Abstract
Accurate rooftop detection from historical aerial imagery is vital for examining long-term urban development and human settlement patterns. However, black-and-white analog photographs pose significant challenges for modern object detection frameworks due to their limited spatial resolution, lack of color information, and archival degradation. To address these limitations, this study introduces a two-stage image enhancement pipeline based on Generative Adversarial Networks (GANs): image colorization using DeOldify, followed by super-resolution enhancement with Real-ESRGAN. The enhanced images were then used to train and evaluate rooftop detection models, including Faster R-CNN, DETReg, and YOLOv11n. Results show that combining colorization with super-resolution substantially improves detection performance, with YOLOv11n achieving a mean Average Precision (mAP) exceeding 85%. This reflects an improvement of approximately 40% over original black-and-white images and 20% over images enhanced through colorization alone. The proposed method effectively bridges the gap between archival imagery and contemporary deep learning techniques, enabling more reliable extraction of building footprints from historical aerial photographs.
Abstract (translated)
从历史航拍图像中准确检测屋顶对于考察长期城市发展和人类居住模式至关重要。然而，黑白胶片照片由于其有限的空间分辨率、缺乏颜色信息以及档案退化等问题，给现代物体检测框架带来了重大挑战。为了解决这些问题，本研究引入了一种基于生成对抗网络（GAN）的两阶段图像增强管道：首先使用DeOldify进行图像着色，然后采用Real-ESRGAN进行超分辨率增强。经过这些处理后的图像被用来训练和评估屋顶检测模型，包括Faster R-CNN、DETReg 和 YOLOv11n。实验结果显示，将着色与超分辨率相结合可以显著提高检测性能，其中YOLOv11n的平均精度均值（mAP）超过了85%。这比原始黑白图像提高了约40%，相比仅通过着色增强的图像也提升了20%。本方法有效地弥合了档案影像和现代深度学习技术之间的差距，使得从历史航拍照片中可靠地提取建筑轮廓成为可能。
URL
https://arxiv.org/abs/2503.23200
