Details

Autor(en) / Beteiligte

• Ha, Synh Viet-Uyen
• Nguyen, Tien-Cuong
• Phan, Hung Ngoc
• Ha, Phuong Hoai

Titel

Real-Time Change Detection with Convolutional Density Approximation

Ist Teil von

• Vietnam journal of computer science, 2024

Ort / Verlag

World Scientific Publishing

Erscheinungsjahr

2024

Link zum Volltext

Quelle

EZB Free E-Journals

Beschreibungen/Notizen

• Background Subtraction (BgS) is a widely researched technique to develop online Change Detection algorithms for static video cameras. Many BgS methods have employed the unsupervised, adaptive approach of Gaussian Mixture Model (GMM) to produce decent backgrounds, but they lack proper consideration of scene semantics to produce better foregrounds. On the other hand, with considerable computational expenses, BgS with Deep Neural Networks (DNN) is able to produce accurate background and foreground segments. In our research, we blend both approaches for the best. First, we formulated a network called Convolutional Density Approximation (CDA) for direct density estimation of background models. Then, we propose a self-supervised training strategy for CDA to adaptively capture high-frequency color distributions for the corresponding backgrounds. Finally, we show that background models can indeed assist foreground extraction by an efficient Neural Motion Subtraction (NeMos) network. Our experiments verify competitive results in the balance between effectiveness and efficiency.