林业工程学报，2022,7(2) ： 135-142 Journal of Forestry Engineering DOI : .2096- 基于M-stacked logs using the Mask Region-based Convolutional Neural Network (Mask R-CNN) instance segmentation model is proposed to explore how the instance segmentation model can be used in scenes of dense-stacked logs. The feasibility of dividing stacked logs of various si zes is expected to realize the intelligent measurement of log diameters, improve the efficiency of log diameter meas urements and reduce the cost of measurement. In this dense-stacked logs detection and segmentation task, the difficulty lies in the detection of dense-stacked small logs and large logs. Due to the poor performance of the original Mask R-CNN model in detection and segmentation of dense-stacked small log and large log targets, this study optimi zes the model parameters on the basis of the original Mask R-CNN model in four aspects, including multi-scale train ing of the input image size model, increasing the sample number of the model Region proposal network and Region based Convolutional Neural Network modules, increases the input size of the model training image, and performs ef fective data augmentation on the training images. In view of these four optimization methods and other log detection
