Personal tools

Difference between revisions of "Real-Time Pedestrian Detection For Privacy Enhancement"

From iis-projects

Jump to: navigation, search
m
 
(4 intermediate revisions by the same user not shown)
Line 16: Line 16:
 
: Knowledge of Matlab and/or C/C++
 
: Knowledge of Matlab and/or C/C++
 
: Interest in video processing and machine learning
 
: Interest in video processing and machine learning
: For FPGA development, VLSI 1 is required
+
: if interested in FPGA development, VLSI 1 is required
  
 
<!--  
 
<!--  
Line 28: Line 28:
 
: Supervision: [[:User:Mluisier | Mathieu Luisier]]
 
: Supervision: [[:User:Mluisier | Mathieu Luisier]]
 
--->
 
--->
 +
 
===Character===
 
===Character===
 
: 20% Theory / Literature Research  
 
: 20% Theory / Literature Research  
Line 50: Line 51:
 
==Results==  
 
==Results==  
  
==Links==  
+
==Links==
 +
* pedestrian dataset: [[http://www.cvc.uab.es/adas/site/?q=node/7 website]]
 +
* semantic segmentation dataset: [[http://www.cvc.uab.es/adas/site/?q=node/77 website]]
  
 
[[#top|↑ top]]
 
[[#top|↑ top]]
Line 58: Line 61:
 
[[Category:Semester Thesis]]
 
[[Category:Semester Thesis]]
 
[[Category:Master Thesis]]
 
[[Category:Master Thesis]]
[[Category:Hot]]
+
[[Category:System Design]]
  
 
<!--  
 
<!--  
Line 97: Line 100:
  
 
--->
 
--->
 +
 +
[[Category:Lukasc]]

Latest revision as of 12:17, 5 February 2016

Pedestrians.png

Short Description

More and more video surveillance data is being collect for real-time surveillance and storage. Privacy is a real issue, posing a legal obstacle when public places are being monitored: real-time surveillance is not allowed in such cases, and stored data can (even for internal use) only be accessed with a court order.

With the use of privacy enhancement techniques, this is different. Currently, such systems are often based on simple motion detection, blurring everything that has moved recently. This can be an option if there is little activity and only very low detail is needed. However, when monitoring a crowded area the results are useless and important detail such as the person's movements is completely hidden.

This project is supposed to overcome this by using deep learning techniques to detect pedestrians/persons and using temporal/motion information to improve the delineation of moving objects. This way the pedestrians can be overpainted, blurred, or overlaid with motion-based information, protecting their privacy while enabling better information to security personnel.


Status: Available

Looking for 1 Master or 2 semester project students
Contact: Lukas Cavigelli

Prerequisites

Knowledge of Matlab and/or C/C++
Interest in video processing and machine learning
if interested in FPGA development, VLSI 1 is required


Character

20% Theory / Literature Research
20% Software Development, 60% FPGA Development & Verification
or 80% software development

Professor

Luca Benini

↑ top

Detailed Task Description

Goals

Practical Details

Results

Links

  • pedestrian dataset: [website]
  • semantic segmentation dataset: [website]

↑ top