The truncated signed distance field (TSDF) has been applied as a fast, accurate, and flexible geometric fusion method in 3D reconstruction of industrial products based on a hand-held laser line scanner. However, this method has some problems for the surface reconstruction of thin products. The surface mesh will collapse to the interior of the model, resulting in some topological errors, such as overlap, intersections, or gaps. Meanwhile, the existing TSDF method ensures real-time performance through significant graphics processing unit (GPU) memory usage, which limits the scale of reconstruction scene. In this work, we propose three improvements to the existing TSDF methods, including: (i) a thin surface attribution judgment method in real-time processing that solves the problem of interference between the opposite sides of the thin surface; we distinguish measurements originating from different parts of a thin surface by the angle between the surface normal and the observation line of sight; (ii) a post-processing method to automatically detect and repair the topological errors in some areas where misjudgment of thin-surface attribution may occur; (iii) a framework that integrates the central processing unit (CPU) and GPU resources to implement our 3D reconstruction approach, which ensures real-time performance and reduces GPU memory usage. The proposed results show that this method can provide more accurate 3D reconstruction of a thin surface, which is similar to the state-of-the-art laser line scanners with 0.02 mm accuracy. In terms of performance, the algorithm can guarantee a frame rate of more than 60 frames per second (FPS) with the GPU memory footprint under 500 MB. In total, the proposed method can achieve a real-time and high-precision 3D reconstruction of a thin surface.

Seed geometric parameters are important in yielding trait scorers, quantitative trait loci, and species recognition and classification. A novel method for automatic measurement of three-dimensional seed phenotypes is proposed. First, a handheld three-dimensional (3D) laser scanner is employed to obtain the seed point cloud data in batches. Second, a novel point cloud-based phenotyping method is proposed to obtain a single-seed 3D model and extract 33 phenotypes. It is connected by an automatic pipeline, including single-seed segmentation, pose normalization, point cloud completion by an ellipse fitting method, Poisson surface reconstruction, and automatic trait estimation. Finally, two statistical models (one using 11 size-related phenotypes and the other using 22 shape-related phenotypes) based on the principal component analysis method are built. A total of 3400 samples of eight kinds of seeds with different geometrical shapes are tested. Experiments show: (1) a single-seed 3D model can be automatically obtained with 0.017 mm point cloud completion error; (2) 33 phenotypes can be automatically extracted with high correlation compared with manual measurements (correlation coefficient (R²) above 0.9981 for size-related phenotypes and R² above 0.8421 for shape-related phenotypes); and (3) two statistical models are successfully built to achieve seed shape description and quantification.

This article proposes a two-stage simultaneous localization and mapping (SLAM) method based on using the red green blue-depth (RGB-D) camera in dynamic environments, which can not only improve tracking robustness and trajectory accuracy but also reconstruct a clean and dense static background model in dynamic environments. In the first stage, to accurately exclude the interference of features in the dynamic region from the tracking, the dynamic object mask is extracted by Mask-RCNN and optimized by using the connected component analysis method and a reference frame-based method. Then, the feature points, lines, and planes in the nondynamic object area are used to construct an optimization model to improve the tracking accuracy and robustness. After the tracking is completed, the mask is further optimized by the multiview projection method. In the second stage, to accurately obtain the pending area, which contains the dynamic object area and the newly added area in each frame, a method is proposed, which is based on a ray-casting algorithm and fully uses the result of the first stage. To extract the static region from the pending region, this paper designs divisible and indivisible regions process methods and the bounding box tracking method. Then, the extracted static regions are merged into the map using the truncated signed distance function method. Finally, the clean static background model is obtained. Our methods have been verified on public datasets and real scenes. The results show that the presented methods achieve comparable or better trajectory accuracy and the best robustness, and can construct a clean static background model in a dynamic scene.