Method for real-time online detection of concrete slump range

The invention discloses a method for real-time online detection of a concrete slump range, and relates to the field of concrete slump detection.The method comprises the steps that S1, a complete concrete falling video in a hopper is collected in real time through a camera unit; s2, frame extraction is conducted on the concrete falling videos in the different slump ranges in an equally-spaced mode, so that a plurality of data sets matched with the different slump ranges are constructed; s3, adopting a neural network to carry out classification model construction on each data set image, so that the slump range of the concrete can be detected and classified; and S4, deploying the neural network model constructed in the step S3 in an upper computer so as to perform slump range identification on the concrete image transmitted by the camera unit in real time through the neural network model. According to the application method for detecting the slump range of the concrete online in real time, the slump range of the