Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determination R2 was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.
Using polystyrene two-dimensional photonic crystal as template, gatifloxacin (GTFX) as imprinting molecule, methanol as solvent, acrylic acid as functional monomer, ethylene glycol dimethyl acrylate as crosslinking agent and 2,2diethyloxyacetophenone as initiator, after UV initiation polymerization the GTFX molecularly imprinted two-dimensional photonic crystal hydrogel (GTFX-MIPCH) sensor was prepared. The response performance of the hydrogel was investigated by measuring the diameter change of the Debye ring. The experimental results showed that the prepared GTFX-MIPCH has a sensitive response to GTFX. When the concentration of GTFX increases from 0 to 1 × 10 −4 mol L −1 , the diameter of the Debye ring decreases by 8.50 mm, the corresponding particle spacing increases by 29.1 nm, and the color of the sensor changes from purple to orange. Also there was a linear relationship between the change of particle spacing (Δd) and the logarithm of GTFX concentration (lg c) in the range 10 −12 -10 −6 mol L −1 . It is noteworthy that the limit of detection of GTFX-MIPCH is as low as 10 −14 mol L −1 . In addition, in a solution of GTFX analogues enrofloxacin, levofloxacin, ciprofloxacin and norfloxacin, the change of particle spacing of the GTFX-MIPCH sensor is 13.3, 11.6, 11.1 and 10.3 nm respectively, indicating that GTFX-MIPCH has good specific recognition ability for GTFX. Moreover, GTFX-MIPCH shows good reusability and can also be used for the detection of GTFX in water samples. This GTFX-MIPCH can achieve a visual detection effect on GTFX through the Debye ring and color change.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.