Advanced search
1 file | 8.45 MB Add to list
Author
Organization
Project
Abstract
Broiler localization is crucial for welfare monitoring, particularly in identifying issues such as wet litter. We focus on multi-camera detection systems since multiple viewpoints not only ensure comprehensive pen coverage but also reduce occlusions caused by lighting, feeder and drinking equipment. Previous multi-view detection studies localize subjects either by aggregating ground plane projections of single-view predictions or by developing end-to-end multi-view detectors capable of directly generating predictions. However, single-view detections may suffer from reduced accuracy due to occlusions, and obtaining ground plane labels for training end-to-end multi-view detectors is challenging. In this paper, we combine the strengths of both approaches by using the readily available aggregated single-view detections as labels for training a multi-view detector. Our approach alleviates the need for hard-to-acquire ground-plane labels. Through experiments on a real-world broiler dataset, we demonstrate the effectiveness of our approach.

Downloads

  • 8581 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 8.45 MB

Citation

Please use this url to cite or link to this publication:

MLA
Cardoen, Thorsten, et al. “Label Efficient Lifelong Multi-View Broiler Detection.” 2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW, IEEE, 2024, pp. 5393–402, doi:10.1109/CVPRW63382.2024.00548.
APA
Cardoen, T., Leroux, S., & Simoens, P. (2024). Label efficient lifelong multi-view broiler detection. 2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW, 5393–5402. https://doi.org/10.1109/CVPRW63382.2024.00548
Chicago author-date
Cardoen, Thorsten, Sam Leroux, and Pieter Simoens. 2024. “Label Efficient Lifelong Multi-View Broiler Detection.” In 2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW, 5393–5402. IEEE. https://doi.org/10.1109/CVPRW63382.2024.00548.
Chicago author-date (all authors)
Cardoen, Thorsten, Sam Leroux, and Pieter Simoens. 2024. “Label Efficient Lifelong Multi-View Broiler Detection.” In 2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW, 5393–5402. IEEE. doi:10.1109/CVPRW63382.2024.00548.
Vancouver
1.
Cardoen T, Leroux S, Simoens P. Label efficient lifelong multi-view broiler detection. In: 2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW. IEEE; 2024. p. 5393–402.
IEEE
[1]
T. Cardoen, S. Leroux, and P. Simoens, “Label efficient lifelong multi-view broiler detection,” in 2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW, Seattle, WA, USA, 2024, pp. 5393–5402.
@inproceedings{01J2X51SSYVSMB7B75JJMJ9XDV,
  abstract     = {{Broiler localization is crucial for welfare monitoring, particularly in identifying issues such as wet litter. We focus on multi-camera detection systems since multiple viewpoints not only ensure comprehensive pen coverage but also reduce occlusions caused by lighting, feeder and drinking equipment. Previous multi-view detection studies localize subjects either by aggregating ground plane projections of single-view predictions or by developing end-to-end multi-view detectors capable of directly generating predictions. However, single-view detections may suffer from reduced accuracy due to occlusions, and obtaining ground plane labels for training end-to-end multi-view detectors is challenging. In this paper, we combine the strengths of both approaches by using the readily available aggregated single-view detections as labels for training a multi-view detector. Our approach alleviates the need for hard-to-acquire ground-plane labels. Through experiments on a real-world broiler dataset, we demonstrate the effectiveness of our approach.}},
  author       = {{Cardoen, Thorsten and Leroux, Sam and Simoens, Pieter}},
  booktitle    = {{2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW}},
  isbn         = {{9798350365481}},
  issn         = {{2160-7508}},
  language     = {{eng}},
  location     = {{Seattle, WA, USA}},
  pages        = {{5393--5402}},
  publisher    = {{IEEE}},
  title        = {{Label efficient lifelong multi-view broiler detection}},
  url          = {{http://doi.org/10.1109/CVPRW63382.2024.00548}},
  year         = {{2024}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: