Flying bird detection is important to avoid bird-aircraft collisions for aviation safety. It is a challenging task due to the wide variations in the appearance of flying birds. In order to make up for the shortcomings of human eye surveillance, image detection of birds has become an increasingly important issue in digital image processing. According to the experimental observations, detecting and localizing the birds in the image is hard because it can tackle the conditions wherein the birds shown are diverse in shapes and sizes and most importantly the complex backgrounds, they are in. Deep learning-based methods are very robust for this kind of task. The following article presents a comparison of two deep learning methods architectures: Single S hot Detector + MobilenetV2 and Single Shot Detector + InceptionV2 for detection of birds in the air. We used the training and testing dataset provided by COCO dataset. The results show that MobilenetV2 + SSD outperforms InceptionV2 + SSD in processing time and accuracy.