Personal tools

Difference between revisions of "Change-based Evaluation of Convolutional Neural Networks"

From iis-projects

Jump to: navigation, search
m (Status: Available)
m
 
(One intermediate revision by the same user not shown)
Line 5: Line 5:
 
Imaging sensor networks, UAVs, smartphones, and embedded industrial and security computer vision systems require power-efficient, low-cost and high-speed implementations of synthetic vision algorithms capable of recognizing and classifying objects in a scene. Many popular algorithms in this area require the evaluations of multiple layers of filter banks. Almost all state-of-the-art synthetic vision systems are based on features extracted using multi-layer convolutional networks (ConvNets). When evaluating ConvNets, most of the time is spent performing the convolutions (80% to 90%), however, in many settings the input image as well as intermediate results change only at very few locations from one frame to the next (consider a fixed camera and just some people or cars moving around in the scene). This project would look into updating intermediate results only upon change of the input, thus potentially saving a lot of computational effort and making embedded smart cameras with a reasonable frame rate feasible.  
 
Imaging sensor networks, UAVs, smartphones, and embedded industrial and security computer vision systems require power-efficient, low-cost and high-speed implementations of synthetic vision algorithms capable of recognizing and classifying objects in a scene. Many popular algorithms in this area require the evaluations of multiple layers of filter banks. Almost all state-of-the-art synthetic vision systems are based on features extracted using multi-layer convolutional networks (ConvNets). When evaluating ConvNets, most of the time is spent performing the convolutions (80% to 90%), however, in many settings the input image as well as intermediate results change only at very few locations from one frame to the next (consider a fixed camera and just some people or cars moving around in the scene). This project would look into updating intermediate results only upon change of the input, thus potentially saving a lot of computational effort and making embedded smart cameras with a reasonable frame rate feasible.  
  
===Status: Available ===
+
===Status: Completed===
 +
Philippe Degen
 
: Looking for 1-2 students for a semester project or 1 student for a master thesis.  
 
: Looking for 1-2 students for a semester project or 1 student for a master thesis.  
 
: Supervision: [[:User:Lukasc | Lukas Cavigelli]]
 
: Supervision: [[:User:Lukasc | Lukas Cavigelli]]
[[Category:Software]] [[Category:System]] [[Category:Available]] [[Category:Semester Thesis]] [[Category:2016]]
+
[[Category:Software]] [[Category:System]] [[Category:Completed]] [[Category:Semester Thesis]] [[Category:2016]]
  
 
===Prerequisites===
 
===Prerequisites===
* Knowledge of C/C++
+
* Knowledge of C/C++ (depending on student's interest: CUDA)
 
* Interest in computer vision and system engineering
 
* Interest in computer vision and system engineering
  

Latest revision as of 17:04, 29 August 2016

X1-adas.jpg
Labeled-scene.png

Description

Imaging sensor networks, UAVs, smartphones, and embedded industrial and security computer vision systems require power-efficient, low-cost and high-speed implementations of synthetic vision algorithms capable of recognizing and classifying objects in a scene. Many popular algorithms in this area require the evaluations of multiple layers of filter banks. Almost all state-of-the-art synthetic vision systems are based on features extracted using multi-layer convolutional networks (ConvNets). When evaluating ConvNets, most of the time is spent performing the convolutions (80% to 90%), however, in many settings the input image as well as intermediate results change only at very few locations from one frame to the next (consider a fixed camera and just some people or cars moving around in the scene). This project would look into updating intermediate results only upon change of the input, thus potentially saving a lot of computational effort and making embedded smart cameras with a reasonable frame rate feasible.

Status: Completed

Philippe Degen

Looking for 1-2 students for a semester project or 1 student for a master thesis.
Supervision: Lukas Cavigelli

Prerequisites

  • Knowledge of C/C++ (depending on student's interest: CUDA)
  • Interest in computer vision and system engineering

Character

10% Literature Research
70% Programming
20% Evaluations

Professor

Luca Benini

↑ top

Detailed Task Description

Meetings & Presentations

The student(s) and advisor(s) agree on weekly meetings to discuss all relevant decisions and decide on how to proceed. Of course, additional meetings can be organized to address urgent issues. At the end of the project, you have to present/defend your work during a 15 min. presentation and 5 min. of discussion as part of the IIS colloquium (as required for any semester or master thesis at D-ITET).


Practical Details

↑ top