Uddhav Bhattarai

Salik Ram Khanal, Ranjan Sapkota, Dawood Ahmed et al.

Early-stage identification of fruit flowers that are in both opened and unopened condition in an orchard environment is significant information to perform crop load management operations such as flower thinning and pollination using automated and robotic platforms. These operations are important in tree-fruit agriculture to enhance fruit quality, manage crop load, and enhance the overall profit. The recent development in agricultural automation suggests that this can be done using robotics which includes machine vision technology. In this article, we proposed a vision system that detects early-stage flowers in an unstructured orchard environment using YOLOv5 object detection algorithm. For the robotics implementation, the position of a cluster of the flower blossom is important to navigate the robot and the end effector. The centroid of individual flowers (both open and unopen) was identified and associated with flower clusters via K-means clustering. The accuracy of the opened and unopened flower detection is achieved up to mAP of 81.9% in commercial orchard images.

Uddhav Bhattarai, Santosh Bhusal, Qin Zhang et al.

One of the major challenges for the agricultural industry today is the uncertainty in manual labor availability and the associated cost. Automated flower and fruit density estimation, localization, and counting could help streamline harvesting, yield estimation, and crop-load management strategies such as flower and fruitlet thinning. This article proposes a deep regression-based network, AgRegNet, to estimate density, count, and location of flower and fruit in tree fruit canopies without explicit object detection or polygon annotation. Inspired by popular U-Net architecture, AgRegNet is a U-shaped network with an encoder-to-decoder skip connection and modified ConvNeXt-T as an encoder feature extractor. AgRegNet can be trained based on information from point annotation and leverages segmentation information and attention modules (spatial and channel) to highlight relevant flower and fruit features while suppressing non-relevant background features. Experimental evaluation in apple flower and fruit canopy images under an unstructured orchard environment showed that AgRegNet achieved promising accuracy as measured by Structural Similarity Index (SSIM), percentage Mean Absolute Error (pMAE) and mean Average Precision (mAP) to estimate flower and fruit density, count, and centroid location, respectively. Specifically, the SSIM, pMAE, and mAP values for flower images were 0.938, 13.7%, and 0.81, respectively. For fruit images, the corresponding values were 0.910, 5.6%, and 0.93. Since the proposed approach relies on information from point annotation, it is suitable for sparsely and densely located objects. This simplified technique will be highly applicable for growers to accurately estimate yields and decide on optimal chemical and mechanical flower thinning practices.

Uddhav Bhattarai, Rajkishan Arikapudi, Steven A. Fennimore et al.

Manual fruit harvesting is common in agriculture, but the amount of time pickers spend on non-productive activities can make it very inefficient. Accurately identifying picking vs. non-picking activity is crucial for estimating picker efficiency and optimising labour management and harvest processes. In this study, a practical system was developed to calculate the efficiency of pickers in commercial strawberry harvesting. Instrumented picking carts were developed to record the harvested fruit weight, geolocation, and cart movement in real time. These carts were deployed during the commercial strawberry harvest season in Santa Maria, CA. The collected data was then used to train a CNN-LSTM-based deep neural network to classify a picker's activity into "Pick" and "NoPick" classes. Experimental evaluations showed that the CNN-LSTM model showed promising activity recognition performance with an F1 score accuracy of over 0.97. The recognition results were then used to compute picker efficiency and the time required to fill a tray. Analysis of the season-long harvest data showed that the average picker efficiency was 75.07% with an estimation accuracy of 95.22%. Furthermore, the average tray fill time was 6.79 minutes with an estimation accuracy of 96.43%. When integrated into commercial harvesting, the proposed technology can aid growers in monitoring automated worker activity and optimising harvests to reduce non-productive time and enhance overall harvest efficiency.