Using LFDA to Learn Subset-Haar-Like Intermediate Feature Weights for Pedestrian Detection.
Kai ZangJifeng ShenWankou YangPublished in: IScIDE (2017)
Keyphrases
- pedestrian detection
- feature weights
- human body
- object detection
- feature weighting
- human detection
- detection rate
- benchmark datasets
- distance function
- objective function
- advanced driver assistance systems
- training data
- false positives
- histogram intersection kernel
- data sets
- histograms of oriented gradients
- visual features
- multi class
- feature selection
- computer vision