Camera Movement Classification: A fundamental base for automatic video analysis

Status: available
Supervisor: Daniel Helm, Martin Kampel

Start: as soon as possible

Problem Statement

Automatic video content analysis is needed in many different domains such as historical film preservation or film archiving. Due to the enormous quantity of available visual media data, automatic approaches shall be used in order to find specific content in videos or create new visual representations of specific domains. A fundamental part in video content analysis and film archival is the detection of camera movements such as panning, tilting, zooming or tracking within one camera shot. Moreover, camera settings like focal length, the distance between a camera and an object are basic settings which give information about the camera operations within given image-sequences.

The goal of this practical work is as follows:

For establishing an automatic video analysis platform, a “Camera Operations Detection module”, shall be developed. This module shall be able to detect and classify camera movements such as panning, tilting, tracking as well as zooming in given input videos.

Workflow

  • Literature Review – getting to know the algorithms
  • Implementation and optimization of state-of-the-art approaches
  • Creation of a deployable software package
  • Evaluation of implemented algorithms
  • Written Report and final presentation

Requirements

Basic knowledge in computer vision
Experience in Python, C++ and Matlab
Interest in Deep Learning (Tensorflow, Keras, PyTorch) and Machine Learning

This work is part of the project “Visual History of the Holocaust”.

The practical course is part of an ongoing research project. A “Forschungsbeihilfe” is available for the selected student.