Vascular tracking of coronary angiographic image sequences is one of the most clinically important tasks in the diagnostic assessment and interventional guidance of cardiac disease. It is difficult to automate this application because the vascular structure is complex; moreover, unsatisfactory angiography image quality may exacerbate the difficulty of vasculature extraction. This paper converts vascular tracking into branch matching and proposes a novel and automatic greedy soft match algorithm. Our method is based on a graph framework. A graph model building module is proposed to represent the vascular structure. Then, a greedy branch searching method is adopted to acquire all possible paths in the graph that may match the reference vessel. Finally, a soft batch matching method that combines branch descriptor and dynamic time warping is presented to select the best matching branch. The solution to the problem takes advantage of both spatial and temporal continuity between successive frames. The experimental results demonstrate that the proposed algorithm is effective and robust for vascular tracking. The F1 score of a single branch dataset, which contains 12 angiographic image sequences with 77 angiograms of contrast agent-filled vessels, is 0.89 ± 0.06 and of a vessel tree dataset which contains nine sequences with 58 angiograms is 0.88 ± 0.05. Extensive experimental results well demonstrate the superior performance of the algorithm. In addition, it provides a universal solution to address the problem of filamentary structure tracking.

Breakthroughs in deep learning, GPUs, and edge computing have paved the way for always-on, live video analytics. However, to achieve real-time performance, a GPU needs to be dedicated amongst a few video feeds. But, GPUs are expensive resources and a large-scale deployment requires supporting hundreds of video cameras - exorbitant cost prohibits widespread adoption. To ease this burden, we propose Tetris, a system comprising of several optimization techniques from computer vision and deep-learning literature blended in a synergistic manner. Tetris is designed to maximize the parallel processing of video feeds on a single GPU, with a marginal drop in inference accuracy. Tetris performs CPU-based tiling of active regions to combine activities across video feeds. resulting in a condensed input volume. It then runs the deep learning model on this condensed volume instead of individual feeds, which significantly improves the GPU utilization. Our evaluation on Duke MTMC dataset reveals that Tetris can process 4x video feeds in parallel compared to any of the existing methods used in isolation.

Mobile advertisements influence customers' in-store purchases and boost in-store sales for brick-and-mortar retailers. Targeting mobile ads has become significantly important to compete with online shopping. The key to enabling targeted mobile advertisement and service is to learn shoppers' interest during their stay in the store. Precise shopper tracking and identification are essential to gain the insights. However, existing sensor-based or vision-based solutions are neither practical nor accurate; no commercial solutions today can be readily deployed in a large store. On the other hand, we recognize that most retail stores have the installation of surveillance cameras, and most shoppers carry Bluetooth-enabled smartphones. Thus, in this paper, we propose TAR to learn shoppers' in-store interest via accurate multi-camera people tracking and identification. TAR leverages widespread camera deployment and Bluetooth proximity information to accurately track and identify shoppers in the store. TAR is composed of four novel design components: (1) a deep neural network (DNN) based visual tracking, (2) a user trajectory estimation by using shopper visual and BLE proximity trace, (3) an identity matching and assignment to recognize shopper's identity, and (4) a cross-camera calibration algorithm. TAR carefully combines these components to track and identify shoppers in real-time. TAR achieves 90% accuracy in two different real-life deployments, which is 20% better than the state-of-the-art solution.

We present a smartphone-based application, called LocBLE, for enabling users to estimate the location of nearby Bluetooth low energy (BLE) beacons. In contrast to existing BLE beacon-based proximity applications that can only show coarse-grained (immediate, near, and far) distance estimation, LocBLE's fine-grained estimation can enhance human-environment interactions.

Developers deploying web applications in the cloud often need to determine how changes such as service tiers or runtime loads may affect user-perceived page load time. We devise and evaluate a systematic methodology for exploring such "what-if" questions at the time a web application is deployed. Given a website, a web request, and “whatif” scenario, with a hypothetical configuration and runtime condition, our methodology, embedded in a system called WebPerf, can estimate a distribution of end-to-end response times for the request under the “what-if” scenario. WebPerf makes three contributions: (1) automated instrumentation of web sites written with increasingly popular task parallel libraries, to capture causal call dependencies of various computation and asynchronous I/O calls; (2) an algorithm to use the call dependencies, together with online- and offlineprofiled models of various I/O calls to estimate a distribution of end-to-end latency of the request; and (3) an algorithm to optimize modeling errors by deciding how many measurements to take within a limited time. We have implemented WebPerf for Microsoft Azure. Our experiments with five real websites and seven scenarios show that the median error of WebPerf’s estimation is within 7% for all applications and scenarios.

Precise positioning of an automobile to within lane-level precision can enable better navigation and context-awareness. However, GPS by itself cannot provide such precision in obstructed urban environments. In this paper, we present a system called CARLOC for lane-level positioning of automobiles. CARLOC uses three key ideas in concert to improve positioning accuracy: it uses digital maps to match the vehicle to known road segments; it uses vehicular sensors to obtain odometry and bearing information; and it uses crowd-sourced location of estimates of roadway landmarks that can be detected by sensors available in modern vehicles. CARLOC unifies these ideas in a probabilistic position estimation framework, widely used in robotics, called the sequential Monte Carlo method. Through extensive experiments on a real vehicle, we show that CARLOC achieves sub-meter positioning accuracy in an obstructed urban setting, an order-of-magnitude improvement over a high-end GPS device.

Precise positioning of an automobile to within lane-level precision can enable better navigation and context-awareness. However, GPS by itself cannot provide such precision in obstructed urban environments. In this paper, we present a system called CARLOC for lane-level positioning of automobiles. CARLOC uses three key ideas in concert to improve positioning accuracy: it uses digital maps to match the vehicle to known road segments; it uses vehicular sensors to obtain odometry and bearing information; and it uses crowd-sourced location of estimates of roadway landmarks that can be detected by sensors available in modern vehicles. CARLOC unifies these ideas in a probabilistic position estimation framework, widely used in robotics, called the sequential Monte Carlo method. Through extensive experiments on a real vehicle, we show that CARLOC achieves sub-meter positioning accuracy in an obstructed urban setting, an order-of-magnitude improvement over a high-end GPS device.

Automotive apps can improve efficiency, safety, comfort, and longevity of vehicular use. These apps achieve their goals by continuously monitoring sensors in a vehicle, and combining them with information from cloud databases in order to detect events that are used to trigger actions (e.g., alerting a driver, turning on fog lights, screening calls). However, modern vehicles have several hundred sensors that describe the low level dynamics of vehicular subsystems, these sensors can be combined in complex ways together with cloud information. Moreover, these sensor processing algorithms may incur significant costs in acquiring sensor and cloud information. In this paper, we propose a programming framework called CARLOG to simplify the task of programming these event detection algorithms. CARLOG uses Datalog to express sensor processing algorithms, but incorporates novel query optimization methods that can be used to minimize bandwidth usage, energy or latency, without sacrificing correctness of query execution. Experimental results on a prototype show that CARLOG can reduce latency by nearly two orders of magnitude relative to an unoptimized Datalog engine.

Motivated by an availability gap for visual media, where images and videos are uploaded from mobile devices well after they are generated, we explore the selective, timely retrieval of media content from a collection of mobile devices. We envision this capability being driven by similarity-based queries posed to a cloud search front-end, which in turn dynamically retrieves media objects from mobile devices that best match the respective queries within a given time limit. Building upon a crowd-sensing framework, we have designed and implemented a system called MediaScope that provides this capability. MediaScope is an extensible framework that supports nearest-neighbor and other geometric queries on the feature space (e.g. clusters, spanners), and contains novel retrieval algorithms that attempt to maximize the retrieval of relevant information. From experiments on a prototype, MediaScope is shown to achieve near-optimal query completeness and low to moderate overhead on mobile devices.

Motivated by an availability gap for visual media, where images and videos are uploaded from mobile devices well after they are generated, we explore the selective, timely retrieval of media content from a collection of mobile devices.

In this paper, we consider the design of a system in which Internet-connected mobile users contribute sensor data as training samples, and collaborate on building a model for classification tasks such as activity or context recognition. Constructing the model can naturally be performed by a service running in the cloud, but users may be more inclined to contribute training samples if the privacy of these data could be ensured. Thus, in this paper, we focus on privacy-preserving collaborative learning for the mobile setting, which addresses several competing challenges not previously considered in the literature: supporting complex classification methods like support vector machines, respecting mobile computing and communication constraints, and enabling user-determined privacy levels. Our approach, Pickle, ensures classification accuracy even in the presence of significantly perturbed training samples, is robust to methods that attempt to infer the original data or poison the model, and imposes minimal costs. We validate these claims using a user study, many real-world datasets and two different implementations of Pickle.

Due to the uncertainty of transmission opportunities between mobile nodes, Delay Tolerant Networks (DTN) routing exploits the opportunistic forwarding mechanism. Optimal policies for opportunistic forwarding are crucial to maximizing the message delivery probability while reducing the forwarding cost. In this paper, we investigate the optimal opportunistic forwarding policies for the energy- constrained DTN by introducing a continuous time Markov framework to model the message dissemination. Based on this framework, we obtain the optimal static and dynamic policies by theoretical analysis and proof. Through extensive numerical results, we conclude that the performance of the optimal dynamic policy is better than that of the static policy. Among the dynamic policies, we find that the negative power function based optimal policy provides the best performance.

Proxy mobile IPv6 (PMIPv6), a network-based IP mobility solution, is a promising approach for mobility management in all-IP wireless networks. How to enhance its handoff-related performance, such as handoff delay and signaling cost, is an important issue. Current solutions rely on approaches such as fast handoff, routing optimization and paging extension. However, the case of many correlated mobile nodes (MNs) moving together and taking handoffs at the same time has not been considered. In this paper, we propose a group-based handoff scheme for correlated MNs to enhance the performance of PMIPv6. We first propose a correlated MNs detection algorithm to detect MNs as groups. Based on this algorithm, we propose a group-based handoff procedure, and discuss its benefits and limitations. Furthermore, we evaluate the performance of PMIPv6 and our proposal through the analysis and simulation. The results show that the proposed scheme is very efficient in reducing both the handoff delay and signaling cost.