Autonomous cars (ACs) and advanced driver-assistance systems (ADAS) have relied on convolutional neural networks (CNNs) for object detection. However, image degradation caused by adverse weather conditions like rain, snow, and fog can decrease the performance of a CNN. So, this paper presents the development of an image-processing technique aimed to mitigate such a problem. First, after an extensive evaluation of models for object detection, YOLOv3 was chosen because of its compromise between precision and inference time. Afterwards, the training and test of a YOLOv3 CNN was investigated for cars, traffic signals, traffic lights, pedestrians, and riders. Performance was evaluated by estimating the average and mean average precision (mAP) for every one of the mentioned object classes. An OpenCV based pre-processing technique to mitigate the degradation imposed by adverse weather conditions was implemented. Specifically, the OpenCV filters of erosion, dilation and joint bilateral filter were applied during training and tests of the datasets Berkeley DeepDrive (BDD100K) and Detection in Adverse Weather Nature (DAWN). The developed work discusses the benefits of OpenCV filters for data augmentation in training and testing CNNs. Our results show a mAP improvement around 3% in the tests with DAWN.