Automation in Natural Rubber Latex Harvesting Field: A Review

Natural rubber remains a highly valuable and versatile material obtained from the latex of rubber trees. The global demand for natural rubber continues to increase as new applications emerge. However, the productivity and management of natural rubber face challenges such as the unavailability of skilled workers, rising labor costs, climate change, and cost fluctuations. This study focuses on three labor-intensive processes: girth measurement, tapping line detection, and grading of Ribbed Smoked Sheet (RSS). These processes are time-consuming, prone to errors, and involve high labor costs. To overcome these limitations, recent studies have applied automated algorithms such as deep learning, machine learning, and image processing. The role of machine learning, image processing, deep learning, and computer vision algorithms in the latex harvesting fields is investigated in this paper. Various methods and devices used in the image acquisition of rubber trees are discussed. The findings demonstrate that deep learning and computer vision methods effectively address the existing challenges in latex harvesting fields. Convolutional Neural Networks (CNNs) achieve higher accuracy in bounding box detection and reduce computational time. Computer vision methods based on CNNs can automatically detect tapping lines on rubber trees, even under varying lighting conditions.