scholarly journals Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi

2019 ◽  
Vol 6 (5B) ◽  
pp. 67-75 ◽  
Author(s):  
Nora Kamarudin ◽  
Nur Anida Jumadi ◽  
Ng Li Mun ◽  
Ng Chun Keat ◽  
Audrey Huong Kah Ching ◽  
...  
Keyword(s):  
Aspect Ratio ◽  
Raspberry Pi ◽  
Cascade Classifier ◽  
Drowsiness Detection ◽  
Driver Drowsiness ◽  
Haar Cascade

scholarly journals Smart Parking Guidance System Using 360o Camera and Haar-Cascade Classifier on IoT System

2019 ◽  
Vol 8 (2S11) ◽  
pp. 864-872 ◽  
Keyword(s):  
Video Processing ◽  
Guidance System ◽  
Raspberry Pi ◽  
Parking Space ◽  
Shopping Malls ◽  
Cascade Classifier ◽  
Parking System ◽  
Parking Lot ◽  
Smart Parking ◽  
Haar Cascade

Nowadays, smart parking guidance system is a crucial research for people’s convenience. The main objective of this research is to develop and analyze on a smart parking guidance system where current available system was compared to this new proposed system. Limited parking space has become serious issue since the number of Malaysia’s populations who are using car keep increasing. Some of the big companies, shopping malls and other public facilities already deployed a smart parking system on their building. However, there are still a lot of buildings that do not own it because the system required a lot of investment, where the huge parking areas need higher cost to install sensors on each parking lot available. The proposed smart parking guidance system in this research was depending on a 360° camera that was modified on raspberry pi camera module and 360o lens and Haar-Cascade classifier. The image and video processing was by Open CV and python program to detect the available parking space and cloud firebase was used to update data where users can access the parking space availability by android mobile phone specifically at a closed parking space. A single 360°camera was replaced several sensors and camera which was implemented on traditional smart parking system. An analysis was done on the performance of the system where it can detect the parking availability with 99.74% accuracy and which is far better than conventional system including reliability and cost for the parking space guidance system.

scholarly journals RANCANG BANGUN APLIKASI NEW NORMAL COVID-19 DETEKSI PENGGUNAAN MASKER MENGGUNAKAN HAAR CASCADE CLASSIFIER

2021 ◽  
Vol 15 (2) ◽  
pp. 199-209
Author(s):  
Ade chandra Saputra ◽  
Ahmadi Ahmadi ◽  
Ariesta Lestari
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Programming Language ◽  
Surveillance System ◽  
Raspberry Pi ◽  
Cascade Classifier ◽  
Public Places ◽  
The Face ◽  
Haar Cascade ◽  
Analysis Design

During the COVID-19 pandemic, when in public places, it is required to apply the 4M health protocol, namely wearing masks, washing hands, maintaining distance, and avoiding crowds. In its implementation, there are officers who always maintain and remind people not to violate health protocols. Like remembering to wear a mask. The mask detection application is made as a computerized surveillance system that can store images of violations of the use of masks and provide warning sounds. Observations, discussions and literature studies are sources of data in this empirical research. Using Python as a programming language assisted with OpenCV for image processing. After passing through the 4 stages of Waterfall, namely Analysis, Design, Manufacturing and Development and Testing, an application is produced where the Raspberry Pi is a processing tool and images are captured from the camera module with a resolution of 1080x1024 px. This application can detect the use of masks with an accuracy of 90.5% using the Machine Learning Haar Cascade Classifier method. Where the condition of the face is a maximum of 30 degrees turned to the side and looked up

scholarly journals Development of a secured room access system based on face recognition using Raspberry Pi and Android based smartphone

2018 ◽  
Vol 197 ◽  
pp. 11008 ◽  
Author(s):  
Asep Najmurrokhman ◽  
Kusnandar Kusnandar ◽  
Arief Budiman Krama ◽  
Esmeralda Contessa Djamal ◽  
Robbi Rahim
Keyword(s):  
Face Recognition ◽  
Raspberry Pi ◽  
Cascade Classifier ◽  
Security Issues ◽  
Access System ◽  
The Face ◽  
Access Control System ◽  
Haar Cascade ◽  
Door Lock ◽  
Access Rights

Security issues are an important part of everyday life. A vital link in security chain is the identification of users who will enter the room. This paper describes the prototype of a secured room access control system based on face recognition. The system comprises a webcam to detect faces and a solenoid door lock for accessing the room. Every user detected by the webcam will be checked for compatibility with the database in the system. If the user has access rights then the solenoid door lock will open and the user can enter the room. Otherwise, the data will be sent to the master user via Android-based smartphone that installed certain applications. If the user is recognized by the master user, then the solenoid door lock will be opened through the signal sent from the smartphone. However, if the user is not recognized, then the buzzer will alert. The main control circuit on this system is Raspberry pi. The software used is OpenCV Library which is useful to display and process the image produced by webcam. In this paper, we employ Haar Cascade Classifier in an image processing of user face to render the face detection with high accuracy.

scholarly journals Pendeteksi Wajah Secara Real Time pada 2 Degree of Freedom (DOF) Kepala Robot Menggunakan Deep Integral Image Cascade

CYCLOTRON ◽  
2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Dwi Agung Ayubi ◽  
Dwi Arman Prasetya ◽  
Irfan Mujahidin
Keyword(s):  
Real Time ◽  
Face Detection ◽  
Humanoid Robot ◽  
Degree Of Freedom ◽  
Raspberry Pi ◽  
Cascade Classifier ◽  
Integral Image ◽  
Haar Cascade ◽  
Time Accuracy ◽  
Face Detector

Abstrak— Teknologi Robot merupakan karya terbaik yang sangat penting bagi kehidupan manusia modern saat ini untuk mempermudah semua pekerjaan manusia. Perkembangan dunia robot saat ini akan difokuskan pada robot yang memiliki fitur mirip manusia. Bahkan diharapkan memiliki kemampuan berinteraksi dan berperilaku seperti manusia yaitu robot humanoid, mekanisme dari gerakan robot humanoid memiliki derajat kebebasan Degree of Freedom (DOF). Layaknya pada manusia robot diberi kemampuan penglihatan untuk mendeteksi adanya objek yang ditangkap secara real time Penelitian kepala robot 2 degree of freedom (DOF) untuk pendeteksi wajah secara real time menggunakan metode Deep Integral Image Cascade untuk deteksi wajahnya. Untuk keakurasian pendeteksi wajah dengan real time pada penelitian ini dengan pengujian akurasi terbesar adalah 95,25% dengan waktu respons pendeteksi tercepat 7 detik dengan waktu terlama 8,55 second rata-rata data citra semuanya tidak terdeteksi dengan benarKata kunci: Raspberry pi, Pendeteksi wajah, Degree of freedom, Haar cascade classifier, Robot kepalaAbstract— Robot technology is the best work that is very important for modern human life today to facilitate all human work. The development of the robot world today will be focused on being a robot that has human-like features. Even expected to have the ability to interact and behave like a humanoid robot, the mechanism of humanoid robot movement has a degree of freedom of Degree of Freedom (DOF). Like in the robot man is given the ability of vision to detect the presence of objects captured in real time robotic head Research 2 degree of freedom (DOF) for face detection in real time using the Deep Integral Image Cascade method to Face Detection.  For the real-time accuracy of the face detector in this research with the greatest precision testing is 95.25% with the fastest detection response time of 7 seconds with the oldest time 8.55 second the average image data everything is not detected with Really.Keywords: Raspberry Pi, face detector, Degree of freedom, Haar Cascade classifier, Robot head

scholarly journals Metode Haar-Cascade Classification Menggunakan Raspberry Pi

MIND Journal ◽  
2018 ◽  
Vol 2 (2) ◽  
pp. 13-22
Author(s):  
Muhammad Ichwan ◽  
Milda Gustiana Husada ◽  
Aldri Helmaputra
Keyword(s):  
Raspberry Pi ◽  
Cascade Classifier ◽  
Integral Image ◽  
Traffic Light ◽  
Haar Cascade

Proses untuk mendeteksi objek dalam citra manggabungkan empat kunci utama yaitu Haar like feature, Integral Image, Adaboost learning dan Cascade Classifier. Metode haar-cascade classification dapat dimanfaatkan sebagai alternatif dalam pengaturan traffic light. Cara kerjanya yaitu, citra yang telah di-capture akan dicocokan dengan data latih, apabila dalam citra tersebut terdapat objek yang sesuai dengan data latih maka objek tersebut di tandai, sehingga objek akan terhitung jumlahnya dengan cara melewati sebuah garis virtual yang dibuat sistem. Dari hasil jumlah objek terdeteksi, sistem dapat mengatur berapa lama lampu merah dan hijau menyala atau mati sesuai dengan jumlah objek yang telah ditentukan. Oleh karena itu, alternatif pengaturan traffic light menggunakan metode Haar-cascade classification digunakan untuk pendeteksian objek. Hasil dari penelitian menggunakan kamera 18 megapiksel 60 FPS jumlah mobil terhitung di garis lebih akurat menggunakan resolusi 480p atau 720p sebesar 79.51%.

scholarly journals Fatigue Detection Using Raspberry Pi 3

2018 ◽  
Vol 7 (2.24) ◽  
pp. 29 ◽  
Author(s):  
Akalya Chellappa ◽  
Mandi Sushmanth Reddy ◽  
R Ezhilarasie ◽  
S Kanimozhi Suguna ◽  
A Umamakeswari
Keyword(s):  
Human Life ◽  
Cloud Service ◽  
Raspberry Pi ◽  
Driver Drowsiness ◽  
Cascade Classifiers ◽  
Physical Injuries ◽  
Warning Message ◽  
Alert Message ◽  
Haar Cascade ◽  
Fatigue Detection

Driver drowsiness is a primary cause of several highway calamities leads to severe physical injuries, loss of money, and loss of human life. The implementation of driver drowsiness detection in real-time will aid in avoiding major accidents. The system is designed for four-wheelers wherein the driver’s fatigue or drowsiness is detected and alerts the person. The proposed method will use 5-megapixel Raspbian camera that captures driver’s face and eyes and processes the images to detect driver’s fatigue. On the detection of drowsiness, the programmed system cautions the driver through an alarm to ensure vigilance. The proposed method constitutes of various stages to determine wakefulness of the driver. According to this output, the warning message is generated. Haar Cascade Classifiers is used to detect the blink duration of the driver and Eye Aspect Ratio (EAR) is calculated. Finally, the alert message along with car plate number is sent to the concerned person mobile with help of Ubidots cloud service and Twilio API. For this Raspberry Pi 3 with Raspbian (Linux Based) Operating System is used.  

scholarly journals PEMANFAATAN RASPBERRY PI SEBAGAI PROCESSOR PADA PENDETEKSIAN DAN PENGENALAN POLA WAJAH

2016 ◽  
Vol 7 (3) ◽  
Author(s):  
Fadli Sirait ◽  
Yoserizal Yoserizal
Keyword(s):  
Discriminant Analysis ◽  
Embedded System ◽  
Face Detection ◽  
Principal Component ◽  
Raspberry Pi ◽  
Cascade Classifier ◽  
Linear Discriminant ◽  
Face Detection And Recognition ◽  
Haar Cascade ◽  
Detection And Recognition

Teknologi biometrik adalah teknologi untuk mengindetifikasi mahluk hidup. Tujuan perancangan  adalah  untuk  membangun  sistem  pendeteksi  wajah  dari  objek  citra  yang  didapat dari  gambar  frame  video  melalui  kamera.  Kemudian  dilakukan  pendeteksi  pola  wajah  yang dikenali  dan  mencari  kemiripan  terhadap  database  model  wajah  menggunakan  Raspberri  Pi berbasis  penggunaan  perangkat  lunak  Free  dan  Opensource.  Perancangan  ini  menggunakan metode  pengenalan  objek  citra  wajah  dengan  Haar  Cascade  Classifier  yang  diimplentasikan pada libarary OpenCV, sedangkan metode pengenalan pola wajah dengan menggunakan analisa PCA (Principal Component Analysist) dan LDA (Linear Discriminant Analysis) menggunakan pemograman  prerangkat  lunak  yang  dibuat  berbasis  Python.  Perangkat  lunak  yang dikembangkan  juga  dijalankan  pada  sistem  operasi  berbasis  Linux  Raspbian  (Jessie  dan Wheezy)  yang  diinstal  di  Raspberry  Pi.  Proses  input  citra  menggunakan  USB  kamera  yang dipasang  pada  Raspberry  Pi  2  Model  B  yang  dilengkapi  dengan  LCD  3,5  inchi.  Berdasarkan data pengujian terhadap 127 input didapat tingkat akurasi untuk pendeteksian satu objek wajah 84-97% sementara performa penggunaan CPU pada Raspberry Pi 41.87-46.25%.Kata kunci: face detection and recognition, Raspberry pi, pengolahan citra, embedded system.

scholarly journals THE CALCULATION SYSTEM OF NUMBER OF PEOPLE IN A ROOM BASED ON HUMAN DETECTION USING HAAR-CASCADE CLASSIFIER

2021 ◽  
Vol 2 (2) ◽  
pp. 75-84
Author(s):  
Gusti Ngurah Rama Putra Atmaja ◽  
Koredianto Usman ◽  
Muhammad Ary Murti
Keyword(s):  
Image Processing ◽  
Computation Time ◽  
Scale Factor ◽  
Human Detection ◽  
Raspberry Pi ◽  
Cascade Classifier ◽  
Final Project ◽  
Object Distance ◽  
Haar Cascade ◽  
Commercial Applications

Data of number of people in the room, calculations are usually carried out by assigning someone to oversee a room. In this final project, a system for calculating the number of people in the room is designed with image processing based on human detection that can be used in rooms, both for commercial applications and for security. This system uses Raspberry Pi device that already has an image processing method Haar-Cascade Classifier.   Input data is in the form of video taken directly via webcam to be captured into a frame so that it   can be used as a input the Haar-Cascade Classifier method and perform the counting process will be sent to the Antares platform. The system design has been tested with five scenarios. Scenario 1 the effect of the distance of the object, scenario 2 the effect of the pose of the object, scenario 3 the effect of the amount the object in the frame, scenario 4 affects the scale factor and scenario 5 measurement computation time. Scenarios 1 to 3 will do the best configuration for minimum neighbour. The system gets the best accuracy of 98,5% when the object distance 4 meters, the best accuracy of 96,6% when the object is facing forward and accuracy the best is 97,7% when the object in the frame is more than two objects with the best configuration use the minimum neighbour 5. Scenario 4 gets accuracy the best is 76,2% when using the scale factor 1.1. Scenario 5 gets the average computation time of the system is under one second, meaning the detection process done pretty fast.

Sign in / Sign up

Export Citation Format

Share Document