Application of delta-wing airplane remote sensing system with dual-camera in mapping vegetation fraction

Abstract

Mapping vegetation fraction in crop fields is an important step in remote sensing applications for precision agriculture. Two critical limitations for using current satellite sensors are the lack of imagery with optimum spatial and spectral resolution and an unfavorable revisit time. Remote sensing sensors placed on low-altitude aerial platforms could fill this gap. This paper validated the availability of red green blue(RGB) and near infrared(NIR) imaging acquired from a delta-wing airplane platform with dual-camera for monitoring vegetation fraction, and explored the technological processes and methods for fast processing of remote sensing image. RGB imaging was used to calculate VI RGB and interpreted by different classification algorithms. We examined the classification accuracy of RGB images respectively in cotton yield estimation and rapid crops classification, further, to study the influence of flight altitude on the classification accuracy. Additionally, we assessed the applicability of NIR imaging in dynamic monitoring vegetation growth status. We found COM and ML achieved the best accuracy in cotton yield estimating, with overall accuracy of 95.42% and 96.25% at a 200m flight altitude. Besides, the result of analyzing the influence of flight altitudes (500m and 1000m) to crop quick classification indicated that VEG, COM and ML methods' variations associated with the flight altitudes, and classification accuracy at 1000m demonstrated more higher than 500m, which appeared better for mapping vegetation in a large area. In addition, we could found that NIR imaging had great potential in dynamic monitoring growth status of vegetation in the future. This paper provides evidence that RGB and NIR imaging acquired using a low-cost dual-camera onboard a delta-wing airplane at low altitudes were a suitable tool to use to discriminate vegetation. This opened the doors for the utilization of this platform and technology in precision agriculture applications and dynamic monitoring grassland biological disasters.