Journal
COMPUTERS AND ELECTRONICS IN AGRICULTURE
Volume 193, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.compag.2022.106696
Keywords
Attention mechanism module; Canopy fruit counting; Deep learning; Fruit size estimation; Green fruit detection
Funding
- National Natural Science (NNSF) of China [61762013]
- Research Fund of Guangxi Key Lab of Multi-source Information Mining Security [20-A-02-02]
- Innova-tion Project of Guangxi Graduate Education [XYCSZ2021007]
- USDA Hatch and Multistate Project Funds [7001292]
- Mississippi State University (MSU) Mississippi Agricultural and Forestry Experiment Station (MAFES)
Ask authors/readers for more resources
In this study, a near real-time method using a low-cost smartphone was proposed to accurately detect immature and mature apples in orchard environments. By adding an attention mechanism module and modifying the network structure, the proposed CA-YOLOv4 detector outperformed other algorithms and showed great potential for efficient real-world applications.
Accurate detection of both immature and mature apples in orchard environments is essential for early crop load management. A near real-time method is proposed in this study for detecting green (early-stage), green-red-mixed (mid-stage; red varieties), or red apples (harvest-stage; red varieties). Both the number of fruits and fruit size were estimated for the entire tree with a single image captured by a low-cost smartphone using two different imaging methods (oblique and panorama modes). An attention mechanism module called the convolutional block attention module (CBAM) was added to the generic YOLOv4 detector to improve the detection accuracy by only focusing on the target canopies. Furthermore, an adaptive layer and larger-scale feature map were included in the modified network structure, enabling it to adapt to various characteristics of fruits and canopies during the entire growing season, such as different fruit colors and sizes, dense-foliage conditions, and severe occlusions. To verify the effectiveness of the proposed method, we compared our improved model, canopy-attention-YOLOv4 (or CA-YOLOv4), with other commonly adopted models available in the literature, such as the original YOLOv4, Faster R CNN, and single-shot multibox detector (SSD). Two commonly planted apple varieties, Envy and Scifresh, were used in the study. The results showed that the proposed CA-YOLOv4 detector performed the best among all the algorithms, with up to similar to 3% improvement in terms of fruit counting over the original YOLOv4. With the Envy variety, fruit detection accuracies were 86.2%, 87.5%, and 92.6% for the early-, mid-, and harvest stages, respectively, whereas the same were 71.0%, 83.6%, and 86.3% for the Scifresh variety, which has denser canopy foliage. Both imaging methods proposed in this study only needed one/single shot targeting the entire fruiting tree, which can be highly efficient for real-world applications in crop load management. Finally, CA YOLOv4 estimated fruit sizes were compared to manual measurements, achieving up to R 2 values of 0.68 in fruit height and 0.66 in fruit width estimations.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available