An Efficient Vehicle Counting Method Using Mask R-CNN

Zaynab Al-Ariny, Mohamed A. Abdelwahab, Mahmoud Fakhry, El Sayed Hasaneen

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

4 Citations (Scopus)

Abstract

In this paper, an accurate approach for vehicle counting in videos using Mask R-CNN and KLT tracker is proposed. Vehicle detection is performed for each N frames using Mask R-CNN instance segmentation model. This model outperforms other deep learning models that using bounding box detection as it provides a segmentation mask for each detected object, the outperformance comes up clearly in cases of occlusions. Once the objects are detected, their corner points are extracted and tracked. An efficient method is introduced to assign point trajectories to their corresponding detected vehicles. The proposed counting algorithm distinguishes precisely between the new vehicles and the counted ones. The experiments performed on diverse challenging videos show excellent results compared to state-of-The-Art counting methods.

Original languageEnglish
Title of host publicationProceedings of 2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages232-237
Number of pages6
ISBN (Electronic)9781728148007
DOIs
Publication statusPublished - Feb 2020
Event2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020 - Aswan, Egypt
Duration: Feb 8 2020Feb 9 2020

Publication series

NameProceedings of 2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020

Conference

Conference2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020
CountryEgypt
CityAswan
Period2/8/202/9/20

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Signal Processing

Fingerprint Dive into the research topics of 'An Efficient Vehicle Counting Method Using Mask R-CNN'. Together they form a unique fingerprint.

Cite this