| NSF Org: |
CNS Division Of Computer and Network Systems |
| Recipient: |
|
| Initial Amendment Date: | August 10, 2014 |
| Latest Amendment Date: | August 10, 2014 |
| Award Number: | 1449860 |
| Award Instrument: | Standard Grant |
| Program Manager: |
John Brassil
CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | October 1, 2014 |
| End Date: | September 30, 2017 (Estimated) |
| Total Intended Award Amount: | $199,995.00 |
| Total Awarded Amount to Date: | $199,995.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1805 N BROAD ST PHILADELPHIA PA US 19122-6104 (215)707-7547 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
PA US 19122-6094 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Information Technology Researc |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
The goal of this US Ignite project is to develop and demonstrate the utility of 3D cameras on police cars connected to cloud-based computing via high-speed wireless networks. Camera-based surveillance systems play an important role in helping law enforcement manage public safety but existing systems have several drawbacks. The first limitation is that most current systems rely on static cameras, which limits the flexibility for law enforcement to deploy the cameras to targeted areas as needed. The second limitation is that most surveillance cameras do no work well in environments with poor visibility such as nighttime or fog. By combining back-end (or cloud-based)video processing with 3D cameras the project addresses both of these issues.
The project will install 3D cameras on police cars belonging to the Temple University campus police department and back-haul the video data via the Temple University GENI WiMax and campus WiFi infrastructures to a campus computing cluster for analysis with the results being relayed back to the police officers as alerts or other status. The project extends existing work on target tracking and detection to deal with 3D video feeds. The project in being run in conjunction with the Temple University campus police department which is providing domain expertise and facilitating testing of the prototype system.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Our research on 3D cameras result in new entity detection algorithms that make use of the additional depth information available from a 3D camera to determine whether a person is within a pre-specified distance away from the camera. Our algorithm is able to accurately detect the person even in poor light conditions. Our research on high-speed wireless networking has resulted in new decision algorithms to better utilize different types of wireless networks. The switching algorithms are designed to dynamically adjust the decision for cars moving at vehicular speeds, and do not require prior knowledge of the deployment of these networks. We have also developed a video summarization algorithm that is able to reduce the amount of video being transmitted by automatically extracting unique frames of interest. This summarization algorithm has multiple applications, including a mechanism to reduce wireless transmission overhead, as well as to help cope with growing amount of video data generated by cameras. In terms of broader impacts, the project helped trained multiple graduate, and undergraduate students in the areas of wireless networking, cloud computing, computer vision, and security/privacy for video capture by law enforcement. The project has resulted in a creation of a new dataset consisting of traffic scenes collected under different weather conditions. This new dataset will be useful for researchers working multiple areas such as self-driving vehicles to test their algorithms. This dataset is made available to the public. In terms of research publications, the project resulted in 10 peer-reviewed journal and conference publications, and 2 poster papers by undergraduate students.
Last Modified: 12/03/2017
Modified by: Chiu C Tan
Please report errors in award information by writing to: awardsearch@nsf.gov.
