The embodiment of the invention provides a tomato maturity prediction method and device,
electronic equipment and a storage medium, and relates to the technical field of
artificial intelligence. The method comprises the following steps: acquiring a
color image, one-dimensional near
infrared spectrum data and one-dimensional ultrasonic spectrum data of a tomato; performing
feature extraction on the
color image to obtain a visual
feature vector; converting the one-dimensional near
infrared spectrum data into two-dimensional near
infrared spectrum data, and performing
feature extraction on the two-dimensional near infrared spectrum data to obtain a near infrared spectrum
feature vector; performing
feature extraction on the one-dimensional ultrasonic spectrum data to obtain an ultrasonic
feature vector; based on an attention mechanism, performing
feature fusion on the visual feature vector, the near infrared spectrum feature vector and the ultrasonic feature vector to obtain a target fusion feature vector; and predicting the target fusion feature vector to obtain the maturity. According to the invention, the accuracy of tomato maturity prediction is improved.