TY - GEN
T1 - Annotating 2D Imagery with 3D Kinematically Configurable Assets of Construction Equipment for Training Pose-Informed Activity Analysis and Safety Monitoring Algorithms
AU - Roberts, Dominic
AU - Wang, Yunpeng
AU - Sabet, Ali
AU - Golparvar-Fard, Mani
N1 - Publisher Copyright:
© 2019 American Society of Civil Engineers.
PY - 2019
Y1 - 2019
N2 - The availability of inexpensive and high-quality cameras has enabled research towards computer vision systems for tracking construction productivity and safety by detecting, tracking, and estimating pose of construction resources and recognizing their activities. To verify these algorithms can generalize to novel visual scenes before deployment, large amounts of labelled training and real-world validation samples are needed. While automatic generation of synthetic data helps with the former, obtaining the latter is less practical. To address this gap, we introduce a tool with which designated annotators perform pose annotation by interactively aligning 3D kinematically configurable equipment models with their depictions on 2D images. Multiple types of informative visual annotation can be retrieved using this technique, notably segmentation masks and equipment pose. Experiments demonstrate our tool's effectiveness for annotating long-form videos of earthmoving operations. We demonstrate how our tool can provide ground-truth annotations for the evaluation of a variety of computer-vision algorithms.
AB - The availability of inexpensive and high-quality cameras has enabled research towards computer vision systems for tracking construction productivity and safety by detecting, tracking, and estimating pose of construction resources and recognizing their activities. To verify these algorithms can generalize to novel visual scenes before deployment, large amounts of labelled training and real-world validation samples are needed. While automatic generation of synthetic data helps with the former, obtaining the latter is less practical. To address this gap, we introduce a tool with which designated annotators perform pose annotation by interactively aligning 3D kinematically configurable equipment models with their depictions on 2D images. Multiple types of informative visual annotation can be retrieved using this technique, notably segmentation masks and equipment pose. Experiments demonstrate our tool's effectiveness for annotating long-form videos of earthmoving operations. We demonstrate how our tool can provide ground-truth annotations for the evaluation of a variety of computer-vision algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85068800590&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068800590&partnerID=8YFLogxK
U2 - 10.1061/9780784482421.005
DO - 10.1061/9780784482421.005
M3 - Conference contribution
AN - SCOPUS:85068800590
T3 - Computing in Civil Engineering 2019: Visualization, Information Modeling, and Simulation - Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019
SP - 32
EP - 38
BT - Computing in Civil Engineering 2019
A2 - Cho, Yong K.
A2 - Leite, Fernanda
A2 - Behzadan, Amir
A2 - Wang, Chao
PB - American Society of Civil Engineers
T2 - ASCE International Conference on Computing in Civil Engineering 2019: Visualization, Information Modeling, and Simulation, i3CE 2019
Y2 - 17 June 2019 through 19 June 2019
ER -