Testing Method of Mushroom Maturity Based on Mask R-CNN
-
摘要:
蘑菇成熟度是判断蘑菇是否可采摘的决定性依据,当前大多数蘑菇培育基地都是依靠人工经验判断蘑菇是否成熟,这不仅对人工经验要求极高,而且增加了劳动强度。针对上述问题,研究了一种基于Mask R-CNN网络的蘑菇目标检测及识别方法,对蘑菇进行单体分割从而判断其成熟度。试验结果表明,该方法能对蘑菇是否成熟做出准确判断,对推广蘑菇的智能化种植具有重要意义。
-
关键词:
- 深度学习 /
- 目标检测 /
- Mask R-CNN /
- 蘑菇成熟度
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.
-
Keywords:
- deep learning /
- target detection /
- Mask R-CNN /
- mushroom maturity
-
表 1 蘑菇目标检测统计结果
Table 1. Detection statistics of mushroom target
网络名称 平均单图检测时间/s 准确率/% Faster R-CNN 0.42 89.6 Mask R-CNN 1.73 95.1 -
[1] LECUN Y, BENGIO Y, HINTON G.Deep learning[J].Nature, 2015, 521(7 553): 436-444. [2] DIAS P A,TABB A,MDEDIROS H.Apple flower detection using deep convolutional networks[J].Computers in Industry,2018(99):17-28. [3] HABARAGAMUWA H,OGAWA Y,SUZUKI T,et al.Detecting greenhouse strawberries (mature and immature),using deep convolutional neural network[J].Engineering in Agriculture,Environment and Food,2018,11(3):127-138. [4] GIRSHICK R, DONAHUE J, DARRELL T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition, 2014: 580-587. [5] SA I,GE Z,DAYOUB F,et al.Deepfruits:a fruit detection system using deep neural networks[J].Sensors,2016,16(8): 1222. doi: 10.3390/s16081222 [6] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].Advances in Neural Information Processing Systems,2015(28):91-99. [7] 王丹丹,何东健.基于R-FCN深度卷积神经网络的机器人疏果前苹果目标的识别[J].农业工程学报,2019,35(3):156-163. doi: 10.11975/j.issn.1002-6819.2019.03.020WANG Dandan,HE Dongjian.Recognition of apple targets before fruits thinning by robot based on R-FCN deep convolution neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2019,35(3):156-163. doi: 10.11975/j.issn.1002-6819.2019.03.020 [8] DAI J, LI Y, HE K, et al.R-FCN: object detection via region-based fully convolutional networks[C]//Advances in neural information processing systems, 2016: 379-387. [9] SONG Y,GLASBEY C A,HORGAN G W,et al.Automatic fruit recognition and counting from multiple images[J].Biosystems Engineering,2014(118):203-215. [10] HE K, GKIOXARI G, DOLLÁR P, et al.Mask R-CNN[C]//Proceedings of the IEEE international conference on computer vision, 2017: 2 961-2 969. [11] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE international conference on computer vision, 2015: 1 440-1 448.