Abstract
To date, unmanned aerial vehicles (UAVs), commonly known as drones, have been widely used in precision agriculture (PA) for crop monitoring and crop spraying, allowing farmers to increase the efficiency of the farming process, meanwhile reducing environmental impact. However, to spray pesticides effectively and safely to the trees in small fields or rugged environments, such as mountain areas, is still an open question. To bridge this gap, in this study, an onboard computer vision (CV) component for UAVs is developed. The system is low-cost, flexible, and energy-effective. It consists of two parts, the hardware part is an Intel Neural Compute Stick 2 (NCS2), and the software part is an object detection algorithm named the Ag-YOLO. The NCS2 is 18 grams in weight, 1.5 watts in energy consumption, and costs about $66. The proposed model Ag-YOLO is inspired by You Only Look Once (YOLO), trained and tested with aerial images of areca plantations, and shows high accuracy (F1 score = 0.9205) and high speed [36.5 frames per second (fps)] on the target hardware. Compared to YOLOv3-Tiny, Ag-YOLO is 2× faster while using 12× fewer parameters. Based on this study, crop monitoring and crop spraying can be synchronized into one process, so that smart and precise spraying can be performed.
Highlights
We study the efficient object detection algorithms optimized for resourcesconstraint hardware and propose a novel model, as it is derived from the famous You Only Look Once (YOLO) (Redmon et al, 2016), and used for agricultural purposes
- By proposing the Ag-YOLO object detection algorithm and testing it on the Neural Compute Stick 2 (NCS2), we demonstrate that a deep learning (DL)-based computer vision (CV) algorithm can be implemented on resource-constraint hardware, to deal with real-life precision agriculture (PA) challenges
Some efficient backbone networks were evaluated, and Almost all the images were green with the variation from light it was found that the backbone networks proposed by to dark green, except for some yellowish-brown spots which were MobileNet v2 and those proposed by ShuffleNet v2 showed time the yellow leaf disease (YLD) diseased palm individuals
Summary
The seed (areca nut) harvested is chewed in most cases because of the stimulating effect of its alkaloids. In a word, it is an importantly high-value crop. In the Hainan Island of China, this crop provides a livelihood to more than 2 million people in rural areas. This cultivar has been suffering from the yellow leaf disease (YLD) that may lead to the decay and wilt of the palms. This study compared the three cases as follows, 1) A 3 × 3 depthwise convolutional layer followed by an activation layer without activation layer for the 1 × 1 convolutional layer; 2) No activation layer for 3 × 3 depth-wise convolutional layers, and a 1 × 1
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
