Personal tools

Real-Time Optical Flow Using Neural Networks

From iis-projects

Revision as of 00:37, 9 February 2015 by Lukasc (talk | contribs) (Practical Details)
Jump to: navigation, search
OptFlowBus.jpg
OptFlowTennis.png

Short Description

Optical flow data is an ingredient to many complex computer vision systems. There are already quite a few algorithms to determine the optical flow between two frames very well. Some of these approaches use spatial correlation of small image patches, others work by looking at few well-trackable points (corners, edges, ...) in both images to find correspondences and then solve complex optimization problems to find reasonable solutions between these key points.

Evaluation of these algorithms is very time-consuming, often taking many seconds per frame on powerful workstations. This puts real-time applications out of reach where computer vision is most interesting: on low-power and mobile platforms, in cars, ...

We would like to take an unconventional approach to improve on this, training deep convolutional neural networks to calculate optical flow. The biggest issue of neural networks is usually to get a large enough, (hand-)labeled dataset. This is not a problem here, since we can take a high-quality algorithm's output as our reference input and getting raw video data without a lot of constraints is not really an issue.

As part of this project, the student(s) will:

  • Explore existing optical flow algorithms
  • Implement the most promissing candidate(s) (or make use of available implementations)
  • Learn the fundamentals of convolutional neural networks (ConvNets)
  • Get to know and use the Torch framework to train and adapt his ConvNet
  • Evaluate the results (accuracy, performance)
  • If there is time left: make a real-time demonstrator (camera interface, working platform, ... is already available)

The project can be adapted to the preferences of the student(s). Just drop me an email or stop by my office if you ..

  • ... want to know more,
  • ... are uncertain whether this project suits you, or
  • ... if you have any other question.

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

Character

30% Theory / Literature Research
70% software development

Professor

Luca Benini

↑ top

Detailed Task Description

This will be written after talking to the interested students, taking into account their interests and existing knowledge.

Goals

Practical Details

Results

Links

If you have a look at these, please don't worry too much about the math involved. The underlying concept is often much simpler, and I will help you with understand whatever you need.

  • Motion tracking/optical flow using keypoint matching [paper]
  • PhD thesis focusing on motion tracking/optical flow using keypoint matching (SIFT-Flow): [website], [thesis]
  • Correlation-based, variational optical flow: [paper]
  • The Torch framework: [website]


↑ top