کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Object Detection enhancement based on Super-Resolution Mapping

نویسندگان :

Danial Abyazi¹ Dadfar Abyazi² Mehran Yazdi³

1- دانشگاه تحصیلات تکمیلی علوم پایه زنجان 2- دانشگاه شیراز 3- دانشگاه شیراز،دانشکده مهندسی برق و کامپیوتر

کلمات کلیدی :

Object detection،Super-Resolution

چکیده :

Object detection, while being a key step in many applications, has remained challenging, mainly due to the different resolutions of objects in an image. On the other hand, Super-Resolution (SR) approaches have recently been developed to improve the resolution of an image. In this paper, we utilize SR to enhance the quality of images before applying them to a detection model and propose a structure where the detection performance is improved. Furthermore, we remove the image noises by SR methods. Comparisons depict the superior visual performance of the proposed method compared to the conventional detection models. We evaluate our proposed method for detection of solar panels in two countries. To this aim, we created a dataset of satellite images needed for implementing detection models. As a result, we can simply evaluate the usage of solar panels in countries.