Loading [a11y]/accessibility-menu.js
Simple background subtraction constraint for weakly supervised background subtraction network | IEEE Conference Publication | IEEE Xplore

Simple background subtraction constraint for weakly supervised background subtraction network


Abstract:

Recently, background subtraction based on deep convolutional neural networks has demonstrated excellent performance in change detection tasks. However, most of the report...Show More

Abstract:

Recently, background subtraction based on deep convolutional neural networks has demonstrated excellent performance in change detection tasks. However, most of the reported approaches require pixel-level label images for training the networks. To reduce the cost of rendering pixel-level annotation data, weakly supervised learning approaches using frame-level labels have been proposed. These labels indicate if a target class is present. Frame-level supervised learning is challenging because we cannot use location information for training the networks. Therefore, some constraints are introduced for guiding foreground locations. Previous works exploit prior information on foreground sizes and shapes. In this work, we propose two constraints for weakly supervised background subtraction networks. Our constraints use binary mask images generated by simple background subtraction. Unlike previous works, our approach does not require prior information on foreground sizes and shapes. Moreover, our constraints are more suitable for change detection tasks. We also present an experiment verifying that our constraints can improve foreground detection accuracy compared to other methods, which do not include them.
Date of Conference: 18-21 September 2019
Date Added to IEEE Xplore: 25 November 2019
ISBN Information:

ISSN Information:

Conference Location: Taipei, Taiwan

Contact IEEE to Subscribe

References

References is not available for this document.