In-field mango fruit sizing is useful for estimation of fruit maturation and size distribution, informing the decision to harvest, harvest resourcing (e.g., tray insert sizes), and marketing. In-field machine vision imaging has been used for fruit count, but assessment of fruit size from images also requires estimation of camera-to-fruit distance. Low cost examples of three technologies for assessment of camera to fruit distance were assessed: a RGB-D (depth) camera, a stereo vision camera and a Time of Flight (ToF) laser rangefinder. The RGB-D camera was recommended on cost and performance, although it functioned poorly in direct sunlight. The RGB-D camera was calibrated, and depth information matched to the RGB image. To detect fruit, a cascade detection with histogram of oriented gradients (HOG) feature was used, then Otsu’s method, followed by color thresholding was applied in the CIE L*a*b* color space to remove background objects (leaves, branches etc.). A one-dimensional (1D) filter was developed to remove the fruit pedicles, and an ellipse fitting method employed to identify well-separated fruit. Finally, fruit lineal dimensions were calculated using the RGB-D depth information, fruit image size and the thin lens formula. A Root Mean Square Error (RMSE) = 4.9 and 4.3 mm was achieved for estimated fruit length and width, respectively, relative to manual measurement, for which repeated human measures were characterized by a standard deviation of 1.2 mm. In conclusion, the RGB-D method for rapid in-field mango fruit size estimation is practical in terms of cost and ease of use, but cannot be used in direct intense sunshine. We believe this work represents the first practical implementation of machine vision fruit sizing in field, with practicality gauged in terms of cost and simplicity of operation.

Pre-harvest fruit yield estimation is useful to guide harvesting and marketing resourcing, but machine vision estimates based on a single view from each side of the tree (“dual-view”) underestimates the fruit yield as fruit can be hidden from view. A method is proposed involving deep learning, Kalman filter, and Hungarian algorithm for on-tree mango fruit detection, tracking, and counting from 10 frame-per-second videos captured of trees from a platform moving along the inter row at 5 km/h. The deep learning based mango fruit detection algorithm, MangoYOLO, was used to detect fruit in each frame. The Hungarian algorithm was used to correlate fruit between neighbouring frames, with the improvement of enabling multiple-to-one assignment. The Kalman filter was used to predict the position of fruit in following frames, to avoid multiple counts of a single fruit that is obscured or otherwise not detected with a frame series. A “borrow” concept was added to the Kalman filter to predict fruit position when its precise prediction model was absent, by borrowing the horizontal and vertical speed from neighbouring fruit. By comparison with human count for a video with 110 frames and 192 (human count) fruit, the method produced 9.9% double counts and 7.3% missing count errors, resulting in around 2.6% over count. In another test, a video (of 1162 frames, with 42 images centred on the tree trunk) was acquired of both sides of a row of 21 trees, for which the harvest fruit count was 3286 (i.e., average of 156 fruit/tree). The trees had thick canopies, such that the proportion of fruit hidden from view from any given perspective was high. The proposed method recorded 2050 fruit (62% of harvest) with a bias corrected Root Mean Square Error (RMSE) = 18.0 fruit/tree while the dual-view image method (also using MangoYOLO) recorded 1322 fruit (40%) with a bias corrected RMSE = 21.7 fruit/tree. The video tracking system is recommended over the dual-view imaging system for mango orchard fruit count.

Eight depth cameras varying in operational principle (stereoscopy: ZED, ZED2, OAK-D; IR active stereoscopy: Real Sense D435; time of flight (ToF): Real Sense L515, Kinect v2, Blaze 101, Azure Kinect) were compared in context of use for in-orchard fruit localization and sizing. For this application, a specification on bias-corrected root mean square error of 20 mm for a camera-to-fruit distance of 2 m and operation under sunlit field conditions was set. The ToF cameras achieved the measurement specification, with a recommendation for use of Blaze 101 or Azure Kinect made in terms of operation in sunlight and in orchard conditions. For a camera-to-fruit distance of 1.5 m in sunlight, the Azure Kinect measurement achieved an RMSE of 6 mm, a bias of 17 mm, an SD of 2 mm and a fill rate of 100% for depth values of a central 50 × 50 pixels group. To enable inter-study comparisons, it is recommended that future assessments of depth cameras for this application should include estimation of a bias-corrected RMSE and estimation of bias on estimated camera-to-fruit distances at 50 cm intervals to 3 m, under both artificial light and sunlight, with characterization of image distortion and estimation of fill rate.

Machine vision from ground vehicles is being used for estimation of fruit load on trees, but a correction is required for occlusion by foliage or other fruits. This requires a manually estimated factor (the reference method). It was hypothesised that canopy images could hold information related to the number of occluded fruits. Several image features, such as the proportion of fruit that were partly occluded, were used in training Random forest and multi-layered perceptron (MLP) models for estimation of a correction factor per tree. In another approach, deep learning convolutional neural networks (CNNs) were directly trained against harvest count of fruit per tree. A R2 of 0.98 (n = 98 trees) was achieved for the correlation of fruit count predicted by a Random forest model and the ground truth fruit count, compared to a R² of 0.68 for the reference method. Error on prediction of whole orchard (880 trees) fruit load compared to packhouse count was 1.6% for the MLP model and 13.6% for the reference method. However, the performance of these models on data of another season was at best equivalent and generally poorer than the reference method. This result indicates that training on one season of data was insufficient for the development of a robust model.

Automated assessment of the number of panicles by developmental stage can provide information on the time spread of flowering and thus inform farm management. A pixel-based segmentation method for the estimation of flowering level from tree images was confounded by the developmental stage. Therefore, the use of a single and a two-stage deep learning framework (YOLO and R²CNN) was considered, using either upright or rotated bounding boxes. For a validation image set and for a total panicle count, the models MangoYOLO(-upright), MangoYOLO-rotated, YOLOv3-rotated, R²CNN(-rotated) and R²CNN-upright achieved weighted F1 scores of 76.5, 76.1, 74.9, 74.0 and 82.0, respectively. For a test set of the images of another cultivar and using a different camera, the R² for machine vision to human count of panicles per tree was 0.86, 0.80, 0.83, 0.81 and 0.76 for the same models, respectively. Thus, there was no consistent benefit from the use of rotated over the use of upright bounding boxes. The YOLOv3-rotated model was superior in terms of total panicle count, and the R²CNN-upright model was more accurate for panicle stage classification. To demonstrate practical application, panicle counts were made weekly for an orchard of 994 trees, with a peak detection routine applied to document multiple flowering events.

In field (on tree) fruit sizing has value in assessing crop health and for yield estimation. As the mobile phone is a sensor and communication rich device carried by almost all farm staff, an Android application (“FruitSize”) was developed for measurement of fruit size in field using the phone camera, with a typical assessment rate of 240 fruit per hour achieved. The application was based on imaging of fruit against a backboard with a scale using a mobile phone, with operational limits set on camera to object plane angle and camera to object distance. Image processing and object segmentation techniques available in the OpenCV library were used to segment the fruit from background in images to obtain fruit sizes. Phone camera parameters were accessed to allow calculation of fruit size, with camera to fruit perimeter distance obtained from fruit allometric relationships between fruit thickness and width. Phone geolocation data was also accessed, allowing for mapping fruits of data. Under controlled lighting, RMSEs of 3.4, 3.8, 2.4, and 2.0 mm were achieved in estimation of avocado, mandarin, navel orange, and apple fruit diameter, respectively. For mango fruit, RMSEs of 5.3 and 3.7 mm were achieved on length and width, benchmarked to manual caliper measurements, under controlled lighting, and RMSEs of 5.5 and 4.6 mm were obtained in-field under ambient lighting.