TY - GEN
T1 - An Efficient Vehicle Counting Method Using Mask R-CNN
AU - Al-Ariny, Zaynab
AU - Abdelwahab, Mohamed A.
AU - Fakhry, Mahmoud
AU - Hasaneen, El Sayed
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - In this paper, an accurate approach for vehicle counting in videos using Mask R-CNN and KLT tracker is proposed. Vehicle detection is performed for each N frames using Mask R-CNN instance segmentation model. This model outperforms other deep learning models that using bounding box detection as it provides a segmentation mask for each detected object, the outperformance comes up clearly in cases of occlusions. Once the objects are detected, their corner points are extracted and tracked. An efficient method is introduced to assign point trajectories to their corresponding detected vehicles. The proposed counting algorithm distinguishes precisely between the new vehicles and the counted ones. The experiments performed on diverse challenging videos show excellent results compared to state-of-The-Art counting methods.
AB - In this paper, an accurate approach for vehicle counting in videos using Mask R-CNN and KLT tracker is proposed. Vehicle detection is performed for each N frames using Mask R-CNN instance segmentation model. This model outperforms other deep learning models that using bounding box detection as it provides a segmentation mask for each detected object, the outperformance comes up clearly in cases of occlusions. Once the objects are detected, their corner points are extracted and tracked. An efficient method is introduced to assign point trajectories to their corresponding detected vehicles. The proposed counting algorithm distinguishes precisely between the new vehicles and the counted ones. The experiments performed on diverse challenging videos show excellent results compared to state-of-The-Art counting methods.
UR - http://www.scopus.com/inward/record.url?scp=85083565933&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083565933&partnerID=8YFLogxK
U2 - 10.1109/ITCE48509.2020.9047800
DO - 10.1109/ITCE48509.2020.9047800
M3 - Conference contribution
AN - SCOPUS:85083565933
T3 - Proceedings of 2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020
SP - 232
EP - 237
BT - Proceedings of 2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 International Conference on Innovative Trends in Communication and Computer Engineering, ITCE 2020
Y2 - 8 February 2020 through 9 February 2020
ER -