Abstract: A cut-point generation method for agricultural pruning includes using a trained artificial intelligence (AI) model to determine whether to remove or retain each of one or more canes of a fruit tree, determining whether or not each of the one or more canes of the fruit tree includes a cut-point, and determining a cut-point location for each of the one or more canes of the fruit tree that is determined to include the cut-point.

Abstract: A method for training an artificial intelligence (AI) model for agricultural pruning includes generating a training group that corresponds to a portion of a fruit tree, generating a training data point based on the training group, and training the AI model using the training data point. The training data point includes a pruning decision for each of one or more canes included in the training group, and a measurement value concerning one or more attributes for each of the one or more canes included in the training group.

Abstract: A method for generating an agricultural cut-point for an agricultural item includes capturing an image of the agricultural item, generating a depth estimation of the agricultural item, segmenting the image of the agricultural item to generate a segmented image that identifies different segments of the agricultural item, detecting an agricultural feature of the agricultural item based on the image of the agricultural item, generating a two-dimensional cut-point based on the segmented image and the agricultural feature, and generating a three-dimensional cut-point based on the two-dimensional cut-point and the depth estimation of the agricultural item.

Abstract: A method for generating an agricultural cut-point for an agricultural item includes capturing an image of the agricultural item, generating a depth estimation of the agricultural item, segmenting the image of the agricultural item to generate a segmented image that identifies different segments of the agricultural item, detecting an agricultural feature of the agricultural item based on the image of the agricultural item, generating a two-dimensional cut-point based on the segmented image and the agricultural feature, and generating a three-dimensional cut-point based on the two-dimensional cut-point and the depth estimation of the agricultural item.