TY - GEN
T1 - Weakly Supervised Road Garbage Quantification System Based on WCCA
AU - Fan, Rongbo
AU - Fan, Xiaobo
AU - Sun, Hongliang
AU - Chen, Jun
AU - Yang, Jianhua
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/7/29
Y1 - 2022/7/29
N2 - Mechanized road sweeping vehicles are an indispensable part of urban infrastructure. However, while improving work efficiency, the high energy consumption and noise pollution of their high-power dust collectors have become new problems that need to be solved. To achieve adoptive control of dust collection power, we propose a vision-based road sweeper intelligent power control system. The system use the proposed Weight Criss-Cross Attention (WCCA) module, embed into the Mobile V2 light-weight image-level classification network, to achieve weakly supervised pixel-by-pixel segmentation of road garbage area, and finally get the road garbage quantification result. With the proposed prior loss function based on the distribution of road garbage image data, WCCA can guide the convergence direction of the model to the correct target area. Finally, two state-of -the-art comparison algorithms are used to prove the superiority of the proposed algorithm.
AB - Mechanized road sweeping vehicles are an indispensable part of urban infrastructure. However, while improving work efficiency, the high energy consumption and noise pollution of their high-power dust collectors have become new problems that need to be solved. To achieve adoptive control of dust collection power, we propose a vision-based road sweeper intelligent power control system. The system use the proposed Weight Criss-Cross Attention (WCCA) module, embed into the Mobile V2 light-weight image-level classification network, to achieve weakly supervised pixel-by-pixel segmentation of road garbage area, and finally get the road garbage quantification result. With the proposed prior loss function based on the distribution of road garbage image data, WCCA can guide the convergence direction of the model to the correct target area. Finally, two state-of -the-art comparison algorithms are used to prove the superiority of the proposed algorithm.
KW - Road Waste Quantification
KW - Sweeping Vehicles
KW - Weakly Supervised
UR - http://www.scopus.com/inward/record.url?scp=85137899681&partnerID=8YFLogxK
U2 - 10.1145/3549179.3549187
DO - 10.1145/3549179.3549187
M3 - 会议稿件
AN - SCOPUS:85137899681
T3 - ACM International Conference Proceeding Series
SP - 42
EP - 47
BT - Proceedings - 2022 4th International Conference on Pattern Recognition and Intelligent Systems, PRIS 2022
A2 - Zhao, Wenbing
PB - Association for Computing Machinery
T2 - 4th International Conference on Pattern Recognition and Intelligent Systems, PRIS 2022
Y2 - 29 July 2022
ER -
