CS Events Monthly View

PhD Defense

Ubiquitous Precise Tracking: From Activity Detection over Indoor Tracking, to Outdoor Vehicle Positioning

 

Download as iCal file

Friday, December 18, 2020, 10:00am - 12:00pm
 

Speaker: Mohamed Ibrahim

Location : Remote via Zoom

Committee: 

Prof. Marco Gruteser (Advisor)

Prof. Dimitri Metaxas

Prof. Badri Nath

Prof. Richard Martin

Prof. Romit Roy Choudhury (UIUC)

Event Type: PhD Defense

Abstract: Context awareness and tracking have changed our daily activities and style of living over the last three decades. Many applications have fueled research and industry efforts to establish accurate, energy-efficient, yet scalable and easy to deploy tracking and sensing systems. One of these applications is indoor and outdoor energy saving. For example, precise room occupancy estimation and activity sensing enable better control of indoor amenities such as light, heating, and air conditioning. These indoor applications can be extended to outdoor use for smart cities, e.g., automatic decrease of lighting for empty streets. However, current tracking systems can still not meet the aforementioned stringent requirements, and as a result there are no real world deployments of such applications. For example, conventional wireless tracking relies on WiFi received signal strength, and more recently on channel state information (CSI) offering decimeter level tracking accuracy. However, these tracking systems require either extensive fingerprints collection (wardriving), the knowledge of anchor locations and/or require expensive hardware that prevents wide deployment of such systems. Therefore, these applications with their sensing requirements still demand more accurate and scalable solutions. This thesis focuses on developing wireless tracking solutions targeting submeter accuracy indoors and meter-level accuracy outdoors by leveraging unconventional wireless signals including visible light and WiFi Fine Time Measurements (FTM). These tracking algorithms can adaptively learn and simultaneously map the environment/anchors while tracking users.The goal of this research is to propose tracking and context aware sensing systems that can tweak their parameters and map the environment through crowd-sourcing without the need of offline training. In particular, the proposed solutions include: (i) EyeLight, a device-free sensing system based on visible light to enable accurate tracking indoors and provide occupancy estimation, room activity recognition services; This system integrates photosensors with light bulbs easing its deployment compared to existing systems requiring the deployment of photosensors on the floor, (ii) an open platform for experimenting with WiFi fine time measurements and a general, repeatable, and accurate measurement framework for evaluating time-based ranging systems, (iii) Wi-Go, a system that simultaneously tracks vehicles and maps WiFi access point positions by fusing WiFi FTMs, GPS, and odometry information. We believe these three systems enable energy-efficient, continuous, precise and easy to deploy indoor and outdoor tracking and context awareness sensing solutions.

: 

 

Join Zoom Meeting
https://rutgers.zoom.us/j/8033370526?pwd=K1M4NEUxbVlhM3Zab3h6cVVieDFWQT09

Join by SIP


Meeting ID: 803 337 0526
Password: 121820
One tap mobile
+16465588656,,8033370526# US (New York)
+13017158592,,8033370526# US (Washington D.C)

Join By Phone
+1 646 558 8656 US (New York)
+1 301 715 8592 US (Washington D.C)
+1 312 626 6799 US (Chicago)
+1 669 900 9128 US (San Jose)
+1 253 215 8782 US (Tacoma)
+1 346 248 7799 US (Houston)
Meeting ID: 803 337 0526
Find your local number: https://rutgers.zoom.us/u/ab23jBQYu0