Sitting posture recognition method based on improved deep residual network

The invention discloses a sitting posture recognition method based on an improved deep residual network, and the method comprises the steps: collecting the pressure value of each point of an array type film pressure sensor in a period of time, and carrying out the weighted average, and obtaining a pressure matrix corresponding to the array type film pressure sensor; inputting the pressure matrix into an upper computer, and carrying out standardization processing; performing cross weighted filtering processing on the standardized pressure matrix to obtain a pressure matrix with a smooth pattern surface; correcting an abnormal extreme value of the pressure matrix with the smooth surface of the graph by adopting an extreme value processing function; and inputting the corrected pressure matrix into a pre-trained CEN-ResNet model, and outputting the confidence of each sitting posture. 本发明公开了基于改进深度残差网络的坐姿识别方法，所述方法包括：采集一段时间内阵列式薄膜压力传感器的各点位压力数值，并做加权平均，得到与阵列式薄膜压力传感器相对应的压力矩阵；将压力矩阵输入到上位机，并标准化处理；对标准化的压力矩阵进行十字加权滤波处理，得到图形表面