基于Ghost-YOLACT的输电线路巡检中瓷瓶裂缝检测

Porcelain Bottle Crack Detection for Transmission Lines Insepction Based on Ghost-YOLACT

电路故障巡检中,瓷瓶裂缝的检测需要达到实时语义要求,并且要根据裂缝长度判别裂缝严重程度。针对上述问题,本文采用实例分割模型YOLACT,将其骨架网络替换成GhostNet,提出Ghost-YOLACT模型,将其应用于输电线路巡检中瓷瓶裂缝检测。实验结果表明,本文提出的方法在自然场景中的裂缝描绘中具有很好的性能,为电路上识别电器部件损坏提供了参考。

In circuit fault inspection,the detection of porcelain bottle crack needs to achieve real-time semantic understanding,and the severity of the crack must be judged according to the length of the crack.To slove the above problems,we adopt instance segmentation model YOLACT,and replace the skeleton network with GhostNet.We propose the Ghost-YOLACT and apply to the crack detection of porcelain bottle.The experimental results show that the method proposed in this paper has good performance in the description of cracks in natural scenes,and provides a reference for identifying electrical component damage on the circuit.