Browsing by Subject "tracking"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    e-DOTS: AN INDOOR TRACKING SOLUTION
    (Office of the Vice Chancellor for Research, 2012-04-13) Rybarczyk, Ryan; Raje, Rajeev; Tuceryan, Mihran
    Accurately tracking an object as its moves in a large indoor area is at-tractive due to its applicability to a wide range of domains. For example, a typical healthcare setup may benefit from tracking their assets, such as spe-cialized equipment, in real-time and thus optimize their usage. Existing techniques, such as the GPS, that focus on outdoor tracking do not provide accurate estimations of location within the confines of an indoor setup. Prev-alent approaches that attempt to provide the ability to perform indoor track-ing primarily focus on a homogenous type of sensor when providing an esti-mation of an object’s location. Such a homogeneous view is neither benefi-cial nor sufficient due to specific characteristics of single type of sensors. This research aims to create a distributed tracking system composed out of many different kinds of inexpensive and off-the-shelf sensors to address this challenge. Specifically, the proposed system, called Enhanced Distributed Object Tracking System (e-DOTS), will incorporate sensors such as web cameras, publically available wireless access points, and inexpensive RFID tracking tags to achieve accurate tracking over a large indoor area in real-time. As an object, in addition to moving in a known indoor setup, may move through an unknown confined area, the e-DOTS needs to incorporate opportunistic discovery of available sensors, select a proper subset of them, and fuse their readings in real-time to achieve an accurate estimation of the current position of that object. A preliminary prototype of e-DOTS has been created and experimented with. The results of these validations are promis-ing and suggest the possibility of e-DOTS achieving its desired goals. Further research is aimed at incorporating different kinds of sensors, different fusion techniques (e.g., Federated Kalman Filtering) and various discovery mecha-nisms to improve the tracking accuracy and the associated response time.
  • Thumbnail Image
    Item
    Forward Collision Prediction with Online Visual Tracking
    (IEEE, 2019-09) Kollazhi Manghat, Surya; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
    Safety is the key aspect when comes to driving. Self-driving vehicles are equipped with driver-assistive technologies like Adaptive Cruise Control, Forward Collision Warning system (FCW) and Collsion Mitigation by Breaking (CMbB) to ensure safety while driving. This paper proposes a method by following a lean way of multi-target tracking implementation and 3D bounding box detection without processing much visual information. Object Tracking is an integral part of environment sensing, which enables the vehicle to estimate the surrounding object’s trajectories to accomplish motion planning. The advancement in the object detection methods greatly benefits when following the tracking by detection approach. This will lead to less complex tracking methodology and thus decreasing the computational cost. Estimation based on particle filter is added to precisely associate the tracklets with detections. The model estimates and plots bounding box for the objects in its camera range and predict the 3D positions in camera coordinates from monocular camera data using a deep learning combined with geometric constraints using 2D bounding box, then the actual distance from the vehicle camera is calculated. The model is evaluated on the KITTI car dataset.
  • No Thumbnail Available
    Item
    Monitoring and Assessing Community-Engaged Activities Across Campus
    (2016-10-23) Norris, Kristin; Weiss, H. Anne; Mack, Heather; Medlin, Kristin; Wittman, Amanda
    Most campuses are eager to answer the question "How are students, faculty, and staff at my campus working to address wicked or public problems?" In this presentation we explore a range of strategies to track and monitor community-engaged activities going on across your campus, which includes curricular, co-curricular or project-based activities that are done in collaboration with the community. This presentation gives participants tools, strategies, steps, and information that can be used to design, initiate, and/or enhance systematic assessment or evaluation of community-engaged activities.