TY - GEN
T1 - Video-Based Activity Forecasting for Construction Safety Monitoring Use Cases
AU - Tang, Shuai
AU - Golparvar-Fard, Mani
AU - Naphade, Milind
AU - Gopalakrishna, Murali M.
N1 - Publisher Copyright:
© 2019 American Society of Civil Engineers.
PY - 2019
Y1 - 2019
N2 - Forecasting activities of construction workers and equipment is immensely desirable for construction safety management, as it can enable capturing near-miss of accidents and right-time intervention of collision, struck-by, trespassing, and improper use of tools. In this paper, an activity forecasting framework for construction safety management is presented, and an application to forecast workers and equipment's motion trajectory from previously observed motion is implemented. A long short-term memory (LSTM) encoder-decoder network is developed to forecast future locations with mixture density network (MDN) used to model uncertainty in predictions. Two contextual cues are proved to help activity forecasting: (1) worker/equipment placement and distances; (2) object type attributes. A joint training schema is employed to forecast target's locations at different future times. The proposed framework can handle very long sequences (around 2000 steps) well and accurately predict future locations in maximum 40 frames (2 seconds). Our experiment results show that the proposed model significantly outperforms conventional time-series analysis models. In 1080p high-definition videos the final model achieves average localization error in 10, 20, 40 future frames with 7.30, 12.71, and 24.22 pixels, respectively.
AB - Forecasting activities of construction workers and equipment is immensely desirable for construction safety management, as it can enable capturing near-miss of accidents and right-time intervention of collision, struck-by, trespassing, and improper use of tools. In this paper, an activity forecasting framework for construction safety management is presented, and an application to forecast workers and equipment's motion trajectory from previously observed motion is implemented. A long short-term memory (LSTM) encoder-decoder network is developed to forecast future locations with mixture density network (MDN) used to model uncertainty in predictions. Two contextual cues are proved to help activity forecasting: (1) worker/equipment placement and distances; (2) object type attributes. A joint training schema is employed to forecast target's locations at different future times. The proposed framework can handle very long sequences (around 2000 steps) well and accurately predict future locations in maximum 40 frames (2 seconds). Our experiment results show that the proposed model significantly outperforms conventional time-series analysis models. In 1080p high-definition videos the final model achieves average localization error in 10, 20, 40 future frames with 7.30, 12.71, and 24.22 pixels, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85068777384&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068777384&partnerID=8YFLogxK
U2 - 10.1061/9780784482445.026
DO - 10.1061/9780784482445.026
M3 - Conference contribution
AN - SCOPUS:85068777384
T3 - Computing in Civil Engineering 2019: Smart Cities, Sustainability, and Resilience - Selected Papers from the ASCE International Conference on Computing in Civil Engineering 2019
SP - 204
EP - 210
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: Smart Cities, Sustainability, and Resilience, i3CE 2019
Y2 - 17 June 2019 through 19 June 2019
ER -