Telekomünikasyon sektöründe kullanılan ek odası kapaklarının sokak düzeyi görüntülerinden tespit edilme başarımının değerlendirilmesi

Abstract

Within the scope of the study, with the proposed method, called innovative method, the manholes used in the telecommunication sector are identified with the deep learning approach from the street-level images and location information of these manholes are produced. In order to evaluate the performance of the innovative method, the results obtained with it in three different study regions located within the borders of the city of Istanbul were compared with the results of the traditional method currently used in the telecommunication sector. During the comparative analysis, the differences between coordinate values of the manholes produced by both methods were determined, the reasons for these differences were emphasized and the possible improvements were discussed. According to the findings, it is concluded that the innovative method cannot replace the traditional method in the current situation. However, if both methods are used together, effectiveness and efficiency in the applications in the telecommunications sector will increase. Nevertheless, in the near future, it is anticipated that the innovative method will replace the traditional method if the suggestions made within the scope of the study are taken into consideration in the solutions of detecting the assets and determining the assets’ coordinates.