2019
DOI: 10.4236/jsea.2019.121001
|View full text |Cite
|
Sign up to set email alerts
|

An FPGA-Based HOG Accelerator with HW/SW Co-Design for Human Detection and Its Application to Crowd Density Estimation

Abstract: Human detection is important in many applications and has attracted significant attention over the last decade. The Histograms of Oriented Gradients (HOG) as effective local descriptors are used with binary sliding window mechanism to achieve good detection performance. However, the computation of HOG under such framework is about billion times and the pure software implementation for HOG computation is hard to meet the real-time requirement. This study proposes a hardware architecture called One-HOG accelerat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(6 citation statements)
references
References 17 publications
0
6
0
Order By: Relevance
“…Unlike most previous work [ 6 , 19 , 20 , 21 , 22 , 23 ], in our design, the flow of the data does not include the processor itself. This is important since in those cases, the processor would be the bottleneck of the system.…”
Section: Results and Comparison With Other Workmentioning
confidence: 99%
See 3 more Smart Citations
“…Unlike most previous work [ 6 , 19 , 20 , 21 , 22 , 23 ], in our design, the flow of the data does not include the processor itself. This is important since in those cases, the processor would be the bottleneck of the system.…”
Section: Results and Comparison With Other Workmentioning
confidence: 99%
“…However, for their pure hardware implementation, they process 1980 × 1020 images and achieve a higher frame rate of 39.6 fps. Huang et al [ 20 ] propose a hardware–software co-design of the algorithm by separating the classification and HOG computation parts. In their design, the HOG generation and computation is done on the FPGA, and the result is sent back to an ARM processor for the classification step.…”
Section: Related Work On Hardware–software Implementationsmentioning
confidence: 99%
See 2 more Smart Citations
“…Luo and Lin [27], and Li et al [36] use the Altera ALTSQRT IP core to calculate the square root function. Huang et al [29] use a Xilinx IP core for square root calculation.…”
Section: B Magnitude Calculationmentioning
confidence: 99%