access icon free Real-time object entity detection system for smart surveillance application

A real-time scheme for detecting object entities in real-time among a set of objects contained in the same class category is proposed. Building a unified framework for real-time object entity detection system without an additional training process to distinguish the object entities while minimising the loss of accuracy is focused. The experimental results on a benchmark dataset demonstrate that the method shows outstanding precision performance while achieving state-of-the-art object detection speed.

Inspec keywords: surveillance; object detection

Other keywords: precision performance; unified framework; benchmark dataset; state-of-the-art object detection speed; additional training process; real-time object entity detection system; smart surveillance application

Subjects: Computer vision and image processing techniques; Optical, image and video signal processing

References

    1. 1)
      • 2. Redmon, J., Farhadi, A.: ‘YOLO9000: better, faster, stronger’, arXiv preprint arXiv:1612.08242, 2016.
    2. 2)
    3. 3)
      • 4. Tamgade, S.N., Bora, V.R.: ‘Motion vector estimation of video image by pyramidal implementation of Lucas Kanade optical flow’. Emerging Trends in Engineering and Technology (ICETET), 2009 2nd Int. Conf. on, 2009, pp. 914917.
    4. 4)
    5. 5)
      • 5. Ryoo, M.S., Aggarwal, J.K.: ‘UT-interaction dataset, ICPR contest on semantic description of human activities (SDHA)’, 2010, Available at http://cvrc.ece.utexas.edu/SDHA2010/Human_Interaction.html.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.1532
Loading

Related content

content/journals/10.1049/el.2017.1532
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading