A novel low-resource consumption and high-speed hardware implementation of HOG feature extraction on FPGA for human detection.
Yuhai HeJiye HuangYiming PanPublished in: Integr. (2024)
Keyphrases
- hardware implementation
- human detection
- resource consumption
- high speed
- histograms of oriented gradients
- feature extraction
- action recognition
- histogram of oriented gradients
- pedestrian detection
- object detection
- hog features
- field programmable gate array
- signal processing
- human body
- fpga implementation
- resource allocation
- surveillance system
- efficient implementation
- hardware architecture
- dedicated hardware
- hardware design
- background subtraction
- response time
- fpga device
- software implementation
- local binary pattern
- solution quality
- processing times
- image processing algorithms
- data transfer
- low power
- feature selection
- feature set
- feature vectors
- feature space
- general purpose processors
- video surveillance
- pipelined architecture
- query execution
- quality of service
- face detection
- object recognition
- pattern recognition
- real time
- computational complexity
- partial occlusion
- scheduling algorithm
- data acquisition
- multi class
- image processing
- computer vision
- machine learning