Application Object Detection Using Histogram of Oriented Gradient For Artificial Intelegence System Module of Nao Robot (Control System Laboratory (LSKK) Bandung Institute of Technology

Saputra A K, Ariani F, Endra R Y


The introduction of the object (object recognition) is one of image processing to identify objects that will be identified for further processing in order to obtain an information data with the existence of the object recognition process. The purpose of this research is to develop intelligent system modules on NAO Robot to build applications that can detect objects around. Testing the accuracy of detection of the algorithm Feature Descriptor Histogram of Oriented Gradient used in building applications for the object detection intelligent system modules on NAO Robot. Results of Design Application Object Detection using the Histogram of Oriented Gradient algorithm can be used to add intelligent system modules on NAO Robot in because of the test results produce a test model tests show a success rate reached 99.10% in identifying the test image. On testing
positive test image, the amount of training data usage greatly affect the object detection process becomes more accurate. In testing the combined image (image test positive and negative) the success rate rose 98.23% to 99.10%.


Image Processing, Computer Vision, Feature Descriptor Algorithm, Histogram of Oriented Gradient, Support Vector Machine, Robot NAO, Artificial Intelegence For Robot.

Full Text:



Linda G. Shapiro & George C. Stockman. 2001. Computer Vision. United States : Prentice Hall.

Navneet Dalal and Bill Triggs. 2003. Histogram of Oriented Gradient for Human Detection. Perancis : INRIA Rhone-Alps, 655 avenue de l’Europe, Montbonnot 38334.

Cristianini & Shawe-Taylor. 2000. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Inggris : Cambridge University Press.


  • There are currently no refbacks.

International Conference on Engineering and Technology Development (ICETD)
Bandar Lampung University
ISSN: 2301-5690