Vehicle detection in aerial images using multiscale structure enhancement and symmetry

Sundaresh Ram, Jeffrey J Rodriguez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Scopus citations

Abstract

Accurate detection and localization of vehicles in aerial images has a wide range of applications including urban planning, military reconnaissance, visual surveillance, and realtime traffic management. Automated detection of vehicles in aerial imagery is a challenging task, due to the density of vehicles on the road, the complexity of the surrounding environment in urban areas, and low spatial resolution of the image sensor array. We propose an automated method for detecting vehicles of varying sizes in low-resolution aerial imagery. First, we develop a new vehicle enhancement filter involving multiscale Hessian analysis. After thresholding, we refine the candidate vehicle detections based on analysis of bilateral symmetry. We show that our proposed method provides improved detection accuracy compared with existing vehicle detection algorithms for various low-resolution aerial images.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages3817-3821
Number of pages5
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2016-August
ISSN (Print)1522-4880

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
Country/TerritoryUnited States
CityPhoenix
Period9/25/169/28/16

Keywords

  • Aerial imagery
  • Bilateral symmetry
  • Hessian filter
  • Vehicle detection
  • Wavelet transform

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Vehicle detection in aerial images using multiscale structure enhancement and symmetry'. Together they form a unique fingerprint.

Cite this