arXiv subjects

Ning Xiao

Publications and source records attributed to Ning Xiao.

3 recordsLinked to original sources

arXiv2021

Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction

Video anomaly detection is commonly used in many applications such as security surveillance and is very challenging.A majority of recent video anomaly detection approaches utilize deep reconstruction models, but their performance is often suboptimal because of insufficient reconstruction error differences between normal and abnormal video frames in practice. Meanwhile, frame prediction-based anomaly detection methods have shown promising performance. In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos. The proposed method is equipped with a multi-path ConvGRU-based frame prediction network that can better handle semantically informative objects and areas of different scales and capture spatial-temporal dependencies in normal videos. A noise tolerance loss is introduced during training to mitigate the interference caused by background noise. Extensive experiments have been conducted on the CUHK Avenue, ShanghaiTech Campus, and UCSD Pedestrian datasets, and the results show that our proposed method outperforms existing state-of-the-art approaches. Remarkably, our proposed method obtains the frame-level AUROC score of 88.3% on the CUHK Avenue dataset.

cs.CV↗

arXiv2018

From Communication to Sensing : Recognizing and Counting Repetitive Motions with Wireless Backscattering

Recently several ground-breaking RF-based motion recognition systems were proposed to detect and/or recognize macro/micro human movements. These systems often suffer from various interferences caused by multiple-users moving simultaneously, resulting in extremely low recognition accuracy. To tackle this challenge, we propose a novel system, called Motion-Fi, which marries battery free wireless backscattering and device-free sensing. Motion-Fi is an accurate, interference tolerable motion-recognition system, which counts repetitive motions without using scenario-dependent templates or profiles and enables multi-users performing certain motions simultaneously because of the relatively short transmission range of backscattered signals. Although the repetitive motions are fairly well detectable through the backscattering signals in theory, in reality they get blended into various other system noises during the motion. Moreover, irregular motion patterns among users will lead to expensive computation cost for motion recognition. We build a backscattering wireless platform to validate our design in various scenarios for over 6 months when different persons, distances and orientations are incorporated. In our experiments, the periodicity in motions could be recognized without any learning or training process, and the accuracy of counting such motions can be achieved within 5% count error. With little efforts in learning the patterns, our method could achieve 93.1% motion-recognition accuracy for a variety of motions. Moreover, by leveraging the periodicity of motions, the recognition accuracy could be further improved to nearly 100% with only 3 repetitions. Our experiments also show that the motions of multiple persons separating by around 2 meters cause little accuracy reduction in the counting process.

eess.SP↗

arXiv2018

COUSTIC: Combinatorial Double auction for Task Assignment in Device-to-Device Clouds

With the emerging technologies of Internet of Things (IOTs), the capabilities of mobile devices have increased tremendously. However, in the big data era, to complete tasks on one device is still challenging. As an emerging technology, crowdsourcing utilizing crowds of devices to facilitate large scale sensing tasks has gaining more and more research attention. Most of existing works either assume devices are willing to cooperate utilizing centralized mechanisms or design incentive algorithms using double auctions. Which is not practical to deal with the case when there is a lack of centralized controller for the former, and not suitable to the case when the seller device is also resource constrained for the later. In this paper, we propose a truthful incentive mechanism with combinatorial double auction for crowd sensing task assignment in device-to-device (D2D) clouds, where a single mobile device with intensive sensing task can hire a group of idle neighboring devices. With this new mechanism, time critical sensing tasks can be handled in time with a distributed nature. We prove that the proposed mechanism is truthful, individual rational, budget balance and computational efficient. Our simulation results demonstrate that combinatorial double auction mechanism gets a 26.3% and 15.8% gains in comparison to existing double auction scheme and the centralized maximum matching based algorithm respectively.

cs.NI↗