基于关键点检测的指针仪表读数算法

通过摄像头实现指针式仪表自动读数时易受复杂环境、摄像头不同角度等因素影响，而且在实际的应用中难以均衡检测速度和检测精度，为此，文章提出一种基于关键点检测的指针仪表读数算法。以ResNet18为主干网络，摒弃了最后两个阶段的残差块以及之后的全连接层，并针对指针仪表表盘的特点设计了一个轻量级特征融合网络，同时引入提高模型性能的姿态修正机(pose refine machine, PRM)。最后利用得到的表盘圆心、零刻度线、当前指针刻度3个关键点信息，通过角度法完成读数计算。实验结果表明，本文算法读数误差仅为0.506%,速度可达53 fps,相比于传统算法具有较高的精确度；相比于其他同类算法，在拥有更少参数量与运算复杂度的情况下，仍能实现对指针关键点的高准确度预测，充分证明所提算法的有效性。

Pointer meter reading algorithm based on key point detection

The automatic reading of pointer instrument by camera is easily affected by complex environment, different camera angles andother factors, and it is difficult to balance the detection speed and detection accuracy in practical applications. Therefore, this paperproposes a pointer instrument reading algorithm based on key point detection. ResNet18 is used as the backbone network, the residualblocks in the last two stages and subsequent fully connected layers are abandoned, and a lightweight feature fusion network is designedaccording to the characteristics of the pointer meter panel, while introducing a pose refine machine ( PRM) that improves modelperformance. Finally, using the obtained three key point information of the dial circle center, the zero scale line, and the current pointerscale, the reading calculation is completed by the angle method. The experimental results show that, the reading error of the algorithm inthis paper is only 0. 506%, and the speed can reach 53 frames/ second, which is more accurate than the traditional algorithm; comparedwith other similar algorithms, the proposed algorithm can still achieve high accuracy prediction of pointer key points with fewerparameters and computational complexity, fully proving the effectiveness of the proposed algorithm.