Endüstriyel Sistemlerde Arkaplan Çıkarımı Tabanlı Hareketli Nesne Tespiti ve Sayılması için Yeni Bir Yaklaşım

Abstract

A New Approach for Background Subraction Based Moving Object Detection and Counting in Industrial SystemsABSTRACT: In recent years, computer vision and image processing approaches hold a very important place in industrial control systems. Especially, the computer vision technique used in the quality control of products in a production line has a great importance in terms of controlling of products fast, smoothly and correctly. When it is considered problems brought up by the inspections carried out by conventional methods, the importance of computer vision concept will be understood more clearly. In this study, a new method was proposed for computer vision based quality control. The proposed method records images of products passed on a production line as a video. These products were counted by using high speed image processing techniques. Products passed on a production line were recorded by using a camera with 60 frame per second (fps). In the proposed method, the images taken in the proposed approach are firstly subjected to some morphological operations to reveal the details of the products clearly. Then, moving objects were detected by removing the background with Gaussian mixture model. Then, it is checked whether or not the objects in the determined area have passed, and the process of counting is performed. The contours of the objects are drawn with Convex hull method and it is determined whether multiple objects pass over the area according to the area of the objects. The counting of the products in high speed production line was performed successfully and completely and the experimental results show that the algorithm is effective and accurate results.

FPGA üzerinde görüntü işleme algoritmalarının gerçek zamanlı gerçekleştirilmesi

“…Literatüre sunulan Anusha ve arkadaşları tarafından sunulan bir diğer çalışmada FPGA çipi üzerinde 3 boyutlu Sobel Operatörü ile kenar tespit uygulaması gerçekleştirilmiştir [13]. Karaköse ve arkadaşları tarafından yapılan bir diğer çalışmada, FPGA-tabanlı morfolojik işlem algoritması geliştirilerek nesnelerin tespiti kolaylaştırılmıştır [14]. Aydoğdu ve arkadaşları bu çalışmalarında FPGA üzerine bağladıkları iki kamera yardımıyla köşe tespiti yapmışlardır [15].…”