A Method of Modern Standardized Apple Orchard Flowering Monitoring Based on S-YOLO

Abstract

Monitoring fruit tree flowering information in the open world is more crucial than in the research-oriented environment for managing agricultural production to increase yield and quality. This work presents a transformer-based flowering period monitoring approach in an open world in order to better monitor the whole blooming time of modern standardized orchards utilizing IoT technologies. This study takes images of flowering apple trees captured at a distance in the open world as the research object, extends the dataset by introducing the Slicing Aided Hyper Inference (SAHI) algorithm, and establishes an S-YOLO apple flower detection model by substituting the YOLOX backbone network with Swin Transformer-tiny. The experimental results show that S-YOLO outperformed YOLOX-s in the detection accuracy of the four blooming states by 7.94%, 8.05%, 3.49%, and 6.96%. It also outperformed YOLOX-s by 10.00%, 9.10%, 13.10%, and 7.20% for mAPALL, mAPS, mAPM, and mAPL, respectively. By increasing the width and depth of the network model, the accuracy of the larger S-YOLO was 88.18%, 88.95%, 89.50%, and 91.95% for each flowering state and 39.00%, 32.10%, 50.60%, and 64.30% for each type of mAP, respectively. The results show that the transformer-based method of monitoring the apple flower growth stage utilized S-YOLO to achieve the apple flower count, percentage analysis, peak flowering time determination, and flowering intensity quantification. The method can be applied to remotely monitor flowering information and estimate flowering intensity in modern standard orchards based on IoT technology, which is important for developing fruit digital production management technology and equipment and guiding orchard production management.

Quantification of Phenological, Physiological, and Morphological Response of Kiwifruit Varieties under Rainfed Conditions

“…This indicates that GDD information can be used to do adaptability evaluation and kiwifruit commercial production. GDD may be a more accurate and reliable predictor of phenology for orchard planning, as Zhou et al [103] reported that monitoring fruit tree flowering can help manage orchards, which leads to increased yield and quality. In our studies, the study site Rawalpindi, which was colder than Chakwal, accumulated higher GDD than Chakwal.…”

Research on cherry maturity detection based on improved DS-YOLOV8

“…In order to further verify the performance of the improved YOLOv8 model, this 2 study set up an ablation test to verify the performance of four groups of networks. YOLOv8+FocalModulation [26],YOLOv8 [27],YOLOV8+dysnakeconv [28] the algorithm in 2 3 this paper analyze the performance of four groups of networks from a quantitative perspective. The 1000 cherry images in the test set are objectively evaluated, and the evaluation indicators include model detection accuracy, average detection time, etc.…”

Multiscale apple recognition method based on improved CenterNet

“…However, the complex background environment, make it very difficult to identify small fruits in the early stage of fruits and vegetables. Extensive research has been done on fruit identification at home and abroad [ [9] , [10] , [11] , [12] ]. The fruit target recognition methods mainly include color difference method [ 13 ], K-means clustering method [ 14 ], fuzzy C-means method [ 15 ], K-Nearest Neighbor method, artificial neural network [ 16 ].…”