Get all the updates for this publication
Crowd density as dynamic texture: behavior estimation and classification
Extracting crowd feature is a key step for crowd density estimation. This paper proposes a simple and novel approach of preprocessing and extraction of crowd feature. A 5 × 5 mask is defined for finding isolated components in the image, which proved very efficient for classification of crowd density. SVM classifier is used for classifying the crowd in five different levels. The proposed method is powerful to understand crowd behavior such as crowd coming toward camera and exiting from the camera site. The results are analyzed for PETS dataset and are very promising for images that have bright sunlight and shadow frames too. This method can be used for intelligent surveillance system in public places. © Springer Nature Singapore Pte Ltd. 2018.
Journal | Data powered by TypesetInformation and Communication Technology |
---|---|
Publisher | Data powered by TypesetSpringer |
ISSN | 21945357 |
Open Access | No |