An improved cascade R-CNN and RGB-D camera-based method for dynamic cotton top bud recognition and localization in the field

Peng, Song; Chen, Keyi; Zhu, Longfu; Yang, Meng; Ji, Chao; Xiao, Ailing; Jia, Haoyang; Zhang, Jian; Yang, Wanneng

doi:10.1016/j.compag.2022.107442

Cited by 9 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The leaf region contributed more to the segmented images, that is, the extracted classification features were mainly from the leaf. Consequently, this reduced the impact on performance when the model was applied to different plots or different years ( Song et al., 2022 ).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A novel method for maize leaf disease classification using the RGB-D post-segmentation image data

Nan,

Song,

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Maize (Zea mays L.) is one of the most important crops, influencing food production and even the whole industry. In recent years, global crop production has been facing great challenges from diseases. However, most of the traditional methods make it difficult to efficiently identify disease-related phenotypes in germplasm resources, especially in actual field environments. To overcome this limitation, our study aims to evaluate the potential of the multi-sensor synchronized RGB-D camera with depth information for maize leaf disease classification. We distinguished maize leaves from the background based on the RGB-D depth information to eliminate interference from complex field environments. Four deep learning models (i.e., Resnet50, MobilenetV2, Vgg16, and Efficientnet-B3) were used to classify three main types of maize diseases, i.e., the curvularia leaf spot [Curvularia lunata (Wakker) Boedijn], the small spot [Bipolaris maydis (Nishik.) Shoemaker], and the mixed spot diseases. We finally compared the pre-segmentation and post-segmentation results to test the robustness of the above models. Our main findings are: 1) The maize disease classification models based on the pre-segmentation image data performed slightly better than the ones based on the post-segmentation image data. 2) The pre-segmentation models overestimated the accuracy of disease classification due to the complexity of the background, but post-segmentation models focusing on leaf disease features provided more practical results with shorter prediction times. 3) Among the post-segmentation models, the Resnet50 and MobilenetV2 models showed similar accuracy and were better than the Vgg16 and Efficientnet-B3 models, and the MobilenetV2 model performed better than the other three models in terms of the size and the single image prediction time. Overall, this study provides a novel method for maize leaf disease classification using the post-segmentation image data from a multi-sensor synchronized RGB-D camera and offers the possibility of developing relevant portable devices.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In response to this issue, the RGB-D sensors present a practical approach. Specifically, RGB-D cameras can extract target information based on the distance of the object, making it more suitable for segmenting infected maize leaves in complex field environments ( Song et al., 2022 ).…”

Section: Introductionmentioning

confidence: 99%

A novel method for maize leaf disease classification using the RGB-D post-segmentation image data

Nan,

Song,

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…In agricultural settings, for instance, the model has been adapted to perform highly accurate object detection tasks. These include identifying and classifying various agricultural pests, monitoring crop health, and facilitating more efficient and sustainable farming practices [ 20 , 21 ]. Similarly, in industrial contexts, Cascade R-CNN’s enhanced detection capabilities have been pivotal in automating quality control processes, detecting manufacturing defects, and ensuring safety in automated systems [ 22 , 23 ].…”

Section: Related Workmentioning

confidence: 99%

Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer

Xu,

Yu,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Agricultural pests and diseases pose major losses to agricultural productivity, leading to significant economic losses and food safety risks. However, accurately identifying and controlling these pests is still very challenging due to the scarcity of labeling data for agricultural pests and the wide variety of pest species with different morphologies. To this end, we propose a two-stage target detection method that combines Cascade RCNN and Swin Transformer models. To address the scarcity of labeled data, we employ random cut-and-paste and traditional online enhancement techniques to expand the pest dataset and use Swin Transformer for basic feature extraction. Subsequently, we designed the SCF-FPN module to enhance the basic features to extract richer pest features. Specifically, the SCF component provides a self-attentive mechanism with a flexible sliding window to enable adaptive feature extraction based on different pest features. Meanwhile, the feature pyramid network (FPN) enriches multiple levels of features and enhances the discriminative ability of the whole network. Finally, to further improve our detection results, we incorporated non-maximum suppression (Soft NMS) and Cascade R-CNN’s cascade structure into the optimization process to ensure more accurate and reliable prediction results. In a detection task involving 28 pest species, our algorithm achieves 92.5%, 91.8%, and 93.7% precision in terms of accuracy, recall, and mean average precision (mAP), respectively, which is an improvement of 12.1%, 5.4%, and 7.6% compared to the original baseline model. The results demonstrate that our method can accurately identify and localize farmland pests, which can help improve farmland’s ecological environment.

show abstract

“…The ROI Pooling module performs maximum pooling on the target prediction boxes and adjusts it to a fixed size. The target prediction box of fixed size is fed into the fully connected layer and softmax classifier to obtain the prediction box position and classification confidence [26,27].…”

Section: Faster R-cnn Networkmentioning

confidence: 99%

Improved Faster Region-Based Convolutional Neural Networks (R-CNN) Model Based on Split Attention for the Detection of Safflower Filaments in Natural Environments

Zhang,

Shi,

Xing

et al. 2023

Agronomy

View full text Add to dashboard Cite

The accurate acquisition of safflower filament information is the prerequisite for robotic picking operations. To detect safflower filaments accurately in different illumination, branch and leaf occlusion, and weather conditions, an improved Faster R-CNN model for filaments was proposed. Due to the characteristics of safflower filaments being dense and small in the safflower images, the model selected ResNeSt-101 with residual network structure as the backbone feature extraction network to enhance the expressive power of extracted features. Then, using Region of Interest (ROI) Align improved ROI Pooling to reduce the feature errors caused by double quantization. In addition, employing the partitioning around medoids (PAM) clustering was chosen to optimize the scale and number of initial anchors of the network to improve the detection accuracy of small-sized safflower filaments. The test results showed that the mean Average Precision (mAP) of the improved Faster R-CNN reached 91.49%. Comparing with Faster R-CNN, YOLOv3, YOLOv4, YOLOv5, and YOLOv6, the improved Faster R-CNN increased the mAP by 9.52%, 2.49%, 5.95%, 3.56%, and 1.47%, respectively. The mAP of safflower filaments detection was higher than 91% on a sunny, cloudy, and overcast day, in sunlight, backlight, branch and leaf occlusion, and dense occlusion. The improved Faster R-CNN can accurately realize the detection of safflower filaments in natural environments. It can provide technical support for the recognition of small-sized crops.

show abstract

An improved cascade R-CNN and RGB-D camera-based method for dynamic cotton top bud recognition and localization in the field

Cited by 9 publications

References 13 publications

A novel method for maize leaf disease classification using the RGB-D post-segmentation image data

A novel method for maize leaf disease classification using the RGB-D post-segmentation image data

Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer

Improved Faster Region-Based Convolutional Neural Networks (R-CNN) Model Based on Split Attention for the Detection of Safflower Filaments in Natural Environments

Contact Info

Product

Resources

About