Abstract: Mushroom maturity is decisive basis for judging whether they are harvesting．Most mushroom breeding bases relies on artificial experience to decide whether mushrooms are mature．This situation not only requires experienced labor but also increases labor intensity．In response to above problems, a mushroom target detection and recognition method based on the Mask R-CNN network was used to divide mushrooms．Experimental results showed that this method could make accurate judgments on whether mushrooms were mature, and it was of great significance to promote intelligent cultivation of mushrooms．