As a flexible and efficient carrier of agricultural environmental information and crop growth information acquisition technology, UAVs have been widely used in agricultural production and scientific research in recent years. UAVs equipped with perceptual imaging equipment have become an important technical means for information acquisition in smart agriculture. Together with ground or underground sensors, they form an integrated air-ground system to provide data support and decision-making basis for intelligent agricultural management. Multi-source information fusion is one of the key technologies to improve the perception ability of UAVs, and its research is of great significance to the application of UAVs. Compared with the acquisition of single information, based on the method of multi-source data fusion, various types of multi-source information are subjected to various operations and processing to extract the characteristic information of the target for analysis and understanding, and finally realize the identification and recognition of the target. The representative related research and solutions for more than 20 years at home and abroad were summarized. Starting from the characteristics of complex background of UAV images, small target, large field of view, and target rotation, recent research on UAV target detection was inducted and analyzed. Finally, the existing problems were discussed, and the future research trend and development direction judgment were given.