Impact of loss functions on semantic segmentation in far-field monitoring

Author(s)

• Wei-Chih Chern, University of Dayton
• Tam V. Nguyen, University of DaytonFollow
• Vijayan K. Asari, University of Dayton
• Hongjo Kim, Yonsei University

Document Type

Article

Publication Date

3-2-2022

Publication Source

Computer-Aided Civil and Infrastructure Engineering

Abstract

Although previous research laid the foundation for vision-based monitoring systems using convolutional neural networks (CNNs), too little attention has been paid to the challenges associated with data imbalance and varying object sizes in far-field monitoring. To fill the knowledge gap, this paper investigates various loss functions to design a customized loss function to address the challenges. Scaffold installation operations recorded by camcorders were selected as the subject of analysis in a far-field surveillance setting. It was confirmed that the data imbalance between the workers, hardhats, harnesses, straps, and hooks caused poor performances especially for small size objects. This problem was mitigated by employing a region-based loss and Focal loss terms in the loss function of segmentation models. The findings illustrate the importance of the loss function design in improving performance of CNN models for far-field construction site monitoring.Although previous research laid the foundation for vision-based monitoring systems using convolutional neural networks (CNNs), too little attention has been paid to the challenges associated with data imbalance and varying object sizes in far-field monitoring. To fill the knowledge gap, this paper investigates various loss functions to design a customized loss function to address the challenges. Scaffold installation operations recorded by camcorders were selected as the subject of analysis in a far-field surveillance setting. It was confirmed that the data imbalance between the workers, hardhats, harnesses, straps, and hooks caused poor performances especially for small size objects. This problem was mitigated by employing a region-based loss and Focal loss terms in the loss function of segmentation models. The findings illustrate the importance of the loss function design in improving performance of CNN models for far-field construction site monitoring.

Inclusive pages

372-390

ISBN/ISSN

1093-9687

Publisher

John Wiley & Sons

Volume

38

Issue

3

eCommons Citation

Chern, Wei-Chih; Nguyen, Tam V.; Asari, Vijayan K.; and Kim, Hongjo, "Impact of loss functions on semantic segmentation in far-field monitoring" (2022). Computer Science Faculty Publications. 230.
https://ecommons.udayton.edu/cps_fac_pub/230