Improved Mask R-CNN Combined with Otsu Preprocessing for Rice Panicle Detection and Segmentation

Hong, Shilan; Jiang, Zhaohui; Liu, Lianzhong; Wang, Jie; Zhou, Lei; Xu, Jianpeng

doi:10.3390/app122211701

Cited by 17 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ten shooting preset points were deployed in the experimental area. The camera timely captured the fixed point and uploaded it to the FTP server to minimize substantial changes in light intensity caused by direct sunlight [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

A Lightweight Recognition Method for Rice Growth Period Based on Improved YOLOv5s

Liu

Wang²,

Zhang

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The identification of the growth and development period of rice is of great significance to achieve high-yield and high-quality rice. However, the acquisition of rice growth period information mainly relies on manual observation, which has problems such as low efficiency and strong subjectivity. In order to solve these problems, a lightweight recognition method is proposed to automatically identify the growth period of rice: Small-YOLOv5, which is based on improved YOLOv5s. Firstly, the new backbone feature extraction network MobileNetV3 was used to replace the YOLOv5s backbone network to reduce the model size and the number of model parameters, thus improving the detection speed of the model. Secondly, in the feature fusion stage of YOLOv5s, we introduced a more lightweight convolution method, GsConv, to replace the standard convolution. The computational cost of GsConv is about 60–70% of the standard convolution, but its contribution to the model learning ability is no less than that of the standard convolution. Based on GsConv, we built a lightweight neck network to reduce the complexity of the network model while maintaining accuracy. To verify the performance of Small-YOLOv5s, we tested it on a self-built dataset of rice growth period. The results show that compared with YOLOv5s (5.0) on the self-built dataset, the number of the model parameter was reduced by 82.4%, GFLOPS decreased by 85.9%, and the volume reduced by 86.0%. The mAP (0.5) value of the improved model was 98.7%, only 0.8% lower than that of the original YOLOv5s model. Compared with the mainstream lightweight model YOLOV5s- MobileNetV3-Small, the number of the model parameter was decreased by 10.0%, the volume reduced by 9.6%, and the mAP (0.5:0.95) improved by 5.0%—reaching 94.7%—and the recall rate improved by 1.5%—reaching 98.9%. Based on experimental comparisons, the effectiveness and superiority of the model have been verified.

show abstract

Section: Methodsmentioning

confidence: 99%

A Lightweight Recognition Method for Rice Growth Period Based on Improved YOLOv5s

Liu

Wang²,

Zhang

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…When part of the foreground is incorrectly classified as the background or part of the background is misclassified as the foreground, the difference between the two parts becomes smaller. This method is mainly used to identify single targets such as landslides [22,23]. The best threshold selection method for this purpose is OTSU, which reduces the probability of misclassification between the foreground and background through inter-class variance.…”

Section: Principles Of Otsumentioning

confidence: 99%

Automatic Extraction Method of Landslide Based on Digital Elevation Model and Digital Orthophoto Map Data Combined in Complex Terrain

Qiu,

Li,

Wang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This study aims to accurately determine the distribution of landslides in the complex terrain of Jiangdingya, Nanyu Township, Zhouqu County, Gansu Province. The digital orthophoto map (DOM) and digital elevation model (DEM) are used to accurately identify landslide areas and analyze associated data. Based on image-based supervised classification, the influence factor constraint analysis is used to further identify and delineate the landslide area. Three mathematical morphology operations—erosion, dilation, and opening—are then applied to automatically identify and extract landslides. Experimental results demonstrate that achieving an accuracy, precision, and recall of 98.02%, 85.24%, and 84.78% shows that it is possible to better avoid interference caused by complex terrain with rich features. High-resolution DEM and DOM data contain rich spectral and texture information. These data can accurately depict geomorphic features of complex terrain and aid in identifying landslide-prone areas when combined with mathematical morphology processing. This contribution is important for identifying landslides in complex terrain and emergency disaster management.

show abstract

“…Apple dataset preprocesses by applying to resize, background removal, and cropping functions. First, resize all images 64*64 then apply the preprocessing method for background removal first convert the whole dataset into a blue channel then the resultant images convert into grayscale images in the last step of background removal applying another method is Otsu's method (Hong, 2022) for covering the grayscale images into the binary mask. Then crop function on the datasets.…”

Section: Introductionmentioning

confidence: 99%

Classification of Apple Plant Leaf Diseases Using Deep Convolutional Neural Network

Aslam,

Sana,

Kiren

et al. 2024

ABBDM

View full text Add to dashboard Cite

Food production is one of the main sources of income and livelihood in the world. Various agricultural products are grown as essential food in the largest areas of World. According to various research, many agriculture sectors face loss due to crop diseases Plant anthologists find new methods for diagnosing plant diseases perfectly and reliably. Classification of crop diseases is done by using machine learning techniques. Now a day largest no of plant diseases is identified by using deep learning methods. In this work, we use an effective approach that is based on Otsu's thresholding method in preprocessing whereas plant diseases classify by using deep CNN. In this research, we use a benchmark dataset of apple leafs from Kaggle. The method that we use in this research is not applied to apple plants in previous studies. The dataset contains three classes first we apply preprocessing on the dataset which applies three models on these images named 19 layer CNN, AlexNet, and Inception V3 model. Apple dataset preprocesses by applying to resize, background removal, and cropping functions. In the first experiment, we did not preprocess the dataset and directly apply deep CNN on original images and show the behavior of this method on the unclean dataset. On the other hand, in the second experiment first, preprocess datasets and then apply deep CNN for the classification of these diseases. apple leaf diseases are also classified by using AlexNet and the inception V3 model lastly 19 layer CNN is compared with two other models named Alexnet and Inception V3 model both are transfer learning models Results of the AlexNet model is quietly better than the CNN and Inception V3 model is not perform well as compare to both algorithms.

show abstract

Improved Mask R-CNN Combined with Otsu Preprocessing for Rice Panicle Detection and Segmentation

Cited by 17 publications

References 35 publications

A Lightweight Recognition Method for Rice Growth Period Based on Improved YOLOv5s

A Lightweight Recognition Method for Rice Growth Period Based on Improved YOLOv5s

Automatic Extraction Method of Landslide Based on Digital Elevation Model and Digital Orthophoto Map Data Combined in Complex Terrain

Classification of Apple Plant Leaf Diseases Using Deep Convolutional Neural Network

Contact Info

Product

Resources

About