Crowd density estimation in still images using multiple local features and boosting regression ensemble.
Muhammad Shahid SaleemMuhammad Jaleed KhanKhurram KhurshidShehzad Muhammad HanifPublished in: Neural Comput. Appl. (2020)
Keyphrases
- image features
- original images
- individual features
- image data
- test images
- multiple classifiers
- ensemble learning
- image database
- salient features
- extracting features
- object recognition
- image regions
- image analysis
- three dimensional
- image registration
- multiple objects
- ensemble methods
- spatial relationships
- feature matching
- extracted features
- feature set
- weak classifiers
- image retrieval
- learning algorithm
- keypoints
- image classification
- input image
- image set
- principal components
- regression model
- weak learners
- gabor filters
- geometric constraints
- training data
- regression problems
- base learners
- combining multiple
- sample images
- feature selection
- image matching
- spatial information
- low level
- random forests
- base classifiers
- multiple features
- image collections
- image content
- model selection
- classification accuracy
- feature vectors
- feature extraction
- gradient boosting