Multi-Camera Tracking Works?

Author: Carlton Purvis, Published on Jun 27, 2013

Being able to track people across cameras and buildings simply by using cameras and analytics is something of a 'holy grail' for the surveillance industry.

Two researchers from Carnegie Mellon University have developed just such a system that allows them use surveillance cameras to track a person's movements throughout a building, even when they are out of sight of the camera. The set-up combines three different datasets that allow them to tag and identify people and place their movements on a map. In this note, we interview one of the researchers and breakdown how the system works.

**** *****************-* *********** **** ******** ******* **** ******** **** ** **** *****-****** tracking ******* ******* ** ***** *** ****** **** * ****** view ** *** ***** ***********, ***** ** *** *** **** in **** ************ ***********. **** **** ********** ********** ** ************ tracking ****** ** “******* ****** ************.”

*** ***** **** **** **** ***** ** * ******* **** in ****, **** ****** ********* (*** *** ****** ****** *****), many ***** *** * ******** ****** ** **** ******* ****** the ***. ********* *** ** ***** **** **** ***** ************ track ******, **** ******* ****** **** ** ********* **** **** clothing, ********** *** ****** ***********. *********** *** **** ********* **** ****.

*** *** **** *****:

********* ****:

  • *********** ********** ******* **** ***** ********. *** *** ***** *** ******* ranged **** ** ** ** *******.
  • *** ****** *** ***** **** ******* -- “** ******* [*******] **** MPEG2 ** ** *** ******, *** **** ** ** * server. ******** *** ***** **** **** *** ******** ** *** cameras *** ** ****'* **** ****," ********* ****.
  • ******** ****** *********** ******** (****** ** ********* ** ******)
  • * ******** ********* ******* ** ******* ******** *****, **********, * pre-loaded ** *** ** *** ********, *** ****** ***********.

********* ****, “** ****’* ******** **** **** [*********] ** ******* facial *********** ** ****** ********* ** **** ** ********, ** recorded ** ** **** * ********** ** ******** (*******), *** this ** **** ** ***** ** ****. *** **** ***********, it ****** ********** ****.” **** **** **** ** ***** * subject ****** *** ***** ** ******* ** *** ****.  

Multiple **** *******

******** *****

“******** *** ***** ***** *********** **** **** ********** ******** ******** switches **** ******** ****** **** **** ***** ******** *** ***** up. ********** ***** *********** **** **** ** ************** ********* ******,” according ** ***** ***** ******. *********, ***** *** ***** ******* data ********* ** ***** * ****** ********** *** ********.

******** ******* ****** ****** ** ****** ******* ** ****** ** different ******* ** *** ****** *** *** ** ****** ******* to **** ***** *** ***** *************. ** ** ****** ****** a ******* *****, *** ****** ***** ***** ********* **. ******* ******** problem **** *** ******* **** ********* *** **** “**** ***’* dress ** *********** ********* ******,” ********* ****. ***** **** ** the ********* **** ******* ******* ******, ****** *** ****** * challenge ** ************** ******* ****.  

** **** ***** *** ********* ***** *** ********** ** “******” it *** *** **** ****** ** ******. “******* *** **** in ** ***** *** ***** *** ****** **, *** *** camera **** ‘** *’** *** *** ****** ** **** *** I’m ****** **** ***** ************* *** **** ****** ***.’" ** *** people ******** ** ****** ******* ******* ******, *** ********** ********* would **** ** *** ** ******** ****** *** **************. **** ***** added * ****** ********* ********** -- * ****** ****** ** in *** ****** ** *** ****.

**********

********** ********** ***** ** *********** ** ***** * ****** ****** be, ***** ** ***** ********* ** ******, * ** ************ of *** ******** **** *** ********* “****” *** ***** *******. Even **** * ****** ** *** ************ *********** ** * person, ** *** *******, *** *** ***** *** ** * person ** ** *** ******** **** ** * ****, ********* by * ****** *******. ************ ******* **** ***** ******* **** **** ignored. *** ********** ***** ** *** ***** ***** ** ********* only ******* ** *** ******. 

***** ****** **** *** ******** **** ****** ** *** ****** views. *** ****** ******** **** ***, *** ***** ** ********** based ** ***** ****** ***** *** *** **********.

****** ***********

****** ********* *** ********* **** ** ********** ******** **** * person ***** *** ** ********** ** ******** ***** ** ********* trajectory. ** *** **** *** **** **** ********* (****** ***** six ******* ** ********* * ****). ************ **** ****** ****** were **** ******** *** ***** **** *****, *** ******* “**** of *** ******** **** ***** ****** ** ** **** **** walking **** **** ***** ******* ****.” **** ******* *** *** a ***** **** ** * ******’* ****, **** **** ***** verify **** ** *** *** **** ****** ******** ** ********** and ******** *****.

“*** **** ** [****** ***** ****** ***********] *** *** **** high *** ***** *** ****** *********** ****** ** ** *** us **** ** *** **** ****** *****,” ********* ****. **** 10 ******* ** *** ** *** ***** ****** ********* ******** usable ****** ***********, *** “** ******** * ********* ** ***** correction **** *** ****’* *** *********. ******* ****** *********** *** ****** could ***** * ****** ****** *** ***** ** ******* ** *** time. *** ********* ***** ****** *********** *** **** ** ***** a ****** ****** *** ***** ** ******* ** *** ****. 

** *** **** ** ** ***** ********* *** **********, ** a ****** ***** ** **** ********, *** **** ****** ** chance ** **** ***** ** ****. *** ****** *********** ***** us **** ** * ********** **** **** **** *** ** be **** ****** **** ***** ***.”

*** *********** **** ******* **** *** ********* ** “*** ********* in **** ******* ********* ***** **** ****** ***** *** **** color *******,” ********** ******* ** ****** *********** **********, ** ******** trajectory (****** ****** *** ****/*** *********** ** ******** * ****) and *** **** ** *** **** *****.

**** ******* ***** ******* **** **** ** *********** ****** *** ******* *********** **********.

Future *****

"** **** ******* ******** *** ********* ************* ******* – **** project ** ******* ** ***** ** ****** *** **********. ********* ***** are ** ******** ***** ** ****** *** *****. **** ***** need * *********** ****** ** *********** *** *******," ********* ****. 

***** *** ** ***** ** ************* *** ******** (********* ** university ****** ** ** ***** ** *** ******** *** *** **********), but ** ***** ** **** ********* *** *********, ********* ****. 

IPVM ********

********* **** ******* ***** **** *** *********** **** *** ** mind **** **** ******* ***** ********. *** ******** ****** ***** be * *** ** **** **** ** ******** *** ***** wander *** ** ** **** ***** ****** *** ** **** of * ******* *********. **** ********** ***** ** ********** ** environments **** ******** ***** ***** ****** **** ** ** ********* for ****** *** ****** *******, *** **** ** **** ******** areas. *** ***** *********** ** **** **** **** ** **** was ****** ********** **********. *** **** ****** *** ******* *** spent ******** ** ****** ** ****** ******* ** **** *** is ***** ** **** ***** ** *** ********. *********'* ********** could **** **** ********** ******* ** **** ******* ***** **** are ** * ********, *** **** **** ****'* ****'** **** through. Another ********** ** ************** ** ******* ********** **** ***** ** ****** ** ******* *** **** ***** ***** environments ** ***** * ****** ** ********. 

** *** ******** ****, *** ***** ******* ** ****** ******** - ** ****** * **** ***** *****, ******** *********** **** and ********** ***********.

*******, ******** ****** *** ***** ********** **** **** *** ***** conducted ** ****, ** ** ***** ** *********** ** *** how **** ***** ***** **** *** ** ********** ** **** with ******* ********** *** ****** ********** *****.

Comments (3)

***'* **** **** ****** ******* ** ***?

**** ********* *** ************ *** ***** ******* ...

***** **** -*****************.***- (**** *'** ***** ***** **) ***** ** **** ** operational ***** ** *****-****** ********.

********** **** *** ***** ** *** ****** **** *****:

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports on Facial Recognition

Face Recognition Camera Tested (Netatmo) on Jan 29, 2016
Can face recognition make home security "better"? That is the bold claim from startup Netatmo with their Welcome camera. But with face...
Simplicam Facial Recognition Tested on Jan 23, 2015
Facial recognition, available for $150? That's the offer from a startup, Simplicam, who has not only cloned Dropcam setup and user interface but...
Japanese Stores Facial Recognition Sharing on Apr 21, 2014
A controversy is brewing in Japan after a newspaper was tipped off about a practice stores use to combat shoplifting. A network of stores uses...
Debunking Start-Up's FST21 Case Study on Oct 07, 2013
This company won ISC West Best in Show 2 years ago, recently received $5 million in funding and is being talked about as the next big thing in...
The Laziest RFP Ever on Aug 13, 2013
Bad RFPs - out of date, vague or just plain confusing - are common. But this RFP is on a whole other level. It is as if no one even looked at...
3VR Significant Layoffs on Jun 28, 2013
3VR has laid off 15 employees, five of which are from its sales team, IPVM has learned. This leaves the company with a skeleton crew of three sales...
Future of Facial Recognition on May 04, 2013
The Boston Bombings reaffirmed how far facial recognition needs to develop to be an effective surveillance tool. Despite the PR spin jobs, facial...
FAILED: Facial Recognition & Boston Bombing on Apr 20, 2013
Facial recognition vendors have been tripping over themselves to take credit, insert or claim the wonders of their offerings to identify the Boston...
Successful Facial Surveillance Case on Jan 07, 2013
Real time facial surveillance is hard to do - accuracy issues, false alerts, cost and deployment complexity all conspire against it. This is why,...

Most Recent Industry Reports

Honeywell Sues Alarm.com For Violating Anti-Trust Laws on Feb 24, 2017
Is Alarm.com about to dominate the smart home software market? That is what Honeywell alleges in its new lawsuit, first reported by...
Axis: "Everything is IP" - False on Feb 24, 2017
Axis is congratulating itself, with executive Fredrick Nilsson declaring: "Now the conversion is all done and everything is IP and analog is...
Advertising Like Avigilon at the ISC West Airport on Feb 24, 2017
Avigilon has grabbed a lot of attention over the last few years advertising at the Las Vegas airport when attendees fly in. But how does that...
Artificial Intelligence Robot Assistant (ACTi) on Feb 23, 2017
Has artificial intelligence come to the video surveillance industry? ACTi has released 'SARA' which it bills as an 'AI assistant that brings...
Cutting Costs 70% Using Milestone With HD Analog on Feb 23, 2017
HD analog and enterprise VMSes are often thought of as being on opposite sides of the spectrum, with HD analog best for small jobs due to its low...
Dahua 4K HD Analog Cameras Announced on Feb 23, 2017
HD analog has been gaining popularity (even if Axis hopes otherwise). Last year, HD analog's max resolution doubled from 1080p to 4MP (see our 4MP...
Uniview (UNV) IP Cameras Tested on Feb 22, 2017
"We're #3," in China says Uniview (UNV). While the company significantly trails Hikvision and Dahua in total sales, one notable difference is that...
Glass Doors and Access Control Tutorial on Feb 22, 2017
The biggest challenge for many access control systems are glass doors. Here's what happens when a maglock is improperly installed to an existing...
Exacq Favorability Results on Feb 22, 2017
For years, Exacq has been one of the most frequently favored VMSes in IPVM integrator statistics (e.g., see Favorite VMS Manufacturers...
The Hot RMR Company - Electric Guard Dog on Feb 22, 2017
The financiers at the Barnes Buchanan conference praised a company named 'Electric Guard Dog'. While the name sounds fairly low tech, the money and...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact