This comparative research paper examines the difference between sugarcane harvesting practices in Thailand and India. The objective of research was to investigate and compare current pattern of sugar harvesting and its impact of these approaches on labor health conditions in the sugarcane industry of both the countries as India and Thailand. Data were collected from target population groups (40 each) from study areas, namely Kanchanaburi and Saraburi provinces in Thailand and Beed District of Maharashtra state from India. The data showed that comparatively in Thailand, adoption of mechanized harvesting was seen more. However in India, mechanized harvesting was seen increasing but still people were largely involved in sugarcane harvesting and it had ill effects on the overall health of female workers specially. The result clearly indicated that there was drastic difference in harvesting system and labor health conditions in Thailand and India. The findings underscore the multifaceted impact of their occupation on various aspects of health including general well-being of female sugarcane cutters. The strenuous nature of sugarcane cutting, coupled with inadequate protective measures and limited access to healthcare has contributed to a range of health care challenges among female sugarcane cutters in India.
The agricultural industry prioritizes crop protection, particularly against threats like pink bollworm infestations in cotton crops. This paper presents a comprehensive solution using the Robot Operating System (ROS) to deploy an autonomous robot for detecting pink bollworm infestations and tracking red illnesses. Drones collect multispectral photos of cotton fields, aiding path planning via Normalized Difference Vegetation Index (NDVI) computations. A bespoke dataset of RGB and multispectral images trained a YOLOv8 model for object detection, achieving a mean Average Precision (mAP) of 67.1%, Precision of 67.9%, and Recall of 61.8%. The robot was tested in two separate cotton fields, with rows around 20 meters long and the camera at 60 cm height for optimal real-time detection. The findings, compared to hand counts and confirmed against NDVI estimates, showed an average accuracy of 76.04% for B.T. Cotton and 67.54% for Organic Cotton fields. This study demonstrates the effectiveness of the proposed system in accurately detecting and managing crop threats. Combining ROS, drones, NDVI calculations, and a robust detection model, it provides a scalable approach for autonomous crop monitoring and protection, with the potential for broader agricultural adoption.
In the modern world, machine learning and artificial intelligence is a significant part of daily life. Now a days, it is adopted in various applications, such as object detection, recognition and classification. This research aimed to use machine learning algorithms for the detection of Huanglongbing (HLB)-Infected disease, healthy and background patch in citrus orchard. HLB-Infected patches need to be identified for appropriate treatments of spraying. However, farmers are unaware of infections on plant leaves and therefore adopt manual disease identification methods. These results decrease in production as the infection spreads. However, due to a lack of required facilities, instant identification needs to be improved in many aspects of the agricultural sector. To conduct this research, firstly, a dataset was created that contained drone images of citrus orchards that was split into three classes, specifically (i) Healthy, (ii) HLB-Infected and (iii) Background. This research collects 6000 image patches of citrus orchard and categorized 2000 images in each class. The next step was to train the machine learning model to identify Healthy, HLB-Infected and Background. In this research three models were trained i.e. EfficientNetV2B0, DenseNet-121 and ResNet-50 model was to detect the HLB infection patch. The models exhibited exceptional performance, with ResNet-50 achieving the highest overall accuracy of 89, followed by EfficientNetV2B0 (87) and DenseNet-121 (85). ResNet-50 demonstrated superior balanced performance with macro-average precision of 90%, recall of 89%, and F1-score of 89%. The generated HLB detection map effectively visualized disease distribution patterns, identifying 31% of patches as HLB-infected, 7% as Healthy and 62% as Background across the orchard grid. This research establishes a reliable framework for large-scale, automated citrus disease monitoring that enables precision agriculture interventions, potentially reducing economic losses and optimizing resource allocation in citrus cultivation through early and accurate HLB detection.