Non-Destructive Assessment of Microbial Spoilage of Broiler Breast Meat Using Structured Illumination Reflectance Imaging with Machine Learning DOI
Ebenezer O. Olaniyi, Yuzhen Lu, Xin Zhang

и другие.

Food Analytical Methods, Год журнала: 2024, Номер 17(5), С. 652 - 663

Опубликована: Фев. 29, 2024

Язык: Английский

Detection of rice panicle density for unmanned harvesters via RP-YOLO DOI

Jingwei Sun,

Jun Zhou,

Yongqiang He

и другие.

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 226, С. 109371 - 109371

Опубликована: Авг. 29, 2024

Язык: Английский

Процитировано

5

Precise extraction of targeted apple tree canopy with YOLO-Fi model for advanced UAV spraying plans DOI
Wei Peng, Xiaojing Yan, Wentao Yan

и другие.

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 226, С. 109425 - 109425

Опубликована: Сен. 10, 2024

Язык: Английский

Процитировано

5

Deep learning-enhanced remote sensing-integrated crop modeling for rice yield prediction DOI Creative Commons
Seungtaek Jeong, Jonghan Ko,

Jong-Oh Ban

и другие.

Ecological Informatics, Год журнала: 2024, Номер 84, С. 102886 - 102886

Опубликована: Ноя. 9, 2024

Язык: Английский

Процитировано

5

Image patch-based deep learning approach for crop and weed recognition DOI Creative Commons
A S M Mahmudul Hasan, Dean Diepeveen, Hamid Laga

и другие.

Ecological Informatics, Год журнала: 2023, Номер 78, С. 102361 - 102361

Опубликована: Ноя. 3, 2023

Accurate classification of weed species in crop plants plays a crucial role precision agriculture by enabling targeted treatment. Recent studies show that artificial intelligence deep learning (DL) models achieve promising solutions. However, several challenging issues, such as lack adequate training data, inter-class similarity between and intra-class dissimilarity the images same at different growth stages or for other reasons (e.g., variations lighting conditions, image capturing mechanism, agricultural field environments) limit their performance. In this research, we propose an based pipeline where patch is considered time to improve We first enhance using generative adversarial networks. The enhanced are divided into overlapping patches, subset which used DL models. For selecting most informative use variance Laplacian mean frequency Fast Fourier Transforms. At test time, model's outputs fused weighted majority voting technique infer class label image. proposed was evaluated 10 state-of-the-art on four publicly available datasets: DeepWeeds, Cotton weed, Corn Tomato weed. Our achieved significant performance improvements all datasets. DenseNet201 top with F1 scores 98.49%, 99.83% 100% Deepweeds, datasets, respectively. highest score dataset 98.96%, obtained InceptionResNetV2. Moreover, addressed issues DeepWeeds more accurately classified minority classes dataset. This indicates can be farming applications.

Язык: Английский

Процитировано

11

Non-Destructive Assessment of Microbial Spoilage of Broiler Breast Meat Using Structured Illumination Reflectance Imaging with Machine Learning DOI
Ebenezer O. Olaniyi, Yuzhen Lu, Xin Zhang

и другие.

Food Analytical Methods, Год журнала: 2024, Номер 17(5), С. 652 - 663

Опубликована: Фев. 29, 2024

Язык: Английский

Процитировано

4