Recent advances in the application of deep learning methods to forestry

Wang, Yong; Zhang, Wei; Gao, Rui; Zheng, Jiangbin; Wang, Xiaohuan

doi:10.1007/s00226-021-01309-2

Cited by 36 publications

(20 citation statements)

References 131 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current few-shot detection methods can be mainly categorized into data augmentation-based, fine-tuning-based, meta learning-based, and model structure-based approaches [23][24][25][26]. This study utilizes a fine-tuning-based method with Faster R-CNN as the basic framework [27] and incorporates contrastive proposal encoding to improve the model's detection accuracy for surface roughness of workpieces from different machining processes.…”

Section: Few-shot Workpiece Surface Roughness Detection Modelmentioning

confidence: 99%

Few-shot detection of surface roughness of workpieces processed by different machining techniques

Yi,

Lv,

Shu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The traditional deep learning method for detecting workpiece surface roughness relies heavily on a large number of training samples. Also, when detecting the surface roughness of workpieces processed by different machining techniques, it requires a large number of samples of that workpiece to rebuild the model. To address these problems, this paper proposes a few-sample visual detection method for the surface roughness of workpieces processed by different techniques. This method first trains a base model using a relatively large amount of samples from one machining technique, then fine-tunes the model using small amounts of samples from workpieces of different techniques. By introducing contrastive proposal encoding into Faster R-CNN, the model's ability to learn surface features from small amounts of workpiece samples is enhanced, thus improving the detection accuracy of surface roughness of workpieces processed by different techniques. Experiments show that this method reduces the model's dependence on training samples and the cost of data preparation. It also demonstrates higher accuracy in surface roughness detection tasks of workpieces processed by different techniques, providing a new approach and insights for few-sample surface roughness detection.

show abstract

Section: Few-shot Workpiece Surface Roughness Detection Modelmentioning

confidence: 99%

Few-shot detection of surface roughness of workpieces processed by different machining techniques

Yi,

Lv,

Shu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Remote sensing technology has provided data with high spatio-temporal resolution and many spectral bands for forestry research, which allows researchers to use more information to build a model than traditional ways of collecting data in the wild. Due to the ability to gain knowledge from large amounts of train data, artificial intelligence technology represented by deep learning models has also been applied in forestry to accomplish diverse tasks (Wang et al, 2021 ) including tree species classification (Wagner et al, 2019 ) and damage assessment (Hamdi et al, 2019 ; Tao et al, 2020 ). In terms of the data types, most studies in forestry have used deep learning models to analyze remote sensing data (Zhu et al, 2017 ; Diez et al, 2021 ), such as unmanned aerial vehicle (UAV) data (Diez et al, 2021 ; Onishi and Ise, 2021 ), high-resolution satellite images (Li et al, 2017 ), and 3-D point cloud data (Zou et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

Improve the Deep Learning Models in Forestry Based on Explanations and Expertise

2022

View full text Add to dashboard Cite

In forestry studies, deep learning models have achieved excellent performance in many application scenarios (e.g., detecting forest damage). However, the unclear model decisions (i.e., black-box) undermine the credibility of the results and hinder their practicality. This study intends to obtain explanations of such models through the use of explainable artificial intelligence methods, and then use feature unlearning methods to improve their performance, which is the first such attempt in the field of forestry. Results of three experiments show that the model training can be guided by expertise to gain specific knowledge, which is reflected by explanations. For all three experiments based on synthetic and real leaf images, the improvement of models is quantified in the classification accuracy (up to 4.6%) and three indicators of explanation assessment (i.e., root-mean-square error, cosine similarity, and the proportion of important pixels). Besides, the introduced expertise in annotation matrix form was automatically created in all experiments. This study emphasizes that studies of deep learning in forestry should not only pursue model performance (e.g., higher classification accuracy) but also focus on the explanations and try to improve models according to the expertise.

show abstract

“…Compared with other non-destructive testing technologies applied in the forestry field, electromagnetic waves have received great attention because of their fast, high-efficiency, easy-to-operate, non-susceptible external interference, and the ability to achieve non-intrusive and nondestructive testing [15][16][17]. With the substantial improvement of computer performance, some researchers have developed progressive algorithms to identify defects in common wood by means of a BP neural network and a convolution neural network, which improves the detection accuracy and efficiency [18].…”

Section: Introductionmentioning

confidence: 99%

Tree Internal Defected Imaging Using Model-Driven Deep Learning Network

et al. 2021

View full text Add to dashboard Cite

The health of trees has become an important issue in forestry. How to detect the health of trees quickly and accurately has become a key area of research for scholars in the world. In this paper, a living tree internal defect detection model is established and analyzed using model-driven theory, where the theoretical fundamentals and implementations of the algorithm are clarified. The location information of the defects inside the trees is obtained by setting a relative permittivity matrix. The data-driven inversion algorithm is realized using a model-driven algorithm that is used to optimize the deep convolutional neural network, which combines the advantages of model-driven algorithms and data-driven algorithms. The results of the comparison inversion algorithms, the BP neural network inversion algorithm, and the model-driven deep learning network inversion algorithm, are analyzed through simulations. The results shown that the model-driven deep learning network inversion algorithm maintains a detection accuracy of more than 90% for single defects or homogeneous double defects, while it can still have a detection accuracy of 78.3% for heterogeneous multiple defects. In the simulations, the single defect detection time of the model-driven deep learning network inversion algorithm is kept within 0.1 s. Additionally, the proposed method overcomes the high nonlinearity and ill-posedness electromagnetic inverse scattering and reduces the time cost and computational complexity of detecting internal defects in trees. The results show that resolution and accuracy are improved in the inversion image for detecting the internal defects of trees.

show abstract

Recent advances in the application of deep learning methods to forestry

Cited by 36 publications

References 131 publications

Few-shot detection of surface roughness of workpieces processed by different machining techniques

Few-shot detection of surface roughness of workpieces processed by different machining techniques

Improve the Deep Learning Models in Forestry Based on Explanations and Expertise

Tree Internal Defected Imaging Using Model-Driven Deep Learning Network

Contact Info

Product

Resources

About