Design and implementation of image processing system for Lumen social robot-humanoid as an exhibition guide for Electrical Engineering Days 2015
📝 Abstract
Lumen Social Robot is a humanoid robot development with the purpose that it could be a good friend to all people. In this year, the Lumen Social Robot is being developed into a guide in the exhibition and in the seminar of the Final Exam of undergraduate and graduate students in Electrical Engineering ITB, named Electrical Engineering Days 2015. In order to be the guide in that occasion, Lumen is supported by several things. They are Nao robot components, servers, and multiple processor systems. The image processing system is a processing application system that allows Lumen to recognize and determine an object from the image taken from the camera eye. The image processing system is provided with four modules. They are face detection module to detect a person’s face, face recognition module to recognize a person’s face, face tracking module to follow a person’s face, and human detection module to detect humans based on the upper parts of person’s body. Face detection module and human detection module are implemented by using the library harcascade.xml on EMGU CV. Face recognition module is implemented by adding the database for the face that has been detected and store it in that database. Face tracking module is implemented by using the Smooth Gaussian filter to the image. —– Lumen Sosial Robot merupakan sebuah pengembangan robot humanoid agar dapat menjadi teman bagi banyak orang. Sistem pengolahan citra merupakan sistem aplikasi pengolah yang bertujuan Lumen dapat mengenali dan mengetahui suatu objek pada citra yang diambil dari camera mata Lumen. System pengolahan citra dilengkapi dengan empat buah modul, yaitu modul face detection untuk mendeteksi wajah seseorang, modul face recognition untuk mengenali wajah orang tersebut, modul face tracking untuk mengikuti wajah seseorang, dan modul human detection untuk mendeteksi manusia berdasarkan bagian tubuh atas orang
💡 Analysis
Lumen Social Robot is a humanoid robot development with the purpose that it could be a good friend to all people. In this year, the Lumen Social Robot is being developed into a guide in the exhibition and in the seminar of the Final Exam of undergraduate and graduate students in Electrical Engineering ITB, named Electrical Engineering Days 2015. In order to be the guide in that occasion, Lumen is supported by several things. They are Nao robot components, servers, and multiple processor systems. The image processing system is a processing application system that allows Lumen to recognize and determine an object from the image taken from the camera eye. The image processing system is provided with four modules. They are face detection module to detect a person’s face, face recognition module to recognize a person’s face, face tracking module to follow a person’s face, and human detection module to detect humans based on the upper parts of person’s body. Face detection module and human detection module are implemented by using the library harcascade.xml on EMGU CV. Face recognition module is implemented by adding the database for the face that has been detected and store it in that database. Face tracking module is implemented by using the Smooth Gaussian filter to the image. —– Lumen Sosial Robot merupakan sebuah pengembangan robot humanoid agar dapat menjadi teman bagi banyak orang. Sistem pengolahan citra merupakan sistem aplikasi pengolah yang bertujuan Lumen dapat mengenali dan mengetahui suatu objek pada citra yang diambil dari camera mata Lumen. System pengolahan citra dilengkapi dengan empat buah modul, yaitu modul face detection untuk mendeteksi wajah seseorang, modul face recognition untuk mengenali wajah orang tersebut, modul face tracking untuk mengikuti wajah seseorang, dan modul human detection untuk mendeteksi manusia berdasarkan bagian tubuh atas orang
📄 Content
Design and Implementation of Image Processing System for Lumen Social Robot-Humanoid as an Exhibition Guide for Electrical Engineering Days 2015 Setyaki Sholata Sya1, Ary Setijadi Prihatmanto2 #School of Electrical Engineering and informatics, Institut Teknologi Bandung Jalan Ganesha 10, Bandung 40132, Indonesia 1setyaki.s.s@gmail.com 3asetijadi@lskk.ee.itb.ac.id
Abstract— Lumen Social Robot is a humanoid robot development with the purpose that it could be a good friend to all people. In this year, the Lumen Social Robot is being developed into a guide in the exhibition and in the seminar of the Final Exam of undergraduate and graduate students in Electrical Engineering ITB, named Electrical Engineering Days 2015. In order to be the guide in that occasion, Lumen is supported by several things. They are Nao robot components, servers, and multiple processor systems. The image processing system is a processing application system that allows Lumen to recognize and determine an object from the image taken from the camera eye. The image processing system is provided with four modules. They are face detection module to detect a person’s face, face recognition module to recognize a person’s face, face tracking module to follow a person’s face, and human detection module to detect humans based on the upper parts of person’s body. Face detection module and human detection module are implemented by using the library harcascade.xml on EMGU CV. Face recognition module is implemented by adding the database for the face that has been detected and store it in that database. Face tracking module is implemented by using the Smooth Gaussian filter to the image.
Keywords—Lumen, image processing system, face detection, face recognition, face tracking, human detection. I. INTRODUCTION Robot has grown significantly both in function and form. Not only in the world of industry, robots are also developed to be the human’s friend as a social robot. According to Hegel et al, a robot can be called a social robot if it has an appearance and social function [1]. To be able to have an appearance and social function, social robot needs to have a shape resembling a human body structure commonly which is commonly called a humanoid robot. So the Lumen robot which is one example of a social-humanoid robot can be used as a guide in both indoors and outdoors condition. This paper will explain the implementation and design of an image processing system in the development of a Lumen robot as a guide at an exhibition and seminar of Final undergraduate and graduate students of Electrical Engineering ITB, namely Electrical Engineering Days 2015. Through this image processing system, Lumen will be able to detect people, know the people and recognize them. II. ANALYSIS AND DESIGN SYSTEM A. Robot Nao Lumen robot is a humanoid Nao robot manufactured by the French company named Aldebaran Robotics. Nao has the look of a child with the height of 573 mm and weight of 4.996 kg. Nao has two autofocus camera located on the forehead and mouth and the camera has the ability of 30 fps, 640 * 480 pixels and has a maximum focus of 6 m. Nao also has an API that can process image processing, especially for the detection of a person’s face. The API module named ALFaceDetection. The module can also store data of the detected faces to Nao’s memory in order to Nao can recognize the faces and perform the repeating detection.
Figure 1. Spesification of Nao’s Camera
Image processing system in Lumen does not use API Nao because of the limited ability in image processing in API and the limited internal memory in saving the face database through this API command. B. Emgu CV Emgu CV is a cross-platform image processing library. Emgu CV is closely related to OpenCV because Emgu CV is a .NET wrapper for OpenCV or it can be said that Emgu CV is OpenCV in .NET. The language of the program in Emgu CV is C #, VB, IronPython and VC ++. Emgu CV can also be used in Linux, Windows, Mac OS X, and various types of mobile as Android, iPhone, iPod Touch, and iPad.
Figure 2 Platform Emgu CV
One advantage of using Emgu CV in performing image processing is that there are lots of library xml that are much related to image processing. The Xml library used in this detection is haar_cascade_face.xml for detecting people’s faces and haar_cascade_upperbody.xml to detect the people. C. Haar Cascade Face detection is based on the identifying and finding the location of the human face image in a picture regardless of the size, position, and condition (Padmaja & Prabakar, 2012). This also applies in the detection of a person based on the detection of the upper body.
Figure 3 Flow Chart Method Haar Cascade
Haar cascade has 4 main concepts in conducting the detection, namely Haar Training, Haar Feature, Integral Image, and Cascade Clasifier. Based on Figure 3, the image that we want to detect will be
This content is AI-processed based on ArXiv data.