J. Imaging, Volume 4, Issue 6 (June 2018) – 10 articles
Cover Story (view full-size image): Deep neural network-based background subtraction (DNN-BS) has demonstrated excellent performance for change detection. However, previous works fail to detail why DNN-BSs work well. This discussion helps to improve DNN-BSs. For investigation of DNN-BSs, we observed feature maps in all layers of a DNN-BS directly, and we found important filters for the detection accuracy by removing specific filters from the DNN-BS. From the analysis, we found that the DNN-BS consists of subtraction operations in convolutional layers and thresholding operations in bias layers and scene-specific filters are generated to suppress false positives from dynamic backgrounds. View Paper here.
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
- You may sign up for e-mail alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.