An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN
Spike development directly affects the yield and quality of rice. We describe an algorithm for automatically identifying multiple developmental stages of rice spikes (AI-MDSRS) that transforms the automatic identification of multiple developmental stages of rice spikes into the detection of rice spi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2022-10-01
|
Series: | Crop Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2214514122001520 |
_version_ | 1811194717122068480 |
---|---|
author | Yuanqin Zhang Deqin Xiao Youfu Liu Huilin Wu |
author_facet | Yuanqin Zhang Deqin Xiao Youfu Liu Huilin Wu |
author_sort | Yuanqin Zhang |
collection | DOAJ |
description | Spike development directly affects the yield and quality of rice. We describe an algorithm for automatically identifying multiple developmental stages of rice spikes (AI-MDSRS) that transforms the automatic identification of multiple developmental stages of rice spikes into the detection of rice spikes of diverse maturity levels. The scales vary greatly in different growth and development stages because rice spikes are dense and small, posing challenges for their effective and accurate detection. We describe a rice spike detection model based on an improved faster regions with convolutional neural network (Faster R-CNN). The model incorporates the following optimization strategies: first, Inception_ResNet-v2 replaces VGG16 as a feature extraction network; second, a feature pyramid network (FPN) replaces single-scale feature maps to fuse with region proposal network (RPN); third, region of interest (RoI) alignment replaces RoI pooling, and distance-intersection over union (DIoU) is used as a standard for non-maximum suppression (NMS). The performance of the proposed model was compared with that of the original Faster R-CNN and YOLOv4 models. The mean average precision (mAP) of the rice spike detection model was 92.47%, a substantial improvement on the original Faster R-CNN model (with 40.96% mAP) and 3.4% higher than that of the YOLOv4 model, experimentally indicating that the model is more accurate and reliable. The identification results of the model for the heading–flowering, milky maturity, and full maturity stages were within two days of the results of manual observation, fully meeting the needs of agricultural activities. |
first_indexed | 2024-04-12T00:31:22Z |
format | Article |
id | doaj.art-ccf7799a405a464cb05fcb3b01e4bcf9 |
institution | Directory Open Access Journal |
issn | 2214-5141 |
language | English |
last_indexed | 2024-04-12T00:31:22Z |
publishDate | 2022-10-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Crop Journal |
spelling | doaj.art-ccf7799a405a464cb05fcb3b01e4bcf92022-12-22T03:55:20ZengKeAi Communications Co., Ltd.Crop Journal2214-51412022-10-0110513231333An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNNYuanqin Zhang0Deqin Xiao1Youfu Liu2Huilin Wu3College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, Guangdong, ChinaCollege of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, Guangdong, China; Corresponding author.College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, Guangdong, ChinaGuangzhou National Modern Agricultural Industry Science and Technology Innovation Center, Guangzhou 511458, Guangdong, ChinaSpike development directly affects the yield and quality of rice. We describe an algorithm for automatically identifying multiple developmental stages of rice spikes (AI-MDSRS) that transforms the automatic identification of multiple developmental stages of rice spikes into the detection of rice spikes of diverse maturity levels. The scales vary greatly in different growth and development stages because rice spikes are dense and small, posing challenges for their effective and accurate detection. We describe a rice spike detection model based on an improved faster regions with convolutional neural network (Faster R-CNN). The model incorporates the following optimization strategies: first, Inception_ResNet-v2 replaces VGG16 as a feature extraction network; second, a feature pyramid network (FPN) replaces single-scale feature maps to fuse with region proposal network (RPN); third, region of interest (RoI) alignment replaces RoI pooling, and distance-intersection over union (DIoU) is used as a standard for non-maximum suppression (NMS). The performance of the proposed model was compared with that of the original Faster R-CNN and YOLOv4 models. The mean average precision (mAP) of the rice spike detection model was 92.47%, a substantial improvement on the original Faster R-CNN model (with 40.96% mAP) and 3.4% higher than that of the YOLOv4 model, experimentally indicating that the model is more accurate and reliable. The identification results of the model for the heading–flowering, milky maturity, and full maturity stages were within two days of the results of manual observation, fully meeting the needs of agricultural activities.http://www.sciencedirect.com/science/article/pii/S2214514122001520Improved Faster R-CNNRice spike detectionRice spike countDevelopmental stage identification |
spellingShingle | Yuanqin Zhang Deqin Xiao Youfu Liu Huilin Wu An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN Crop Journal Improved Faster R-CNN Rice spike detection Rice spike count Developmental stage identification |
title | An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN |
title_full | An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN |
title_fullStr | An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN |
title_full_unstemmed | An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN |
title_short | An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN |
title_sort | algorithm for automatic identification of multiple developmental stages of rice spikes based on improved faster r cnn |
topic | Improved Faster R-CNN Rice spike detection Rice spike count Developmental stage identification |
url | http://www.sciencedirect.com/science/article/pii/S2214514122001520 |
work_keys_str_mv | AT yuanqinzhang analgorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT deqinxiao analgorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT youfuliu analgorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT huilinwu analgorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT yuanqinzhang algorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT deqinxiao algorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT youfuliu algorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn AT huilinwu algorithmforautomaticidentificationofmultipledevelopmentalstagesofricespikesbasedonimprovedfasterrcnn |