Deep Learning-Based Object Detection in Diverse Weather Conditions

The number of different types of composite images has grown very rapidly in current years, making object detection an extremely critical task that requires a deeper understanding of various deep learning strategies that help to detect objects with higher accuracy in less time. A brief description of object detection strategies under various weather conditions is discussed in this paper with their advantages and disadvantages. So, to overcome this, transfer learning has been used and implementation has been done with two pretrained models (i.e., YOLO and Resnet50) with denoising which detects the object under different weather conditions like sunny, snowy, rainy, and hazy. And comparison has been made between the two models. The objects are detected from the images under different conditions where Resnet50 is identified to be the best model.