Related Experiment Video
Updated: Sep 2, 2026
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
Published on: August 8, 2017
Detecting SSC in litchi fruits using NIR-enhanced RGB camera combined with VNIR-ENIR transmittance hyperspectral
Teng Long1, Yibin Luo1, Junjie Li1
1College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, China; National Center for International Collaboration Research on Precision Agricultural Aviationdc Pesticides Spraying Technology, South China Agricultural University, Guangzhou 510642, China; Guangdong Engineering Technology Research Center of Smart Agriculture, South China Agricultural University, Guangzhou 510642, China.
Abstract:
Hyperspectral image (HSI) reconstruction offers a cost-effective approach for detecting food internal components, but most of the existing HSI reconstruction only covers spectral wavelengths below 1000 nm. This issue was circumvented in this paper by proposing a novel approach based on NIR-enhanced RGB camera coupled with VNIR-ENIR (400-1160 nm) transmittance HSI reconstruction to detect SSC in litchi fruit. Specifically, a dedicated VNIR-ENIR transmittance HSI reconstruction dataset was constructed for litchi fruit, and a multi-stage progressive spectral shuffle attention network (MPSSNet) was then developed to reconstruct VNIR-ENIR transmittance HSIs from the high-resolution NIR-enhanced RGB images. The results showed that the SSC prediction model based on the NIR-enhanced RGB images combined with transmittance HSI reconstruction achieved an Rp2 of 0.8907, only 3.88% lower than the original HSI model (Rp2 = 0.9295). The comparable prediction accuracy demonstrated that the proposed method was a cost-effective alternative to hyperspectral cameras for detecting internal components.
