Skip to main content
ARS Home » Plains Area » College Station, Texas » Southern Plains Agricultural Research Center » Aerial Application Technology Research » Research » Publications at this Location » Publication #335167
Title: Crop classification and LAI estimation using original and resolution-reduced images from consumer-grade cameras

Author
item ZHANG, JIAN - Huazhong Agricultural University
item Yang, Chenghai
item SONG, HUAIBO - Northwest Agricultural & Forestry University
item Hoffmann, Wesley
item YEYIN, SHI - Texas A&M University
item ZHANG, DONGYAN - Anhui Agricultural University
item ZHANG, GUOZHONG - Huazhong Agricultural University

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/26/2017
Publication Date: 10/17/2017
Citation: Zhang, J., Yang, C., Song, H., Hoffmann, W.C., Yeyin, S., Zhang, D., Zhang, G. 2017. Crop classification and LAI estimation using original and resolution-reduced images from consumer-grade cameras. Remote Sensing. 9(10):1-18.

Interpretive Summary: Consumer-grade cameras are being increasingly used for remote sensing applications in recent years. However, the performance of this type of cameras has not been systematically tested and well documented in the literature. This research evaluated original and resolution-reduced images taken from two consumer-grade cameras - a normal color camera and a modified near-infrared camera - for crop identification and canopy cover estimation. Results show the two types of images combined or the normal color images alone can be used for crop identification and canopy cover estimation. Moreover, images with spatial resolutions of 0.4 to 4 m had better results than those with coarser resolutions. The findings from this study indicate that a normal color camera alone with relatively coarse spatial resolutions can be used for such agricultural applications as crop identification and canopy cover estimation, though an additional near-infrared camera has the potential to improve the results for some applications.

Technical Abstract: Consumer-grade cameras are being increasingly used for remote sensing applications in recent years. However, the performance of this type of cameras has not been systematically tested and well documented in the literature. The objective of this research was to evaluate the performance of original and resolution-reduced images taken from two consumer-grade cameras - a RGB camera and a modified near-infrared (NIR) camera - for crop identification and leaf area index (LAI) estimation. Airborne RGB and NIR images taken over a 22-square-km cropping area were mosaicked and aligned to create a four-band mosaic with a spatial resolution of 0.4 m. The spatial resolution of the mosaic was then reduced to 1, 2, 4, 10, 15, and 30 m for comparison. Six supervised classifiers were applied to the RGB images and the four-band images for crop identification, and vegetation indexes (VIs) derived from the RGB and four-band images were related to ground-measured LAI. Results show the four-band images provided slightly better classification accuracy than the RGB images for crop identification by most classifiers. However, the VIs based on the RGB images provided similar or even higher correlations with LAI. Moreover, spatial resolutions at 0.4, 1, 2 and 4 m achieved better results for both crop identification and LAI prediction than the coarser spatial resolutions. The results from this study indicate that RGB images alone with relatively coarse spatial resolutions (1-4 m) can be used for such agricultural applications as crop identification and canopy cover estimation.