This paper presents DriveTrack, a new benchmark and data generation framework for long-range keypoint tracking in real-world videos. DriveTrack is motivated by the observation that the accuracy of state-of-the-art trackers depends strongly on visual attributes around the selected keypoints, such as texture and lighting. The problem is that these artifacts are especially pronounced in real-world videos, but these trackers are unable to train on such scenes due to a dearth of annotations. DriveTrack bridges this gap by building a framework to auto- matically annotate point tracks on autonomous driving datasets. We release a dataset consisting of 1 billion point tracks across 24 hours of video, which is seven orders of magnitude greater than prior real-world benchmarks and on par with the scale of synthetic benchmarks. DriveTrack unlocks new use cases for point tracking in real-world videos. First, we show that fine- tuning keypoint trackers on DriveTrack improves accuracy on real-world scenes by up to 7%. Second, we analyze the sensitiv- ity of trackers to visual artifacts in real scenes and motivate the idea of running assistive keypoint selectors alongside trackers.

This paper argues that network and application delivery infrastructures have become highly centralized and are more vulnerable to attacks and disasters than is desirable. It proposes a research agenda for decentralized fallback networks and focuses on a key component---a city-scale decentralized network using existing Wi-Fi access points, which are deployed across almost all buildings in cities. It proposes a routing system that uses information about buildings from geospatial maps instead of traditional routing mechanisms to scale well to millions of Wi-Fi nodes.

This paper introduces ChirpTransformer, a versatile LoRa encoding framework that harnesses broad chirp features to dynamically modulate data, enhancing network coverage, throughput, and energy efficiency. Unlike the standard LoRa encoder that offers only single configurable chirp feature, our framework introduces four distinct chirp features, expanding the spectrum of methods available for data modulation. To implement these features on commercial off-the-shelf (COTS) LoRa nodes, we utilize a combination of a software design and a hardware interrupt. ChirpTransformer serves as the foundation for optimizing encoding and decoding in three specific case studies: weak signal decoding for extended network coverage, concurrent transmission for heightened network throughput, and data rate adaptation for improved network energy efficiency. Each case study involves the development of an end-to-end system to comprehensively evaluate its performance. The evaluation results demonstrate remarkable enhancements compared to the standard LoRa. Specifically, ChirpTransformer achieves a 2.38 × increase in network coverage, a 3.14 × boost in network throughput, and a 3.93 × of battery lifetime.

Data center network operators often need accurate estimates of aggregate network performance. Unfortunately, existing methods for estimating aggregate network statistics are either inaccurate or too slow to be practical at the data center scale.

Passive human tracking using Wi-Fi has been researched broadly in the past decade. Besides straightforward anchor point localization, velocity is another vital sign adopted by the existing approaches to infer user trajectory. However, state-of-the-art Wi-Fi velocity estimation relies on Doppler-Frequency-Shift (DFS), which suffers from the inevitable signal noise incurring unbounded velocity errors, further degrading the tracking accuracy. In this article, we present WiVelo, which explores new spatial-temporal signal correlation features observed from different antennas to achieve accurate velocity estimation. First, we use subcarrier shift distribution (SSD) extracted from channel state information (CSI) to define two correlation features for direction and speed estimation, separately. Then, we design a mesh model calculated by the antennas’ locations to enable a fine-grained velocity estimation with bounded direction error. Finally, with the continuously estimated velocity, we develop an end-to-end trajectory recovery algorithm to mitigate velocity outliers with the property of walking velocity continuity. We implement WiVelo on commodity Wi-Fi hardware and extensively evaluate its tracking accuracy in various environments. The experimental results show our median and 90-percentile tracking errors are 0.47 m and 1.06 m, which are half and a quarter of state-of-the-art. The datasets and source codes are published through Github ( https://github.com/research-source/code ).

LoRa and its enabled LoRa wide-area network (LoRaWAN) have been seen as an important part of the next-generation network for massive Internet-of-Things (IoT). Due to LoRa's low-power and long-range nature, LoRa signals are much weaker than the noise floor, particularly in complex urban or semi-indoor environments. Therefore, weak signal decoding is critical to achieve the desired wide-area coverage in general. Existing work has shown the advantages of exploring deep neural networks (DNN) for weak signal decoding. However, the existing single-gateway based DNN decoder is hard to fully leverage the spatial information in multi-gateway scenarios. In this paper, we propose SRLoRa, an efficient DNN LoRa decoder that fully utilizes the spatial information from multiple gateways to decode extremely weak LoRa signals. Specifically, we design interleaving denoising and merging layers to improve signal quality at ultra-low SNR. We develop efficient merging on feature maps extracted by denoising DNNs to tolerate time misalignments among different signals. We define max and min operations in the merging layer to efficiently extract salient features and reduce noise, merging the features extracted from multiple gateways to guide future DNN layers to gradually improve signal quality. We implement SRLoRa with USPR N210 and commercial LoRa nodes and evaluate its performance indoors and outdoors. The results show that with four gateways, SRLoRa achieves SNR gain at 4.53--4.82 dB, which is 2.51× of Charm, leading to a 1.84× coverage area compared to standard LoRa in an urban deployment.

In this paper, we propose NEC (Neural Enhanced Cancellation), a defense mechanism, which prevents unautho-rized microphones from capturing a target speaker’s voice. Compared with the existing scrambling-based audio cancellation approaches, NEC can selectively remove a target speaker’s voice from a mixed speech without causing interference to others. Specifically, for a target speaker, we design a Deep Neural Network (DNN) model to extract high-level speaker-specific but utterance-independent vocal features from his/her reference audios. When the microphone is recording, the DNN generates a shadow sound to cancel the target voice in real-time. Moreover, we modulate the audible shadow sound onto an ultrasound frequency, making it inaudible for humans. By leveraging the non-linearity of the microphone circuit, the microphone can accurately decode the shadow sound for target voice cancellation. We implement and evaluate NEC comprehensively with 8 smartphone microphones in different settings. The results show that NEC effectively mutes the target speaker at a microphone without interfering with other users’ normal conversations.

Internet-of-Things (IoT) aims to connect billions of low-date rate and energy-constrained end-devices in the near future. Although many IoT systems have been commercialized, most of them focus on home and body scale applications. To establish a low-cost IoT at the city scale, LoRa Wide Area Networks (LoRaWAN) have become attractive in recent years due to their desirable kilometer or even longer communication distance with low energy consumption. However, due to the expensive cost of densely deploying end-nodes, the understanding of LoRa link behavior is still coarse-grained, and hard to fully realize the link dynamics, networking coverage, and localization accuracy of LoRaWAN in an urban environment. This paper shows a fine-grained LoRa link-level measurement via mobile end-nodes. We deploy two gateways and six mobile end-nodes and collect data packets over four months at a$6\times 6\ km^{2}$urban area. The evaluation mainly focuses on answering three questions: 1) Does a LoRa link stably perform in both spatial and temporal dimensions? 2) How large area can be covered for reliable communication by each gateway in the urban environment? 3) What accuracy can be achieved to localize an end-node through LoRa links? According to our measurement, our key findings are 1) The spatial and temporal behavior of LoRa links is quite dynamic due to the different types of land covers and the frequent micro-environment changes in the urban areas; 2) Each gateway can cover about 11.3 km2area and marginal SNR gains (e.g., 2 dB) of LoRa links are efficient enough to enlarge 32.6% coverage area of a gateway; and 3). The median localization error is about 400 m. Without densely deployed LoRa gateways, the SOTA LoRa localization can support road-level localization, even when an end node is close to one of the gateways.

Long Range Wide Area Network (LoRaWAN), using the linear chirp for data modulation, is known for its low-power and long-distance communication to connect massive Internet-of-Things devices at a low cost. However, LoRaWAN throughput is far behind the demand for the dense and large-scale IoT deployments, due to the frequent collisions with the by-default random channel access (i.e., ALOHA). Recently, some works enable an effective LoRa carrier-sense for collision avoidance. However, the continuous back-off makes the network throughput easily saturated and degrades the energy efficiency at LoRa end nodes. In this paper, we propose CurveALOHA, a brand-new media access control scheme to enhance the throughput of random channel access by embracing non-linear chirps enabled quasi-orthogonal logical channels. First, we empirically show that non-linear chirps can achieve similar noise tolerance ability as the linear one does. Then, we observe that multiple nonlinear chirps can create new logical channels which are quasi-orthogonal with the linear one and each other. Finally, given a set of non-linear chirps, we design two random chirp selection methods to guarantee an end node can access a channel with less collision probability. We implement CurveALOHA with the software-defined radios and conduct extensive experiments in both indoor and outdoor environments. The results show that CurveALOHA’s network throughput is 59.6% higher than the state-of-the-art carrier-sense MAC.

Federated learning (FL) is an emerging distributed machine learning (ML) paradigm with enhanced privacy, aiming to achieve a "good" ML model for as many as participants while consuming as little as wall clock time. By executing across thousands or even millions of clients, FL demonstrates heterogeneous statistical characteristics and system divergence widely across participants, making its training suffer when adopting the traditional ML paradigm. The root cause of the training efficiency degradation is the random client selection criteria. Although existing FL paradigms propose several optimization schemes for client selection, they are still coarse-grained due to their under-exploitation on the clients' data and system heterogeneity, yielding sub-optimal performance for a variety of FL applications. In this paper, we propose PyramidFL1 to speed up the FL training while achieving a higher final model performance (i.e., time-to-accuracy). The core of PyramidFL is a fine-grained client selection, in which PyramidFL does not only focus on the divergence of those selected participants and non-selected ones for client selection but also fully exploits the data and system heterogeneity within selected clients to profile their utility more efficiently. Specifically, PyramidFL first determines the utility-based client selection from the global (i.e., server) view and then optimizes its utility profiling locally (i.e., client) for further client selection. In this way, we can prioritize the use of those clients with higher statistical and system utility consistently. In comparison with the state-of-the-art (i.e., Oort), our evaluation on the open-source FL benchmark shows that PyramidFL improves the final model accuracy by 3.68% -- 7.33%, with a speedup of 2.71 x -- 13.66X on the wall clock time consumption.

Passive human tracking via Wi-Fi has been re-searched broadly in the past decade. Besides straight-forward anchor point localization, velocity is another vital sign adopted by the existing approaches to infer user trajectory. However, state-of-the-art Wi-Fi velocity estimation relies on Doppler-Frequency-Shift (DFS) which suffers from the inevitable signal noise incurring unbounded velocity errors, further degrading the tracking accuracy. In this paper, we present WiVelo11Code&datasets are available at https://github.com/liecn/WiVelo_SECON22 that explores new spatial-temporal signal correlation features observed from different antennas to achieve accurate velocity estimation. First, we use sub carrier shift distribution (SSD) extracted from channel state information (CSI) to define two correlation features for direction and speed estimation, separately. Then, we design a mesh model calculated by the antennas' locations to enable a fine-grained velocity estimation with bounded direction error. Finally, with the continuously estimated velocity, we develop an end-to-end trajectory recovery algorithm to mitigate velocity outliers with the property of walking velocity continuity. We implement WiVelo on commodity Wi-Fi hardware and extensively evaluate its tracking accuracy in various environments. The experimental results show our median and 90% tracking errors are 0.47 m and 1.06 m, which are half and a quarter of state-of-the-arts.

Cross-view vehicle Reidentification (ReID) has attracted widespread attention as an increasingly important vision task in intelligent transportation and urban surveillance. Benefiting from Convolutional Neural Network (CNN), recent studies have promoted the development of vehicle ReID by extracting discriminative local features. However, two fundamental challenges of small interclass discrepancy caused by different views and large intraclass distance caused by similar appearance still hinder the performance of cross-view vehicle ReID. In this paper, a novel View-aware Sphere Learning Network (VSLN) is proposed to alleviate the above issues while maintaining the merits of CNN-based approaches to generate view-aware sphere-based features. First, a Sphere Feature Embedding Network (SFEN) is proposed to constrain the images into hypersphere for extracting sphere features. On the other hand, this study presents a sphere similarity triple loss to help SFEN concentrate more on robust and discriminative vehicle parts. Second, since the vehicle images are usually captured from different viewpoints, this study further extends SFEN by introducing a Vehicle Viewpoint Predictor (VVP) combined with global attention mechanism to enlarge the discrepancy of interclass and shorten the distance of intraclass. Moreover, a city-scale data set, named Vehicle from Different Viewpoints, containing image-level viewpoint labels, is collected for training VVP. As a result, the proposed VLSN can achieve 96.31% Top-1 accuracy and 79.46% Top-1 accuracy on VeRi-776 and VRIC data sets, respectively. Overall, extensive experimental results on two benchmark data sets show that the proposed VSLN outperforms state-of-the-art methods.

User identified gesture recognition is a fundamental step towards ubiquitous WiFi based sensing. We propose WiHF, which first simultaneously enables cross-domain gesture recognition and user identification using commodity WiFi in a real-time manner. The basic idea of WiHF is to derive a domain-independent motion change pattern of arm gestures from WiFi signals, rendering the unique gesture characteristics and the personalized user performing styles. To extract the motion change pattern in real time, we develop an efficient method based on the seam carving algorithm. Moreover, taking as input the motion change pattern, a deep neural network (DNN) is adopted for both gesture recognition and user identification tasks. In DNN, we apply splitting and splicing schemes to optimize collaborative learning for dual tasks. We implement WiHF and extensively evaluate its performance on a public dataset including 6 users and 6 gestures performed across 5 locations and 5 orientations in 3 environments. Experimental results show that WiHF achieves 97.65 and 96.74 percent for in-domain gesture recognition and user identification accuracy, respectively. The cross-domain gesture recognition accuracy is comparable with the state-of-the-art method, but the processing time is reduced by 30×.

The screens of our smartphones and laptops display our private information persistently. The term “shoulder surfing” refers to the behavior of unauthorized people peeking at our screens, easily causing severe privacy leakages. Many countermeasures have been used to prevent naked eye-based peeking by reducing the possible peeking distance. However, the risk from modern smartphones with powerful cameras is underestimated. In this paper, we propose SRPeek, a long-distance shoulder surfing attack method using smartphones. Our key observation is that although a single image captured by smartphone cameras is blurred, the attacker can leverage super-resolution (SR) techniques to recover the information from multiple blurry images. We design an end-to-end system deployed on commercial smartphones, including an innovative deep neural network (DNN) architecture, StARe, for efficient multi-image SR. We implement SRPeek in Android and conduct extensive experiments to evaluate its performance. The results demonstrate we can recognize 90% of characters at a distance of 6m with telephoto lenses and 1.8m with common lenses, calling for the vigilance of the Quietly growing shoulder surfing threat.

Low-Power Wide-Area Networks (LPWANs) are an emerging Internet-of-Things (IoT) paradigm marked by low-power and long-distance communication. Among them, LoRa is widely deployed for its unique characteristics and open-source technology. By adopting the Chirp Spread Spectrum (CSS) modulation, LoRa enables low signal-to-noise ratio (SNR) communication. However, the standard demodulation method does not fully exploit the properties of chirp signals, thus yields a sub-optimal SNR threshold under which the decoding fails. Consequently, the communication range and energy consumption have to be compromised for robust transmission. This paper presents NELoRa, a neural-enhanced LoRa demodulation method, exploiting the feature abstraction ability of deep learning to support ultra-low SNR LoRa communication. Taking the spectrogram of both amplitude and phase as input, we first design a mask-enabled Deep Neural Network (DNN) filter that extracts multi-dimension features to capture clean chirp symbols. Second, we develop a spectrogram-based DNN decoder to decode these chirp symbols accurately. Finally, we propose a generic packet demodulation system by incorporating a method that generates high-quality chirp symbols from received signals. We implement and evaluate NELoRa on both indoor and campus-scale outdoor testbeds. The results show that NELoRa achieves 1.84-2.35 dB SNR gains and extends the battery life up to 272% (~0.38-1.51 years) in average for various LoRa configurations.

Multi-view vehicle re-identification (Re-ID) aims to retrieve all images of a target vehicle from a large gallery where the vehicles are captured from non-overlapping cameras. However, the drastic variation in vehicle appearance under different viewpoints greatly affects the performance of the multi-view vehicle Re-ID model, so the key issue in multi-view vehicle Re-ID is learning an effective feature representation that is robust to both dramatic intra-class variability and small inter-class variability. To achieve this goal, we have proposed a multi-center metric learning framework for multi-view vehicle Re-ID. In our approach, we model latent views from vehicle visual appearance directly without any extra labels except ID. Firstly, we introduce several latent view clusters for a vehicle to model latent multi-view information and each view cluster has a learnable center. Then multi-view vehicle matching task can be transformed into two subproblems, cross-view matching and cross-target matching. Finally, an intra-class ranking loss with cross-view center constraint and a cross-class ranking loss with cross-vehicle center constraint are proposed to address the two subproblems, respectively. Extensive experimental evaluations on three widely used benchmarks show the superiority of the proposed framework in contrast to a series of existing state-of-the-arts.

User identified gesture recognition is a fundamental step towards ubiquitous device-free sensing. We propose WiHF, which first simultaneously enables cross-domain gesture recognition and user identification using WiFi in a real-time manner. The basic idea of WiHF is to derive a cross-domain motion change pattern of arm gestures from WiFi signals, rendering both unique gesture characteristics and the personalized user performing styles. To extract the motion change pattern in realtime, we develop an efficient method based on the seam carving algorithm. Moreover, taking as input the motion change pattern, a Deep Neural Network (DNN) is adopted for both gesture recognition and user identification tasks. In DNN, we apply splitting and splicing schemes to optimize collaborative learning for dual tasks. We implement WiHF and extensively evaluate its performance on a public dataset including 6 users and 6 gestures performed across 5 locations and 5 orientations in 3 environments. Experimental results show that WiHF achieves 97.65% and 96.74% for in-domain gesture recognition and user identification accuracy, respectively. The cross-domain gesture recognition accuracy is comparable with the state-of-the-art methods, but the processing time is reduced by 30×.

Wi-Fi imaging has attracted significant interests due to the ubiquitous availability of Wi-Fi devices today. In this paper, we present Wi-Fi See It All (WiSIA), a versatile Wi-Fi imaging system built upon commercial off-the-shelf (COTS) Wi-Fi devices, which is able to simultaneously detect objects and humans, segment their boundaries, and identify them within the image plane. To achieve this, WiSIA utilizes three techniques. First, instead of constructing the image plane at the receiver side using a high-cost antenna array and complex parameter estimation, WiSIA pushes the image plane to the object side with two pairs of transceivers and 2D-IFFT. Second, WiSIA extracts the specific physical signature of the signals reflected from multiple objects to segment their boundaries. Third, WiSIA incorporates a cGAN (conditional Generative Adversarial Network) to enhance the boundary of different objects. We have implemented WiSIA using COTS Wi-Fi devices and evaluated it using a rich set of experiments. Our results demonstrate the efficacy of WiSIA. It outperforms the state-of-the-art vision-based method in dark and occlusion scenarios, demonstrating its superiority in such challenge scenarios.