The utilization of remote sensing products for vehicle detection through deep learning has gained immense popularity, especially due to the advancement of unmanned aerial vehicles (UAVs). UAVs offer millimeter-level spa- tial resolution at low flight altitudes, which surpasses traditional airborne platforms. Detecting vehicles from very high-resolution UAV data is crucial in numerous applications, including parking lot and highway management, traffic monitoring, search and rescue missions, and military operations. Obtaining UAV data at desired periods allows the detection and tracking of target objects even several times during a day. Despite challenges such as diverse vehicle char- acteristics, traffic congestion, and hardware limitations, the detection task must be executed swiftly and accurately. This study successfully achieved automated detection and instance segmentation of parked and moving vehicles across a large university campus by employing the robust learning capabilities of the You Only Look Once version 7 (YOLOv7) deep learning algorithm. The generation of an ultrahigh-resolution orthomosaic of the university campus was accomplished through photogrammetric processing, employing 20-megapixel aerial images obtained from RGB UAV flights with polyg- onal nadir-view and bundle-grid oblique-view imaging geometries. The vehicle dataset was created by cropping image patches containing vehicle objects from the orthomosaic and manually labeling the boundaries of the vehicle targets using the LabelMe annotation tool. After expanding the dataset by applying data augmentation, the YOLOv7 algorithm was trained and tested using the transfer learning approach. The accuracy metric of precision, recall, and mAP@0.50 scores for the bounding boxes and masks of vehicles were estimated as 99.79, 97.54, and 99.46%, respectively. In addition, the robustness of the trained algorithm was also tested on a short video and ( > 80%) prediction scores were achieved.