Detection of infrared moving small targets from dynamic background based on improved ViBe algorithm

To address the poor adaptability of the ViBe algorithm in dynamic backgrounds, this paper proposes an improved ViBe algorithm incorporating adaptive threshold setting based on dynamic feedback. The algorithm evaluates the dynamic characteristics of a scene by calculating the standard deviation of pixel samples. Subsequently, the dynamic feedback mechanism adaptively adjusts the pixel classification threshold R and the temporal sampling factor ψ(x) according to the assessed scene dynamics. Furthermore, an adaptive background model reinitialization is introduced to resolve issues caused by sudden camera shakes or directional changes. Experimental results demonstrate that, compared to existing algorithms, the proposed algorithm significantly enhances pixel classification accuracy and the real-time background model updating in diverse scenarios. It also improves the precision of moving target detection, reduces the false detection rates, and increases overall robustness.