Intelligent Point Cloud Edge Detection Method Based on Projection Transformation

An edge detection method based on projection transformation is proposed. First, the vertical projection transformation is carried out on the target point cloud. Data X and data Y are normalized to the width and height of the image, respectively. Data Z is normalized to the range of 0-255, and the depth represents the gray level of the image. Then, the Canny algorithm is used to detect the edge of the projection transformed image, and the detected edge data is back projected to extract the edge point cloud in the point cloud. Evaluate the performance by calculating the normal vector of the edge point cloud. Compared with the normal vector of the whole data point cloud of the target, the normal vector of the edge point cloud can well express the characteristics of the target, and the calculation time is reduced to 10% of the original.

Deep Learning-Based Point Upsampling for Edge Enhancement of 3D-Scanned Data and Its Application to Transparent Visualization

Large-scale 3D-scanned point clouds enable the accurate and easy recording of complex 3D objects in the real world. The acquired point clouds often describe both the surficial and internal 3D structure of the scanned objects. The recently proposed edge-highlighted transparent visualization method is effective for recognizing the whole 3D structure of such point clouds. This visualization utilizes the degree of opacity for highlighting edges of the 3D-scanned objects, and it realizes clear transparent viewing of the entire 3D structures. However, for 3D-scanned point clouds, the quality of any edge-highlighting visualization depends on the distribution of the extracted edge points. Insufficient density, sparseness, or partial defects in the edge points can lead to unclear edge visualization. Therefore, in this paper, we propose a deep learning-based upsampling method focusing on the edge regions of 3D-scanned point clouds to generate more edge points during the 3D-edge upsampling task. The proposed upsampling network dramatically improves the point-distributional density, uniformity, and connectivity in the edge regions. The results on synthetic and scanned edge data show that our method can improve the percentage of edge points more than 15% compared to the existing point cloud upsampling network. Our upsampling network works well for both sharp and soft edges. A combined use with a noise-eliminating filter also works well. We demonstrate the effectiveness of our upsampling network by applying it to various real 3D-scanned point clouds. We also prove that the improved edge point distribution can improve the visibility of the edge-highlighted transparent visualization of complex 3D-scanned objects.

Machine Learning Optimised Hyperspectral Remote Sensing Retrieves Cotton Nitrogen Status

Hyperspectral imaging spectrometers mounted on unmanned aerial vehicle (UAV) can capture high spatial and spectral resolution to provide cotton crop nitrogen status for precision agriculture. The aim of this research was to explore machine learning use with hyperspectral datacubes over agricultural fields. Hyperspectral imagery was collected over a mature cotton crop, which had high spatial (~5.2 cm) and spectral (5 nm) resolution over the spectral range 475–925 nm that allowed discrimination of individual crop rows and field features as well as a continuous spectral range for calculating derivative spectra. The nominal reflectance and its derivatives clearly highlighted the different treatment blocks and were strongly related to N concentration in leaf and petiole samples, both in traditional vegetation indices (e.g., Vogelman 1, R2 = 0.8) and novel combinations of spectra (R2 = 0.85). The key hyperspectral bands identified were at the red-edge inflection point (695–715 nm). Satellite multispectral was compared against the UAV hyperspectral remote sensing’s performance by testing the ability of Sentinel MSI to predict N concentration using the bands in VIS-NIR spectral region. The Sentinel 2A Green band (B4; mid-point 559.8 nm) explained the same amount of variation in N as the hyperspectral data and more than the Sentinel Red Edge Point 1 (B5; mid-point 704.9 nm) with the lower 10 m resolution Green band reporting an R2 = 0.85, compared with the R2 = 0.78 of downscaled Sentinel Red Edge Point 1 at 5 m. The remaining Sentinel bands explained much lower variation (maximum was NIR at R2 = 0.48). Investigation of the red edge peak region in the first derivative showed strong promise with RIDAmid (R2 = 0.81) being the best index. The machine learning approach narrowed the range of bands required to investigate plant condition over this trial site, greatly improved processing time and reduced processing complexity. While Sentinel performed well in this comparison and would be useful in a broadacre crop production context, the impact of pixel boundaries relative to a region of interest and coarse spatial and temporal resolution impacts its utility in a research capacity.

Non-Metallic Impurities in Continuous Cast Billets

Non-metallic impurities in continuous cast billets are evaluated by a growth rate of edge point impurities. The first part of our research was devoted to a relationship between the growth rate of edge point impurities and other macrostructure defects. A correlation-regression analysis of steel macrostructure quality showed the relationship between the rate of edge point impurities and segregation cracks in general, as well as corner streaks. The second part of our research indicated that impurities in billets from conventional carbon steel were crucially influenced by a method of pouring steel from a tundish into a mould. By transferring from open stream casting to shrouded casting, the quantity of non-metallic impurities in billets decreases by 7 times. In case of open stream casting, prevailing inclusions are oxides resulting from secondary oxidation, while the growth rate of edge point impurities in billets increases with an increased content of sulphur and phosphorus in steel, and decreases with an increased manganese/sulphur ratio. In case of shrouded casting, non-metallic impurities are limited to casting temperature and speed: steel overheating in the tundish above the liquidus temperature and withdrawal speed of billets. Less non-metallic impurities in case of the shrouded casting are contributed by steel overheating in the tundish above the liquidus temperature over 30oС and withdrawal speed, not exceeding 2.5 m/min.

Analysis of pile spacing considering end-bearing soil arching and friction soil arching

The soil arching effect is an important premise for anti-slide piles to exert the retaining ability. Pile space is an essential factor for the design of piles and is related to the soil arching behind piles. However, previous studies rarely considered the friction soil arching effect between piles and regarded the axis stress uniformly distributed. In this research, a method considering end-bearing soil arching and friction soil arching simultaneously was proposed to calculate the reasonable pile spacing. The said method considered the general shear failure and the yielding failure of these two soil arching. The yielding stress of inner-edge point and outer-edge point at arch-foot of the end-bearing soil arching were taken into consideration respectively. Based on the ultimate balance theory, the controlling equations of pile spacing were established. The case study showed that the method in this research conforms better to practice compared to previous researches. Matlab programming was employed to realize the automatic calculation.