Camouflage detection plays a pivotal role in military reconnaissance, where accurately identifying concealed objects can significantly enhance mission success. This paper presents a comparative study of digital imaging and multispectral imaging technologies for detecting camouflaged objects. Utilizing aerial imagery, we evaluated the performance of these imaging methods under various environmental conditions. A robust system was developed to acquire, pre-process, and analyze images for feature extraction, object detection, and classification, employing the YOLOv11 algorithm - a state-of-the-art machine learning technique. Our results reveal the distinct advantages of multispectral imaging in identifying camouflaged targets, particularly under challenging lighting and weather conditions. This study not only demonstrates the superior capabilities of YOLOv11 in processing multispectral data but also provides valuable insights for enhancing reconnaissance accuracy through advanced imaging technologies. The findings have significant implications for military applications and other fields requiring efficient and reliable object detection capabilities.