The bird nests on transmission lines can pose a threat to the safe operation of power equipment and even affect the stability of the whole power system. To address the problem of poor applicability of transmission line bird nest detection methods in complex scenarios, an improved YOLOv5-based transmission line bird nest detection method is proposed in this paper. This method first designs a feature balancing network by combining a channel attention and spatial attention mechanism, and uses channel weights and spatial weights as a guide to achieve the balance of semantic and spatial information between features in different levels of the detection network. To avoid the continuous weakening of the feature information because of the increase of network layers, a feature enhancement module is proposed to capture the channel and location information related to the bird nest. Finally, transmission line UAV inspection images are used to build a bird nest dataset for training and testing. The experimental results show that the proposed transmission line bird nest detection method has strong generalization capability and applicability, and also provides technical reference for power image defect detection. This work is supported by the National Natural Science Foundation of China (No. 62102373, No. 61873246, No. 62072416 and No. 62006213).