Abstract
Tobacco is an essential economic crop in China. The detection of tobacco plants in aerial images plays an important role in the management of tobacco plants and, in particular, in yield estimations. Traditional yield estimation is based on site inspections, which can be inefficient, time-consuming, and laborious. In this paper, we proposed an algorithm to detect tobacco plants in RGB aerial images automatically. The proposed algorithm is comprised of two stages: (1) A candidate selecting algorithm extracts possible tobacco plant regions from the input, (2) a trained CNN (Convolutional Neural Network) classifies a candidate as either a tobacco-plant region or a nontobacco-plant one. This proposed algorithm is trained and evaluated on different datasets. It demonstrates good performance on tobacco plant detection in aerial images and obtains a significant improvement on AP (Average Precision) compared to faster R-CNN (Regions with CNN features) and YOLOv3 (You Only Look Once v3).
Highlights
Tobacco is native to South America [1] and it is widely cultivated in the southern and northern provinces of China
Yield estimation plays an important role in the management of tobacco planting and in the agriculture precision, motivating many studies [3,4]
For the tobacco region proposal algorithm, we compared it with selective search edge boxes
Summary
Tobacco is native to South America [1] and it is widely cultivated in the southern and northern provinces of China. Can it be made into cigarettes, it has a variety of significant medical properties [2]. There have been studies on how to estimate production using remote sensing data [5,6] which can be costly and computationally expensive. For these two reasons, finding a low cost and efficient method to automatically estimate the yield of tobacco plants is both urgent and necessary. There are many researches on estimating production by treating it as an object detection task in aerial images [4,7]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
