arXiv subjects

Qian Zhou

Publications and source records attributed to Qian Zhou.

25 records · Page 2Linked to original sources

arXiv2024

A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism

Spiking Neural Networks (SNNs) are well-suited for processing event streams from Dynamic Visual Sensors (DVSs) due to their use of sparse spike-based coding and asynchronous event-driven computation. To extract features from DVS objects, SNNs commonly use event-driven convolution with fixed kernel parameters. These filters respond strongly to features in specific orientations while disregarding others, leading to incomplete feature extraction. To improve the current event-driven convolution feature extraction capability of SNNs, we propose a DVS object recognition model that utilizes a trainable event-driven convolution and a spiking attention mechanism. The trainable event-driven convolution is proposed in this paper to update its convolution kernel through gradient descent. This method can extract local features of the event stream more efficiently than traditional event-driven convolution. Furthermore, the spiking attention mechanism is used to extract global dependence features. The classification performances of our model are better than the baseline methods on two neuromorphic datasets including MNIST-DVS and the more complex CIFAR10-DVS. Moreover, our model showed good classification ability for short event streams. It was shown that our model can improve the performance of event-driven convolutional SNNs for DVS objects.

cs.CV↗

arXiv2023

360TripleView: 360-Degree Video View Management System Driven by Convergence Value of Viewing Preferences

360-degree video has become increasingly popular in content consumption. However, finding the viewing direction for important content within each frame poses a significant challenge. Existing approaches rely on either viewer input or algorithmic determination to select the viewing direction, but neither mode consistently outperforms the other in terms of content-importance. In this paper, we propose 360TripleView, the first view management system for 360-degree video that automatically infers and utilizes the better view mode for each frame, ultimately providing viewers with higher content-importance views. Through extensive experiments and a user study, we demonstrate that 360TripleView achieves over 90\% accuracy in inferring the better mode and significantly enhances content-importance compared to existing methods.

cs.MM↗

arXiv2023

Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI

Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications. Deep learning has demonstrated great potential for accelerating MRI by reconstructing images from undersampled data. However, most existing deep conventional neural networks (CNN) directly apply square convolution to k-space data without considering the inherent properties of k-space sampling, limiting k-space learning efficiency and image reconstruction quality. In this work, we propose an encoding enhanced (EN2) complex CNN for highly undersampled pulmonary MRI reconstruction. EN2 employs convolution along either the frequency or phase-encoding direction, resembling the mechanisms of k-space sampling, to maximize the utilization of the encoding correlation and integrity within a row or column of k-space. We also employ complex convolution to learn rich representations from the complex k-space data. In addition, we develop a feature-strengthened modularized unit to further boost the reconstruction performance. Experiments demonstrate that our approach can accurately reconstruct hyperpolarized 129Xe and 1H lung MRI from 6-fold undersampled k-space data and provide lung function measurements with minimal biases compared with fully-sampled image. These results demonstrate the effectiveness of the proposed algorithmic components and indicate that the proposed approach could be used for accelerated pulmonary MRI in research and clinical lung disease patient care.

eess.IV↗

arXiv2023

DeepStream: Bandwidth Efficient Multi-Camera Video Streaming for Deep Learning Analytics

Deep learning video analytic systems process live video feeds from multiple cameras with computer vision models deployed on edge or cloud. To optimize utility for these systems, which usually corresponds to query accuracy, efficient bandwidth management for the cameras competing for the fluctuating network resources is crucial. We propose DeepStream, a bandwidth efficient multi-camera video streaming system for deep learning video analytics. DeepStream addresses the challenge of limited and fluctuating bandwidth resources by offering several tailored solutions. We design a novel Regions of Interest detection (ROIDet) algorithm which can run in real time on resource constraint devices, such as Raspberry Pis, to remove spatial redundancy in video frames and reduce the amount of data to be transmitted. We also propose a content-aware bandwidth optimization framework and an Elastic Transmission Mechanism that exploits correlations among video contents. We implement DeepStream on Raspberry Pis and a desktop computer. Evaluations on real-world datasets show that DeepStream's ROIDet algorithm saves up to 54\% bandwidth with less than 1\% accuracy drop. Additionally,DeepStream improves utility by up to 23\% compared to baselines under the same bandwidth conditions.

cs.NI↗

arXiv2021

Photonically-confined solar cells: prospects for exceeding the Shockley-Queisser limit

The Shockley-Queisser (SQ) limit, introduced by W. Shockley and H. J. Queisser in 1961, is the most well-established fundamental efficiency limit for single-junction photovoltaic solar cells. For widely-studied semiconductors such as Si, GaAs and lead-halide perovskite, the SQ limits under standard solar illumination (1-sun) are 32.7%, 32.5% and 31% for bandgaps of 1.12 eV, 1.43 eV and 1.55 eV, respectively. Here, we propose that the fundamental efficiency limits for single-junction solar cells may be surpassed via photon confinement, substantially raising the theoretical limits to 49%, 45.2% and 42.1% for Si, GaAs and methylammonium lead iodide (MAPbI3) perovskite cells under 1-sun. Such enhancement is possible through the containment of luminescent photons within the solar cell, allowing the suppression of both non-radiative and radiative recombination losses, which were considered inevitable in the classical SQ model. Importantly, restricting photon emission from the solar cells raises the open-circuit voltage (VOC) to values approaching the semiconductor bandgaps, surpassing the theoretical VOC values predicted by the SQ model. The fill factors of the cells are expected to increase substantially, resulting in current-voltage characteristics with very-high squareness for ideal diode operation. Our work introduces a new framework for improving solar cell performance beyond the conventional limits.

physics.app-ph↗

arXiv2021

CrossRoI: Cross-camera Region of Interest Optimization for Efficient Real Time Video Analytics at Scale

Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale video feeds in real time is data intensive and poses severe challenges to network and computation systems today. We present CrossRoI, a resource-efficient system that enables real time video analytics at scale via harnessing the videos content associations and redundancy across a fleet of cameras. CrossRoI exploits the intrinsic physical correlations of cross-camera viewing fields to drastically reduce the communication and computation costs. CrossRoI removes the repentant appearances of same objects in multiple cameras without harming comprehensive coverage of the scene. CrossRoI operates in two phases - an offline phase to establish cross-camera correlations, and an efficient online phase for real time video inference. Experiments on real-world video feeds show that CrossRoI achieves 42% - 65% reduction for network overhead and 25% - 34% reduction for response delay in real time video analytics applications with more than 99% query accuracy, when compared to baseline methods. If integrated with SotA frame filtering systems, the performance gains of CrossRoI reach 50% - 80% (network overhead) and 33% - 61% (end-to-end delay).

cs.DC↗

arXiv2021

DeepRT: A Soft Real Time Scheduler for Computer Vision Applications on the Edge

The ubiquity of smartphone cameras and IoT cameras, together with the recent boom of deep learning and deep neural networks, proliferate various computer vision driven mobile and IoT applications deployed on the edge. This paper focuses on applications which make soft real time requests to perform inference on their data - they desire prompt responses within designated deadlines, but occasional deadline misses are acceptable. Supporting soft real time applications on a multi-tenant edge server is not easy, since the requests sharing the limited GPU computing resources of an edge server interfere with each other. In order to tackle this problem, we comprehensively evaluate how latency and throughput respond to different GPU execution plans. Based on this analysis, we propose a GPU scheduler, DeepRT, which provides latency guarantee to the requests while maintaining high overall system throughput. The key component of DeepRT, DisBatcher, batches data from different requests as much as possible while it is proven to provide latency guarantee for requests admitted by an Admission Control Module. DeepRT also includes an Adaptation Module which tackles overruns. Our evaluation results show that DeepRT outperforms state-of-the-art works in terms of the number of deadline misses and throughput.

cs.DC↗