(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Crowd level estimation based on head detection

Crowd level estimation based on head detection / Loh Kah Leong
Pemprosesan imej adalah salah satu istilah yang paling biasa dalam teknologi penglihatan. Secara umum, ia boleh dikelompokkan kepada beberapa kumpulan: memeriksa kehadiran, pengesanan objek dan penyetempatan, pengukuran, pengenalpastian dan pengesahan. Semasa operasi pemprosesan imej, imej input yang diberi adalah input gammbar dan output gambar adalah kualiti tinggi atau lebih banyak gambar maklumat bergantung pada teknik yang digunakan. Pengesanan manusia adalah salah satu bahagian yang paling penting dalam pemprosesan imej. Sistem komputer boleh dilatih oleh algoritma yang berbeza dan selepas memeriksa imej input dapat mengenal pasti manusia dalam gambar input. Pemprosesan imej adalah proses memakan masa, dalam projek ini, kajian ini menyediakan dan menguji algoritma yang paling sesuai digunakan dalam pengesanan manusia yang memberikan masa pemprosesan kurang dan ketepatan tertinggi dalam pengesanan manusia. Dalam bahagian pemprosesan imej Viola Jones Algoritma digunakan untuk mengira bilangan kepala yang dikesan. Algoritma Viola Jones berlari menggunakan MATLAB untuk menguji dan mendapatkan prestasi terbaik. _______________________________________________________________________________________________________ Image processing is one of the most common terms in vision technology. In general, it can be clustered into a few groups: checking for presence, object detection and localization, measurement, identification and verification. In image processing operation, the given input image is the input and the output is the high quality or more information picture depend on technique used. Human detection is one of the most important part in image processing. A computer system can be trained by different algorithm and after checking the input image can identify the number and position of human in the input picture. Image processing is a time consuming process, in this project our study is provides and test the most suitable algorithm used in human detection which provide less processing time and highest accuracy in human detection. In the image processing part Viola Jones Algorithm is the best option for object detection image processing. Haar cascade classifier window are able to detect all the coordinates in the picture with different scale about the possible of human head in the input image. Viola Jones Algorithm is ran using MATLAB to test and obtain the best performance which using the shortest execute time to get the most accuracy result.
Contributor(s):
Loh Kah Leong - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875008604
Language:
English
Subject Keywords:
Image; vision; algorithm
First presented to the public:
6/1/2019
Original Publication Date:
2/26/2020
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 92
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2020-02-26 17:44:04.592
Date Last Updated
2020-12-02 12:20:16.492
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Crowd level estimation based on head detection1 2020-02-26 17:44:04.592