UAV detection plays a key role in various fields.From the perspective of a UAV,factors such as the size of an object,different background interferences,and lighting will all affect the detection effect,leading to missed or false detection of the object.To solve this problem,a small object detection algorithm is proposed.Firstly,a module of Hybrid Control of Attention-mechanism and Convolution (HCAC）is used to effectively extract contextual details of objects of different scales,directions,and shapes,while associating objects with position information through relative position encoding.Secondly,in view of the small size characteristics of small objects,a high-resolution detection branch is introduced,the large object detection head and its redundant network layers are pruned,and a Multi-level Weighted Feature fusion Network (MWFN) is used for multi-dimensional fusion.Finally,the WIoU loss is used as the bounding box regression loss,combined with the dynamic non-monotonic focusing mechanism,to evaluate the quality of the anchor box,so that the detector can handle anchor boxes of different qualities and improve the overall performance.Experiments were conducted on the UAV aerial photography dataset VisDrone2019.The results showed that,compared with the basic algorithm,the proposed algorithm has its accuracy and mAP increased by 9.0 and 9.8 percentage points respectively,which has better detection results.