Density-Based Multifeature Background Subtraction with Support Vector Machine

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 34; no. 5; pp. 1017 - 1023
• Main Authors: Bohyung Han, Davis, L. S.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.05.2012; IEEE Computer Society
• Subjects: Applied sciences; Artificial intelligence; Background modeling and subtraction; Computational modeling; Computer science; control theory; systems; Convergence; Data processing. List processing. Character string processing; Density functional theory; Exact sciences and technology; Haar-like features; Image color analysis; Kernel; kernel density approximation; Memory organisation. Data processing; Pattern recognition. Digital image processing. Computational geometry; Software; support vector machine; Support vector machines; Vectors; Computer vision; Gradient; Segmentation; Image processing; Video signal; Shadow; Haar-like features; Background modeling and subtraction; Haar function; Spatial variation; Object recognition; Modeling; Search algorithm; Luminance; Subtraction; support vector machine; Scene analysis; Object detection; Vector support machine; Illumination; Generative model; kernel density approximation
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2011.243

Background modeling and subtraction is a natural technique for object detection in videos captured by a static camera, and also a critical preprocessing step in various high-level computer vision applications. However, there have not been many studies concerning useful features and binary segmentation algorithms for this problem. We propose a pixelwise background modeling and subtraction technique using multiple features, where generative and discriminative techniques are combined for classification. In our algorithm, color, gradient, and Haar-like features are integrated to handle spatio-temporal variations for each pixel. A pixelwise generative background model is obtained for each feature efficiently and effectively by Kernel Density Approximation (KDA). Background subtraction is performed in a discriminative manner using a Support Vector Machine (SVM) over background likelihood vectors for a set of features. The proposed algorithm is robust to shadow, illumination changes, spatial variations of background. We compare the performance of the algorithm with other density-based methods using several different feature combinations and modeling techniques, both quantitatively and qualitatively.