TY - GEN
T1 - Precise detection in densely packed scenes
AU - Goldman, Eran
AU - Herzig, Roei
AU - Eisenschtat, Aviv
AU - Goldberger, Jacob
AU - Hassner, Tal
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Man-made scenes are often densely packed, containing numerous objects, often identical, positioned in close proximity. We show that precise object detection in such scenes remains a challenging frontier even for state-of-the-art object detectors. We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings. Our contributions include: (1) A layer for estimating the Jaccard index as a detection quality score; (2) a novel EM merging unit, which uses our quality scores to resolve detection overlap ambiguities; finally, (3) an extensive, annotated data set, SKU-110K, representing packed retail environments, released for training and testing under such extreme settings. Detection tests on SKU-110K, and counting tests on the CARPK and PUCPR+, show our method to outperform existing state-of-the-art with substantial margins.
AB - Man-made scenes are often densely packed, containing numerous objects, often identical, positioned in close proximity. We show that precise object detection in such scenes remains a challenging frontier even for state-of-the-art object detectors. We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings. Our contributions include: (1) A layer for estimating the Jaccard index as a detection quality score; (2) a novel EM merging unit, which uses our quality scores to resolve detection overlap ambiguities; finally, (3) an extensive, annotated data set, SKU-110K, representing packed retail environments, released for training and testing under such extreme settings. Detection tests on SKU-110K, and counting tests on the CARPK and PUCPR+, show our method to outperform existing state-of-the-art with substantial margins.
KW - Categorization
KW - Recognition: Detection
KW - Retrieval
UR - http://www.scopus.com/inward/record.url?scp=85072810992&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00537
DO - 10.1109/CVPR.2019.00537
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85072810992
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 5222
EP - 5231
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -