Memory efficient hardware accelerator for kernel support vector machine based pedestrian detection.
Asim KhanChong-Min KyungPublished in: ISOCC (2016)
Keyphrases
- memory efficient
- pedestrian detection
- human body
- field programmable gate array
- object detection
- human detection
- histogram intersection kernel
- occlusion handling
- detection rate
- real time
- benchmark datasets
- crowded scenes
- iterative deepening
- feature space
- histograms of oriented gradients
- hardware implementation
- parallel implementation
- external memory
- support vector
- pedestrian tracking
- embedded systems
- multi class
- face detection
- cascade classifier
- parallel computation
- computer vision
- image processing
- computational complexity
- false positives
- feature vectors