<p>Detecting objects in computer vision is a challenging task, especially under varied weather conditions such as rain, fog, snow, etc. which degrades the visibility, and illumination changes in the image. These conditions create specific challenges in object detection in recognizing the distinct objects in the image. The influence of changing weather conditions remains the cause for concern although deep learning has revolutionized object detection through multi-stage detectors that offer improved accuracy over one-stage detectors, which allow rapid inference. This survey offers a comprehensive exploration of the various object detection methods, and datasets, and emphasizes the challenges posed under the challenging weather conditions. By analyzing current methodologies in object detection and identifying gaps in existing research, this paper provides the limitations under the weather conditions and highlights the research opportunities under weather conditions for the development of better object detection methods that can be suitable for surveillance applications.</p>