Image procesing based soccer robot with wireless communication: obtaining multiple robots position and orientation by utilizing high-angle shot of camera = Robot sepakbola berbasis pengolahan citra dengan komunikasi nirkabel: mendapatkan posisi dan orientasi robot menggunakan sudut kamera high-angle

Giorgy, Giorgy (2015) Image procesing based soccer robot with wireless communication: obtaining multiple robots position and orientation by utilizing high-angle shot of camera = Robot sepakbola berbasis pengolahan citra dengan komunikasi nirkabel: mendapatkan posisi dan orientasi robot menggunakan sudut kamera high-angle. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Cover.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (18kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (145kB) | Preview
Preview	Text (TOC) TOC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (183kB) | Preview
Preview	Text (Chapter 1) Chapter 1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (427kB) | Preview
	Text (Chapter 2) Chapter 2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter 3) Chapter 3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter 4) Chapter 4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (4MB)
	Text (Chapter 5) Chapter 5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (361kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (230kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (35MB)

Abstract

This report proposes an alternate method to obtain position and orientation of multiple socer robots in global vision system. The proposed method uses highangle shot of camera as a substitute to bird-eye angle and a specially designed robot markers that contain cues for the detection of the position, the orientation, and the IDs of the robots. Ball detection and movement simulation are also discussed in this report. In this report, perspective transformation is utilized to normalize the perspective arena image obtained from high-angle shot. The robot marker uses 3 cues, which are “marker outer square”, ”ID squares”, and “heading square”. These markers are detected by using contour method with border tracing algorithm and color segmentation. Color segmentation is also used in detecting the position of the ball. For better feature extraction, Polygonal approximation method is applied to the result of the detection. There are four testing phases, which are unit testing, integration testing, system testing, and regression testing. The results of unit testing are: four arenas are detected from four different rooms, the robot detection has an error of 0.86%, and ball detection has an error of 0.4%. Integration testing obtains the global orientation of the robot, which has an error of 1.1%. From the result of system testing, the best camera resolution is 360p with 50% minimum camera brightness. The result of system testing also proves that the application system can be implemented in different rooms and with different camera positions. Regression testing results in modification of the application code when fault or error occurs in the entire testings. In conclusion, the proposed method can be applied as a technique to detect the position and the orientation of soccer robots. / Laporan ini mengusulkan metode alternatif untuk mendapatkan posisi dan orientasi robot-robot sepak bola dalam global vision system. Metode yang digunakan dalam permainan robot sepak bola dengan pendekatan centralized dan hybrid ini menggunakan sudut pandang kamera high-angle sebagai subtitusi bird-eye angle dan desain robot markers yang menggunakan tanda khusus untuk pendeteksian posisi, orientasi, dan ID robot. Hasil kamera high-angle menghasilkan citra arena sepak bola yang berbentuk perpektif yang dinormalisasikan menggunakan metode perspective transformation. Robot marker menggunakan tiga penanda, yaitu “marker outer square”, “ID squares”, dan “heading square”. Penanda - penanda tersebut dideteksi menggunakan metode contour border tracing dan color segmentation. Hasil pendeteksian tersebut digunakan dalam polygonal aproximation untuk menetukan posisi dan orientasi robot. Pengujian dilakukan dalam empat tahap, yaitu unit testing, integration testing, system testing, dan regression testing. Hasil yang didapatkan dari unit testing yaitu arena terdeteksi sebanyak empat kali dari empat ruangan yang berbeda, pendeteksian robot didapatkan error sebesar 0.86%, pendeteksian bola didapatkan error sebesar 0.4%. Hasil yang didapatkan dari integration testing berupa orientasi robot dengan error sebesar 1.1%. System testing menghasilkan resolusi terbaik kamera pada 360p, dengan tingkat cahaya minimal 50%. Hasil dari system testing juga membuktikan bahwa sistem aplikasi dapat diterapkan pada ruangan dan posisi kamera yang berbeda. Regression testing menghasilkan modifikasi program saat terjadinya kesalahan selama keselurhan pengujian. Dapat disimpulkan bahwa metode yang diusulkan dapat digunakan sebagai teknik pendeteksian posisi dan orientasi robot sepak bola.

Actions (login required)

View Item