Multi-target detection in CCTV footage for tracking applications using deep learning techniques

Dimou, A. and Medentzidou, P. and Álvarez García, Federico and Daras, P. (2016). Multi-target detection in CCTV footage for tracking applications using deep learning techniques. In: "IEEE International Conference on Image Processing (ICIP 2016)", 25/09/2016 - 28/09/2016, Phoenix, AZ, USA. pp.. https://doi.org/10.1109/ICIP.2016.7532493.

Description

Title: Multi-target detection in CCTV footage for tracking applications using deep learning techniques
Author/s:
  • Dimou, A.
  • Medentzidou, P.
  • Álvarez García, Federico
  • Daras, P.
Item Type: Presentation at Congress or Conference (Unspecified)
Event Title: IEEE International Conference on Image Processing (ICIP 2016)
Event Dates: 25/09/2016 - 28/09/2016
Event Location: Phoenix, AZ, USA
Title of Book: IEEE International Conference on Image Processing (ICIP 2016)
Título de Revista/Publicación: 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Date: 2016
ISSN: 1522-4880
Subjects:
Freetext Keywords: CCTV, motion blur, PTZ, R-CNN, spatial transformer, RNN
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Real-world CCTV footage often poses increased challenges in object tracking due to Pan-Tilt-Zoom operations, low camera quality and diverse working environments. Most relevant challenges are moving background, motion blur and severe scale changes. Convolutional neural networks, which offer state-of-the-art performance in object detection, are increasingly utilized to pursue a more efficient tracking scheme. In this work, the use of heterogeneous training data and data augmentation is explored to improve their detection rate in challenging CCTV scenes. Moreover, it is proposed to use the objects' spatial transformation parameters to automatically model and predict the evolution of intrinsic camera parameters and accordingly tune the detector for better performance. The proposed approaches are tested on publicly available datasets and real-world CCTV videos.

Funding Projects

TypeCodeAcronymLeaderTitle
FP7FP7-607480LASIEUnspecifiedUnspecified

More information

Item ID: 46043
DC Identifier: http://oa.upm.es/46043/
OAI Identifier: oai:oa.upm.es:46043
DOI: 10.1109/ICIP.2016.7532493
Official URL: http://ieeexplore.ieee.org/document/7532493/
Deposited by: Memoria Investigacion
Deposited on: 24 May 2017 17:46
Last Modified: 24 May 2017 17:46
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM