Super Resolution Image Acquisition for Object Detection in the Military Industry

Automatic object detection is important in the military industry. Since these objects are small and camouflaged, that is, they are not clear, it becomes even more important that they appear clear and large. Therefore, in order to facilitate object detection algorithms in the field of the military industry, we present a model that obtains high-resolution and high-dimensional images from low-resolution and low-dimensional images. The presented model is a combination of fast super-resolution convolutional neural networks and the VGG16 model, which is widely used in the literature. Due to the limited data in the field of the military industry, the dataset was collected manually from the internet. Our dataset, which has 900 images in total, has been reproduced with certain data augmentation techniques. For model training, low-dimensional images were obtained from the collected high-dimensional images by the bicubic interpolation method. After model training, a BRISQUE score of 47.81 was obtained.