-person approaches, as well as human mesh recovery, encompassing methods based on explicit models and implicit representations. We also present comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions. A regularly updated project page can be found at https://github.com/liuyangme/SOTA-3DHPE-HMR.

The growing diversity of digital face manipulation techniques has led to an urgent need for a universal and robust detection technology to mitigate the risks posed by malicious forgeries. We present a blended-based detection approach that has robust applicability to unseen datasets. It combines a method for generating synthetic training samples, i.e., reconstructed blended images, that incorporate potential deepfake generator artifacts and a detection model, a multi-scale feature reconstruction network, for capturing the generic boundary artifacts and noise distribution anomalies brought about by digital face manipulations. Experiments demonstrated that this approach results in better performance in both cross-manipulation detection and cross-dataset detection on unseen data.

Coordination engineering was employed to optimize the coordination environment of the Zr atom anchored on the porphyrins (PP). Five promising ZrPP-A candidates as electrocatalysts for nitrogen reduction reaction (NRR) were identified through a four-step screening strategy. First-principles calculations were utilized to evaluate the performance of the candidate electrocatalysts for NRR. A comprehensive search for reaction pathways revealed that NRR reactions with these selected catalysts tend to follow a hybrid pathway. It is found that orbital hybridization and charge transfer between Zr and its coordination atoms, as well as between ZrPP-A and the adsorbed N2 ensured the stability and high catalytic activity of these selected ZrPP-A. Zr plays a crucial role in coordinating charge transfer during the NRR process. Simultaneously, the coordinating atoms and the PP moiety jointly provide additional charge transfers to or from the adsorbate. An asymmetric coordination environment results in an asymmetric charge distribution of the substrate, causing the adsorbed polarized N2 molecule oriented toward the asymmetric charge aggregation region. Our work underscores the importance of considering not only the single-atom catalyst itself but also its coordination environment for the rational design of efficient catalysts.

Robustness in Simultaneous Localization and Mapping (SLAM) remains one of the key challenges for the real-world deployment of autonomous systems. SLAM research has seen significant progress in the last two and a half decades, yet many state-of-the-art (SOTA) algorithms still struggle to perform reliably in real-world environments. There is a general consensus in the research community that we need challenging real-world scenarios which bring out different failure modes in sensing modalities. In this paper, we present a novel multi-modal indoor SLAM dataset covering challenging common scenarios that a robot will encounter and should be robust to. Our data was collected with a mobile robotics platform across multiple floors at Northeastern University's ISEC building. Such a multi-floor sequence is typical of commercial office spaces characterized by symmetry across floors and, thus, is prone to perceptual aliasing due to similar floor layouts. The sensor suite comprises seven global shutter cameras, a high-grade MEMS inertial measurement unit (IMU), a ZED stereo camera, and a 128-channel high-resolution lidar. Along with the dataset, we benchmark several SLAM algorithms and highlight the problems faced during the runs, such as perceptual aliasing, visual degradation, and trajectory drift. The benchmarking results indicate that parts of the dataset work well with some algorithms, while other data sections are challenging for even the best SOTA algorithms. The dataset is available at https://github.com/neufieldrobotics/NUFR-M3F.

We report the calibration of a gaseous Time Projection Chamber based on Micromegas charge readout modules with cosmic ray muons, utilizing their penetrating power and relatively uniform energy deposition per unit length. Muon events were selected through track reconstruction to characterize detector performances, such as the drift velocity, electron lifetime, detector gain, and electric field distortion. The evolution of detector performances with gas purities and electric drift fields over a 50-day data-taking cycle was measured by the muon calibration method. For instance, the drift velocity degraded with gas impurities from ${3.40\pm 0.07 ~ cm/\mu s}$ to ${3.06\pm 0.06 ~ cm/\mu s}$, and then recovered with gas purification. A ${^{137}Cs}$ calibration source was also placed inside the detector as a reference for muon calibrations.

Polymer-sorted high-density carbon nanotube (CNT) arrays have shown great potential to extend the silicon-based Moore's law. Imaging the CNT arrays on insulators like SiO2/Si using low-voltage scanning electron microscopy (LVSEM) to acquire array information like the alignment, density, and distribution of residual polymers is necessary. Such a task remains challenging due to the nanoscale CNT body (1-2 nm in diameter), nanoscale tube-to-tube separation (1-10 nm), the broadening of the apparent diameter, and the complex image contrast caused by the insulating substrate and polymer residues. In this study, the imaging mechanism for this system is investigated. Two methods are developed to separate the three dominant contrasts, i.e. topographic contrast, charge contrast, and material contrast, by selecting the take-off angle and energy of the emitted electrons as enabled by changing the working distance or the deceleration voltage. The contrast formation and separation mechanism is further confirmed by the dynamic contrast evolution due to the electron-beam-induced deposition of amorphous carbon. The contrast separation method is further applied to an individual CNT, reducing its apparent diameter from 36 nm to 6 nm. This result hints at the potential for LVSEM to count the density exceeding 150 CNTs/um of CNT arrays. Finally, a comparative study of LVSEM and transmission electron microscopy confirms the failure of LVSEM to resolve CNTs in a bundle. The results suggest that the density of CNT arrays may be underestimated in reported SEM data. The proposed method can serve as a useful tool for further study and application of arrayed CNTs., Comment: 25 pages, 9 figures main text. 5 pages, 6 figures supplementary materials

Beam monitoring and evaluation are very important to boron neutron capture therapy (BNCT), and a variety of detectors have been developed for these applications. However, most of the detectors used in BNCT only have a small detection area, leading to the inconvenience of the full-scale 2-D measurement of the beam. Based on micromegas technology, we designed a neutron detector with large detection area and high counting rate. This detector has a detection area of 288 mm multiples 288 mm and can measure thermal, epithermal, and fast neutrons with different detector settings. The BNCT experiments demonstrated that this detector has a very good 2-D imaging performance for the thermal, epithermal, fast neutron and gamma components, a highest counting rate of 94 kHz/channel, and a good linearity response to the beam power. Additionally, the flux fraction of each component can be calculated based on the measurement results. The Am-Be neutron source experiment indicates that this detector has a spatial resolution of approximately 1.4 mm, meeting the requirements of applications in BNCT. It is evident that this micromegas-based neutron detector with a large area and high counting rate capability has great development prospects in BNCT beam monitoring and evaluation applications.