The automatic Vehicle Detection in Various Weather Conditions (VDVWC) challenge is a dynamic competition integrated into ICDEC 2024 to foster innovation and collaboration among undergraduate and post-graduate students and researchers. The main objective of this competition was to establish a benchmark for evaluating and comparing the effectiveness of machine learning and deep learning-based vehicle detection algorithms using standard evaluation metrics such as mean Average Precision (mAP). In line with this objective, the competition aimed to drive significant advancements in object detection technology and methodology, particularly under various adverse weather and lighting conditions, thereby contributing to the broader field of computer vision. The competition had two challenging rounds, where the participants were stimulated to showcase their skills based on the given criteria. In the first phase, the participants needed to train a model based on our newly developed VDVWC dataset, which contains 3200 images of vehicles in miscellany weather and lighting conditions. The top five performers were selected from Round 1 based on the best mAP score and weightage of their trained models. Subsequently, in the second round, the top participants needed to submit an architectural design of their models along with a brief description. This report provides comprehensive details about the competition, including information about the dataset, the evaluation measures, and a brief description of each submitted method. Challenge details can be found at https://sites.google.com/view/vdvwc/home and the entire dataset can be found at https://github.com/Sourajit-Maity/juvdv2-vdvwc .