Analytics of deep neural network in change detection

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

10 被引用数 (Scopus)

抄録

Recently, deep neural networks (DNNs) have demonstrated excellent performance for change detection. The DNN-based background subtraction automatically discovers background features from datasets and outperforms traditional background modeling based on handcraft features and/or subtraction strategies. Most researchers mainly discuss the accuracy of foreground detection and do not analyze how and why the DNN works well for change detection tasks. It is necessary to understand what the DNN learns as background features in order to discuss the potential of the DNN in background subtraction. In this paper, we focus on the filters in the first convolution layer and the activations of neurons in the last fully connected layer to understand the behavior of the DNN. From the experiment, we found that 1) the first layer performs the role of background subtraction using several filters, and 2) the last layer categorizes some background changes into a group without supervised signals. These findings suggest the possibility of a new background modeling strategy based on data-driven extracted features.

本文言語英語
ホスト出版物のタイトル2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781538629390
DOI
出版ステータス出版済み - 10 20 2017
イベント14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017 - Lecce, イタリア
継続期間: 8 29 20179 1 2017

出版物シリーズ

名前2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017

その他

その他14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017
Countryイタリア
CityLecce
Period8/29/179/1/17

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

フィンガープリント 「Analytics of deep neural network in change detection」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル