Nowadays, video surveillance systems are widely deployed in various places, e.g., schools, parks, airports, roads, etc. However, existing video surveillance systems are far from full utilization due to high computation overhead in video processing. In this work, we present ViTrack, a framework for efficient multi-video tracking using computation resource on the edge for commodity video surveillance systems. In the heart of ViTrack lies a two layer spatial/temporal compressed target detection method to significantly reduce the computation overhead by combining videos from multiple cameras. Further, ViTrack derives the video relationship and camera information even in absence of camera location, direction, etc. To alleviate the impact of variant video quality and missing targets, ViTrack leverages a Markov Model based approach to efficiently recover missing information and finally derive the complete trajectory. We implement ViTrack on a real deployed video surveillance system with 110 cameras. The experiment results demonstrate that ViTrack can provide efficient trajectory tracking with processing time 45x less than the existing approach. For 110 video cameras, ViTrack can run on a Dell OptiPlex 390 computer to track given targets in almost real time. We believe ViTrack can enable practical video analysis for widely deployed commodity video surveillance systems.

Acoustic motion tracking has been viewed as a promising user interaction technique in many scenarios such as Virtual Reality (VR), Smart Appliance, video gaming, etc. Existing acoustic motion tracking approaches, however, suffer from long window of accumulated signal and time-consuming signal processing. They are inherently difficult to achieve both high accuracy and low delay. In this paper, we present Vernier, an efficient and accurate acoustic tracking method based on commodity mobile devices. We design a new approach to efficiently and accurately derive phase change and thus moving distance. Vernier significantly reduces the tracking delay/overhead by removing the complicated frequency analysis and long window of signal accumulation, while keeping a high tracking accuracy. We implement Vernier on Android, and evaluate its performance with COTS mobile devices including Samsung Galaxy S7 and Sony L50t. Experimental results show that Vernier outperforms previous approaches with a tracking error less than 4 mm. The tracking speed achieves 3× improvement to the previous phase based approaches and 10× to Doppler Effect based approaches. Vernier is also validated in applications like controlling and drawing, and we believe it is generally applicable in many real applications.

Acoustic based tracking has been shown promising in many applications like Virtual Reality, smart home, video gaming, etc. Its real life deployments, however, face fundamental limitations. Existing approaches generally need three sound sources, while most COTS devices (e.g., TVs) and speakers have only two sound sources. We present AcouRadar, an acoustic-based localization system with single sound source. In the heart of AcouRadar we adopt a general new model which quantifies signal properties of different frequencies, distances and angles to the source. We verify the model and show that signal from a single source can provide features for localization. To address practical challenges, (1) we design an online model adaption method to address model deviation from real signal, (2) we design pulse modulated signals to alleviate the impact of environment such as multipath effect, and (3) to address signal dynamics over time, we derive relatively stable amplitude ratio between different frequencies, and thus provide a spectrum based localization method. We implement AcouRadar on Android and evaluate its performance for different COTS speakers in different environments. The results show that the model for localization can be generalized to different speakers. AcouRadar can achieve single source localization with average error less than 5 cm and average angle error of 1.76°.

With the development and popularization of WiFi, surfing on the Internet with mobile devices has become an indispensable part of people's daily life. However, as an infrastructure, WiFi access points (APs) are easily connected by some undesired users nearby. In this paper, we propose NiFi, a non-intrusive WiFi user-identification system based on WiFi signals that enable AP to automatically identify legitimate users in indoor environments, such as home, office, and hotel. The core idea is that legitimate and undesired users may have different physical constraints, e.g., moving area, walking path, and so on, leading to different signal sequences. NiFi analyzes and exploits the characteristics of signal sequences generated by mobile devices. NiFi proposes a practical and effective method to extract useful features and measures similarity for signal sequences while not relying on precise user location information. We implement NiFi on Commercial Off-The-Shelf APs, and the implementation does not require any modification to user devices. The experiment results demonstrate that NiFi is able to achieve an average identification accuracy at 90.83% with true positive rate at 98.89%.

Nowadays, video surveillance systems are widely deployed in various places, e.g., schools, parks, airports, roads, etc. However, existing video surveillance systems are far from full utilization due to high computation overhead in video processing. In this work, we present ViTrack, a framework for efficient multi-video tracking using computation resource on the edge for commodity video surveillance systems. In the heart of ViTrack lies a two layer spatial/temporal compressive target detection method to significantly reduce the computation overhead by combining videos from multiple cameras. Further, ViTrack derives the video relationship and camera information even in absence of camera location, direction, etc. To address variant video quality and missing targets, ViTrack leverages a Markov Model based approach to efficiently recover missing information and finally derive the complete trajectory. We implement ViTrack on a real deployed video surveillance system with 110 cameras. The experiment results demonstrate that ViTrack can provide efficient trajectory tracking with processing time 45x less than the existing approach. For 110 video cameras, ViTrack can run on a Dell OptiPlex 390 computer to track given targets in almost real time. We believe ViTrack can enable practical video analysis for widely deployed commodity video surveillance systems.

With the development and popularization of WiFi, surfing on the Internet with mobile devices has become an indispensable part of people's daily life. However, as an infrastructure, WiFi APs are easily connected by some undesired users nearby. In this paper, we propose NiFi, a non-intrusive WiFi user identification system based on WiFi signals that enables AP to automatically identify legitimate users in indoor environment such as home, office and hotel. The core idea is that legitimate and undesired users may have different physical constraints, e.g., moving area, walking path, etc, leading to different signal sequences. NiFi analyzes and exploits the characteristics of signal sequences generated by mobile devices. NiFi proposes a practical and effective method to extract useful features and measure similarity for signal sequences, while not relying on precise user location information. We implement NiFi on Commercial Off-The-Shelf (COTS) APs, and the implementation does not require any modification to user devices. The experiment results demonstrate that NiFi is able to achieve an average identification accuracy at 90.83% with true positive rate at 98.89%.

Cloud storage services such as Dropbox, Google Drive, and Microsoft OneDrive provide users with a convenient and reliable way to store and share data from anywhere, on any device, and at any time. The cornerstone of these services is the data synchronization (sync) operation which automatically maps the changes in users' local filesystems to the cloud via a series of network communications in a timely manner. If not designed properly, however, the tremendous amount of data sync traffic can potentially cause (financial) pains to both service providers and users.