Road defect is one of the most important factors for traffic accident. Therefore, these defects should be corrected as soon as possible. It usually occurs cracks, rutting, and potholes in road surface. These errors are based on the fact that people have recognized and fixed these errors in our day. But if these errors are not corrected in a short time, the size of the error grows day by day. There are various methods used to detect road errors in the literature. One of these methods is the use of computer vision. There are various types of roads in real life. Since the studies in the literature have been carried out only by taking into account one type of road, the accuracy rates decrease when these studies are used in different types of roads. In the study carried out, different roads have been made adaptive by the operations performed in the detection of road errors from the received images. Images taken from the camera on a vehicle are used for the study. The study applied is ensured to have high accuracy rates in different types of roads via customization. In the second stage, the image blurred by using median filter and the unprocessed images are collected, and the darkest parts of the image are brought into the forefront. The image is converted into a binary image and improved by mathematical morphological operations. As a result of the operations performed, which of the five classes including un-cracked roads, superficial crack, crocodile crack, linear crack and transverse crack the roads belong to is determined. In the study carried out, the fact that it is fast and that its accuracy rates are good indicate that it can be used in real life.

No 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.

No abstract

No abstract