Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model
Lentinula edodes logs are susceptible to sundry bacteria contamination during the culture process, and the manual identification of contaminated logs is difficult, untimely, and inaccurate. Aiming to solve this problem, this paper proposes a method for the identification of contaminated Lentinula ed...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/9/2121 |
| _version_ | 1827664433030103040 |
|---|---|
| author | Dawei Zu Feng Zhang Qiulan Wu Cuihong Lu Weiqiang Wang Xuefei Chen |
| author_facet | Dawei Zu Feng Zhang Qiulan Wu Cuihong Lu Weiqiang Wang Xuefei Chen |
| author_sort | Dawei Zu |
| collection | DOAJ |
| description | Lentinula edodes logs are susceptible to sundry bacteria contamination during the culture process, and the manual identification of contaminated logs is difficult, untimely, and inaccurate. Aiming to solve this problem, this paper proposes a method for the identification of contaminated Lentinula edodes logs based on the deep learning model Ghost–YOLOv4. Firstly, a data set of Lentinula edodes log sundry bacteria contamination was constructed. Secondly, in view of the problems that the YOLOv4 network parameters are too large and that the detection speeds of Lentinula edodes log videos are slow, the backbone feature extraction network was replaced with a lightweight network, GhostNet, and the YOLOv4 enhancement feature extraction network PANet and the Yolo Head modules were completed. The modification of the network reduced the number of parameters of the network and improved the detection speed of the network. Finally, the feature extraction network introduced the migration learning pre-training model, which reduced the computational pressure and overfitting problems of the model and further improved the performance of the Ghost–YOLOv4 network. Not only did the constructed Ghost–YOLOv4 ensure the accuracy of the identification and detection of Lentinula edodes log sundry bacteria contamination, but it also had better results in detection speed and real-time performance, and it provides an effective solution for the lightweight deployment of a target detection model on embedded equipment in culture sheds. |
| first_indexed | 2024-03-10T00:59:59Z |
| format | Article |
| id | doaj.art-bf06fba58ff44c82941bf6c8edfb906a |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T00:59:59Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-bf06fba58ff44c82941bf6c8edfb906a2023-11-23T14:37:42ZengMDPI AGAgronomy2073-43952022-09-01129212110.3390/agronomy12092121Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning ModelDawei Zu0Feng Zhang1Qiulan Wu2Cuihong Lu3Weiqiang Wang4Xuefei Chen5School of Information Science & Engineering, Shandong Agricultural University, Tai’an 271018, ChinaSchool of Information Science & Engineering, Shandong Agricultural University, Tai’an 271018, ChinaSchool of Information Science & Engineering, Shandong Agricultural University, Tai’an 271018, ChinaSchool of Information Science & Engineering, Shandong Agricultural University, Tai’an 271018, ChinaSchool of Information Science & Engineering, Shandong Agricultural University, Tai’an 271018, ChinaSchool of Information Science & Engineering, Shandong Agricultural University, Tai’an 271018, ChinaLentinula edodes logs are susceptible to sundry bacteria contamination during the culture process, and the manual identification of contaminated logs is difficult, untimely, and inaccurate. Aiming to solve this problem, this paper proposes a method for the identification of contaminated Lentinula edodes logs based on the deep learning model Ghost–YOLOv4. Firstly, a data set of Lentinula edodes log sundry bacteria contamination was constructed. Secondly, in view of the problems that the YOLOv4 network parameters are too large and that the detection speeds of Lentinula edodes log videos are slow, the backbone feature extraction network was replaced with a lightweight network, GhostNet, and the YOLOv4 enhancement feature extraction network PANet and the Yolo Head modules were completed. The modification of the network reduced the number of parameters of the network and improved the detection speed of the network. Finally, the feature extraction network introduced the migration learning pre-training model, which reduced the computational pressure and overfitting problems of the model and further improved the performance of the Ghost–YOLOv4 network. Not only did the constructed Ghost–YOLOv4 ensure the accuracy of the identification and detection of Lentinula edodes log sundry bacteria contamination, but it also had better results in detection speed and real-time performance, and it provides an effective solution for the lightweight deployment of a target detection model on embedded equipment in culture sheds.https://www.mdpi.com/2073-4395/12/9/2121crop disease monitoringprecision agricultureartificial intelligenceGhost–YOLOv4 |
| spellingShingle | Dawei Zu Feng Zhang Qiulan Wu Cuihong Lu Weiqiang Wang Xuefei Chen Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model Agronomy crop disease monitoring precision agriculture artificial intelligence Ghost–YOLOv4 |
| title | Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model |
| title_full | Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model |
| title_fullStr | Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model |
| title_full_unstemmed | Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model |
| title_short | Sundry Bacteria Contamination Identification of Lentinula Edodes Logs Based on Deep Learning Model |
| title_sort | sundry bacteria contamination identification of lentinula edodes logs based on deep learning model |
| topic | crop disease monitoring precision agriculture artificial intelligence Ghost–YOLOv4 |
| url | https://www.mdpi.com/2073-4395/12/9/2121 |
| work_keys_str_mv | AT daweizu sundrybacteriacontaminationidentificationoflentinulaedodeslogsbasedondeeplearningmodel AT fengzhang sundrybacteriacontaminationidentificationoflentinulaedodeslogsbasedondeeplearningmodel AT qiulanwu sundrybacteriacontaminationidentificationoflentinulaedodeslogsbasedondeeplearningmodel AT cuihonglu sundrybacteriacontaminationidentificationoflentinulaedodeslogsbasedondeeplearningmodel AT weiqiangwang sundrybacteriacontaminationidentificationoflentinulaedodeslogsbasedondeeplearningmodel AT xuefeichen sundrybacteriacontaminationidentificationoflentinulaedodeslogsbasedondeeplearningmodel |