Aiming at the problem that the workload of human judgment of the power line tilt angle is large and prone to large errors, this paper proposes an improved algorithm Line-YOLO based on YOLOv8s-seg. Firstly, the problem of the variable shape of the power line is solved through the introduction of deformable convolutional DCNv4, and the detection accuracy is improved. The BiFPN structure is also introduced for the Neck layer, which shortens the time required for feature fusion and improves the detection efficiency. After that, the EMA attention mechanism module is added behind the second and third C2f modules of the original model, which improves the model’s ability to recognize the target, and effectively solves the problem of loss and error when power line targets overlap. Finally, a small target detection head is added after the first EMA attention mechanism module for detecting small or occluded targets in the image, which improves the model’s ability to detect small targets. In this paper, we conduct experiments by collecting relevant power line connection images and making our dataset. The experimental results show that the $mAP@0.5$ of Line-YOLO is improved by 6.2% compared to the benchmark model, the number of parameters is reduced by 28.2%, the floating-point operations per second is enhanced by 35.3%, and the number of detected frames per second is improved by 14 FPS. It is proved by the experiments that the enhanced model Line-YOLO detects the results better, and it can efficiently complete the power line angle detection task.