Single-Shot Convolution Neural Networks for Real-Time Fruit Detection Within the Tree.

Image/video processing for fruit detection in the tree using hard-coded feature extraction algorithms has shown high accuracy on fruit detection during recent years. While accurate, these approaches even with high-end hardware are still computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks architecture based on single-stage detectors. Using deep-learning techniques eliminates the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This architecture takes the input image and divides into AxA grid, where A is a configurable hyper-parameter that defines the fineness of the grid. To each grid cell an image detection and localization algorithm is applied. Each of those cells is responsible to predict bounding boxes and confidence score for fruit (apple and pear in the case of this study) detected in that cell. We want this confidence score to be high if a fruit exists in a cell, otherwise to be zero, if no fruit is in the cell. More than 100 images of apple and pear trees were taken. Each tree image with approximately 50 fruits, that at the end resulted on more than 5000 images of apple and pear fruits each. Labeling images for training consisted on manually specifying the bounding boxes for fruits, where (x, y) are the center coordinates of the box and (w, h) are width and height. This architecture showed an accuracy of more than 90% fruit detection. Based on correlation between number of visible fruits, detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Processing speed is higher than 20 FPS which is fast enough for any grasping/harvesting robotic arm or other real-time applications. HIGHLIGHTS: Using new convolutional deep learning techniques based on single-shot detectors to detect and count fruits (apple and pear) within the tree canopy.

Sweet cherry water relations and fruit production efficiency are affected by rootstock vigor.

Rootstock vigor is well known to affect yield and productive performance in many fruit crops and the dwarfing trait is often the preferred choice for modern orchard systems thanks to its improved productivity and reduced canopy volume. This work investigates the different physiological responses induced by rootstock vigor on cherry, by comparing shoot and fruit growth, water relations, leaf gas exchanges as well as fruit vascular and transpiration in/outflows of "Black Star" trees grafted on semi-vigorous (CAB6 P) and on semi-dwarfing (Gisela™6) rootstocks. The daily patterns of stem (Ψstem), leaf (Ψleaf) and fruit (Ψfruit) water potential, leaf photosynthesis, stomatal conductance and transpiration, shoot and fruit growth, fruit phloem, xylem and transpiration flows were assessed both in pre- and post-veraison, while productivity and fruit quality were determined at harvest. At both stages, no significant differences were found on Ψleaf, photosynthesis, fruit daily growth rates as well as fruit vascular and transpiration flows, while trees on Gisela™6 showed lower shoot growth rates and lower Ψstem and Ψfruit than trees on CAB6 P. The resulting decrease in stem-to-leaf Ψ gradient on Gisela™6 trees determined a reduction in shoot growth by decreasing shoot strength as sinks for water and carbohydrates. On the other hand, Gisela™6 fruit lowered their Ψfruit thanks to a higher osmotic accumulation and increased their competitiveness towards shoots, as confirmed by the higher productivity and fruit soluble solid content found at harvest for these trees. These results indicate that rootstock vigor alters resource competition between vegetative and reproductive growth, which can affect water use efficiency, yield, and fruit quality.