FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113522598> ?p ?o ?g. }

• W3113522598 endingPage "54" @default.
• W3113522598 startingPage "54" @default.
• W3113522598 abstract "In recent years, many agriculture-related problems have been evaluated with the integration of artificial intelligence techniques and remote sensing systems. Specifically, in fruit detection problems, several recent works were developed using Deep Learning (DL) methods applied in images acquired in different acquisition levels. However, the increasing use of anti-hail plastic net cover in commercial orchards highlights the importance of terrestrial remote sensing systems. Apples are one of the most highly-challenging fruits to be detected in images, mainly because of the target occlusion problem occurrence. Additionally, the introduction of high-density apple tree orchards makes the identification of single fruits a real challenge. To support farmers to detect apple fruits efficiently, this paper presents an approach based on the Adaptive Training Sample Selection (ATSS) deep learning method applied to close-range and low-cost terrestrial RGB images. The correct identification supports apple production forecasting and gives local producers a better idea of forthcoming management practices. The main advantage of the ATSS method is that only the center point of the objects is labeled, which is much more practicable and realistic than bounding-box annotations in heavily dense fruit orchards. Additionally, we evaluated other object detection methods such as RetinaNet, Libra Regions with Convolutional Neural Network (R-CNN), Cascade R-CNN, Faster R-CNN, Feature Selective Anchor-Free (FSAF), and High-Resolution Network (HRNet). The study area is a highly-dense apple orchard consisting of Fuji Suprema apple fruits (Malus domestica Borkh) located in a smallholder farm in the state of Santa Catarina (southern Brazil). A total of 398 terrestrial images were taken nearly perpendicularly in front of the trees by a professional camera, assuring both a good vertical coverage of the apple trees in terms of heights and overlapping between picture frames. After, the high-resolution RGB images were divided into several patches for helping the detection of small and/or occluded apples. A total of 3119, 840, and 2010 patches were used for training, validation, and testing, respectively. Moreover, the proposed method’s generalization capability was assessed by applying simulated image corruptions to the test set images with different severity levels, including noise, blurs, weather, and digital processing. Experiments were also conducted by varying the bounding box size (80, 100, 120, 140, 160, and 180 pixels) in the image original for the proposed approach. Our results showed that the ATSS-based method slightly outperformed all other deep learning methods, between 2.4% and 0.3%. Also, we verified that the best result was obtained with a bounding box size of 160 × 160 pixels. The proposed method was robust regarding most of the corruption, except for snow, frost, and fog weather conditions. Finally, a benchmark of the reported dataset is also generated and publicly available." @default.
• W3113522598 created "2021-01-05" @default.
• W3113522598 creator A5004115027 @default.
• W3113522598 creator A5013486686 @default.
• W3113522598 creator A5017880637 @default.
• W3113522598 creator A5029598844 @default.
• W3113522598 creator A5032300680 @default.
• W3113522598 creator A5034562479 @default.
• W3113522598 creator A5038515900 @default.
• W3113522598 creator A5047273130 @default.
• W3113522598 creator A5057971546 @default.
• W3113522598 creator A5062377651 @default.
• W3113522598 creator A5068523611 @default.
• W3113522598 creator A5071340024 @default.
• W3113522598 creator A5076941451 @default.
• W3113522598 creator A5083926768 @default.
• W3113522598 creator A5088000884 @default.
• W3113522598 date "2020-12-25" @default.
• W3113522598 modified "2023-10-17" @default.
• W3113522598 title "ATSS Deep Learning-Based Approach to Detect Apple Fruits" @default.
• W3113522598 cites W1532898750 @default.
• W3113522598 cites W180836830 @default.
• W3113522598 cites W1964487621 @default.
• W3113522598 cites W1984560974 @default.
• W3113522598 cites W2030222098 @default.
• W3113522598 cites W2076063813 @default.
• W3113522598 cites W2490973504 @default.
• W3113522598 cites W2541630240 @default.
• W3113522598 cites W2543665758 @default.
• W3113522598 cites W2565950292 @default.
• W3113522598 cites W2773784572 @default.
• W3113522598 cites W2790568319 @default.
• W3113522598 cites W2790979755 @default.
• W3113522598 cites W2794915299 @default.
• W3113522598 cites W2890513934 @default.
• W3113522598 cites W2896107488 @default.
• W3113522598 cites W2896971046 @default.
• W3113522598 cites W2898498213 @default.
• W3113522598 cites W2901867974 @default.
• W3113522598 cites W2901871634 @default.
• W3113522598 cites W2904950031 @default.
• W3113522598 cites W2909494862 @default.
• W3113522598 cites W2912706692 @default.
• W3113522598 cites W2919115771 @default.
• W3113522598 cites W2920621226 @default.
• W3113522598 cites W2928389720 @default.
• W3113522598 cites W2936307272 @default.
• W3113522598 cites W2938495304 @default.
• W3113522598 cites W2943955917 @default.
• W3113522598 cites W2944599236 @default.
• W3113522598 cites W2944963477 @default.
• W3113522598 cites W2962721361 @default.
• W3113522598 cites W2963299996 @default.
• W3113522598 cites W2963353662 @default.
• W3113522598 cites W2964241181 @default.
• W3113522598 cites W2971456001 @default.
• W3113522598 cites W2981630388 @default.
• W3113522598 cites W2982673914 @default.
• W3113522598 cites W2989928569 @default.
• W3113522598 cites W2992240579 @default.
• W3113522598 cites W2996445195 @default.
• W3113522598 cites W2996945294 @default.
• W3113522598 cites W2997692196 @default.
• W3113522598 cites W3000696750 @default.
• W3113522598 cites W3003266520 @default.
• W3113522598 cites W3003732786 @default.
• W3113522598 cites W3005287219 @default.
• W3113522598 cites W3007597990 @default.
• W3113522598 cites W3008439211 @default.
• W3113522598 cites W3010924259 @default.
• W3113522598 cites W3014641072 @default.
• W3113522598 cites W3035396860 @default.
• W3113522598 cites W3036650396 @default.
• W3113522598 cites W3039926407 @default.
• W3113522598 cites W3042421576 @default.
• W3113522598 cites W3042706118 @default.
• W3113522598 cites W3048750283 @default.
• W3113522598 cites W3081171346 @default.
• W3113522598 cites W3085201316 @default.
• W3113522598 cites W3104341624 @default.
• W3113522598 cites W639708223 @default.
• W3113522598 doi "https://doi.org/10.3390/rs13010054" @default.
• W3113522598 hasPublicationYear "2020" @default.
• W3113522598 type Work @default.
• W3113522598 sameAs 3113522598 @default.
• W3113522598 citedByCount "27" @default.
• W3113522598 countsByYear W31135225982021 @default.
• W3113522598 countsByYear W31135225982022 @default.
• W3113522598 countsByYear W31135225982023 @default.
• W3113522598 crossrefType "journal-article" @default.
• W3113522598 hasAuthorship W3113522598A5004115027 @default.
• W3113522598 hasAuthorship W3113522598A5013486686 @default.
• W3113522598 hasAuthorship W3113522598A5017880637 @default.
• W3113522598 hasAuthorship W3113522598A5029598844 @default.
• W3113522598 hasAuthorship W3113522598A5032300680 @default.
• W3113522598 hasAuthorship W3113522598A5034562479 @default.
• W3113522598 hasAuthorship W3113522598A5038515900 @default.
• W3113522598 hasAuthorship W3113522598A5047273130 @default.

• next