Spatial-channel transformer network based on mask-RCNN for efficient mushroom instance segmentation  

作　　者：Jiaoling Wang Weidong Song Wengang Zheng Qingchun Feng Mingfei Wang Chunjiang Zhao 

机构地区：[1]Northwest Agriculture and Forestry University,Xi’an 712199,China [2]Nanjing Institute of Agricultural Mechanization,Ministry of Agriculture and Rural Affairs,Nanjing 210014,China [3]Intelligent equipment Technology Research Center,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China [4]Zhejiang Provincial Key Laboratory of Agricultural Intelligent Equipment and Roboics/College of Biosystems Engineering and Food Science,Zhejiang University,Hangzhou 310058,China

出　　处：《International Journal of Agricultural and Biological Engineering》2024年第4期227-235,共9页国际农业与生物工程学报（英文）

基　　金：supported by China Agriculture Research System of MOF and MARA(CARS-20);Zhejiang Provincial Key Laboratory of Agricultural Intelligent Equipment and Robotics Open Fund(2023ZJZD2301);Chinese Academy of Agricultural Science and Technology Innovation Project“Fruit And Vegetable Production And Processing Technical Equipment Team”(2024);Beijing Nova Program(20220484023).

摘　　要：Edible mushrooms are rich in nutrients;however,harvesting mainly relies on manual labor.Coarse localization of each mushroom is necessary to enable a robotic arm to accurately pick edible mushrooms.Previous studies used detection algorithms that did not consider mushroom pixel-level information.When these algorithms are combined with a depth map,the information is lost.Moreover,in instance segmentation algorithms,convolutional neural network(CNN)-based methods are lightweight,and the extracted features are not correlated.To guarantee real-time location detection and improve the accuracy of mushroom segmentation,this study proposed a new spatial-channel transformer network model based on Mask-CNN(SCT-Mask-RCNN).The fusion of Mask-RCNN with the self-attention mechanism extracts the global correlation outcomes of image features from the channel and spatial dimensions.Subsequently,Mask-RCNN was used to maintain a lightweight structure and extract local features using a spatial pooling pyramidal structure to achieve multiscale local feature fusion and improve detection accuracy.The results showed that the SCT-Mask-RCNN method achieved a segmentation accuracy of 0.750 on segm_Precision_mAP and detection accuracy of 0.638 on Bbox_Precision_mAP.Compared to existing methods,the proposed method improved the accuracy of the evaluation metrics Bbox_Precision_mAP and segm_Precision_mAP by over 2%and 5%,respectively.

关 键 词：edible mushrooms PICKING instance segmentation deep learning algorithm 

分 类 号：S22[农业科学—农业机械化工程]