2012 24th International Conference on Microelectronics (ICM) 2012
DOI: 10.1109/icm.2012.6471380
|View full text |Cite
|
Sign up to set email alerts
|

HOG based fast human detection

Abstract: International audienceObjects recognition in image is one of the most difficult problems in computer vision. It is also an important step for the implementation of several existing applications that require high-level image interpretation. Therefore, there is a growing interest in this research area during the last years. In this paper, we present an algorithm for human detection and recognition in real-time, from images taken by a CCD camera mounted on a car-like mobile robot. The proposed technique is based … Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0
5

Year Published

2016
2016
2022
2022

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 40 publications
(12 citation statements)
references
References 7 publications
0
7
0
5
Order By: Relevance
“…The HOG algorithm used in this case study has been previously implemented on a variety of computing platforms [44,45,46]. For the sake of this case study we break down the algorithm into 3 tasks: gradient computation, normalisation, and classification.…”
Section: Tasksmentioning
confidence: 99%
See 1 more Smart Citation
“…The HOG algorithm used in this case study has been previously implemented on a variety of computing platforms [44,45,46]. For the sake of this case study we break down the algorithm into 3 tasks: gradient computation, normalisation, and classification.…”
Section: Tasksmentioning
confidence: 99%
“…If computing is placed at the access or routing layers, we can assume a more powerful CPU is available. The work in [46] implements the algorithm on an Intel Core i7 processor. Finally, the cloud layer would use server class processors, such as the Intel Xeon platform used to implement the algorithm in [45].…”
Section: Platformsmentioning
confidence: 99%
“…Memiliki rata-rata akurasi hasil deteksi manusia pada kondisi dalam ruangan adalah 86,1%, sedangkan pada kondisi luar ruangan adalah 88,3%. Sudut orientasi posisi manusia terhadap kamera yang paling baik adalah pada sudut 0 0 , 45 0 , dan 90 0 Metode Histogram of Oriented Gradient merupakan metode feature based yang melihat tampilan lokal dan bentuk obyek pada citra berupa intensitas distribusi gradient atau arah kontur dengan alasan bahwa postur orang yang dideteksi memiliki variasi penampilan [3]. Metode HOG memberikan fleksibilitas yang lebih daripada metode lain, karena metode ini berdasarkan feature ekstraksi yang digunakan pada komputer vision dan pengolahan citra dengan cara menghitung nilai gradien pada suatu citra untuk mendapatkan hasil yang akan digunakan untuk mendeteksi obyek [4].…”
Section: Pendahuluanunclassified
“…Pada desain penelitian ini digunakan metode Histogram of Oriented Gradient (HOG) sebagai metode object detection. Metode HOG merupakan metode feature based yang melihat tampilan lokal dan bentuk objek pada citra berupa intensitas distribusi gradien atau arah kontur [2]. Metode ini menggunakan database berupa histogram yang berisi kumpulan nilai gradien pada sebaran orientasi tertentu.…”
Section: A Histogram Of Oriented Gradientunclassified
“…Jl. Arief Rahman Hakim, Surabaya 60111 e-mail: muhammad_rivai@ee.its.ac.id, fajarbudiman@ee.its.ac.id P A-111 tiap sel dibagi menjadi 9 kelompok dalam rentang 0° sampai 180° [2], [3]. Kemudian besaran gradien piksel akan dijumlahkan pada setiap kelompok.…”
Section: ) Pengelompokan Orientasiunclassified