KEYWORDS: Point clouds, 3D image reconstruction, Feature extraction, 3D modeling, Image restoration, 3D image processing, 3D metrology, Convolution, RGB color model, Visualization
The creation of three-dimensional (3D) models is a challenging problem, and the existing point cloud-based reconstruction methods have achieved some success by directly generating a point cloud in a single stage. However, these methods have certain limitations and cannot accurately reconstruct 3D point cloud models with complex surface structures. We propose a learning-based reconstruction method to generate dense point clouds by learning multiple features of sparse point clouds. First, the image encoder embedded in the attention mechanism is used to improve the attention of the network to the target local area, and the decoder is used to generate a sparse point cloud. Second, a point cloud feature extraction block was designed to extract the effective features describing the sparse point cloud. Finally, the decoder was used to generate dense point clouds to complete the point cloud refinement. By evaluating the targets with different surface structures, verifying the effectiveness of the network by comparing with other reconstruction methods with different principles, and carrying out measurement experiments on real objects, the 3D error of the point cloud obtained is <2 mm, which meets the practical requirements.
Research into early data collection is often neglected, despite the growing focus on micro hyperspectral imaging technology in the medical field. Unfortunately, the data obtained from a single micro hyperspectral image is often limited in scope, making it hard to extract features and analyze spectral data of healthy cells. To address the above issues, a micro hyperspectral image stitching method based on RGB image layer feature localization and stitching is proposed, Extract the collected data into three RGB bands, perform feature extraction on them, calculate the horizontal offset, and complete the matching and stitching of microscopic hyperspectral images based on the coordinate position relationship.By employing the mean filtering technique, data fusion can be accomplished, thus allowing for the stitching of hyperspectral images on the micro dimension for spectral information.
In autonomous driving and other robotics, rich depth perception is critical for 3D reconstruction tasks of outdoor landscapes. Many neural networks combine sparse depth maps with high-quality RGB images to generate a dense effect, resulting in dense depth maps. However, they frequently combine LiDAR and RGB image data by conducting feature concatenation or element addition, which results in the loss of some features as well as changes to the depth values of the original sparse data. To address these issues, this article proposes that the relationship between spatial and channel attention be used to link local and global features in order to accurately complete and correct sparse input so that the RGB images can better lead the depth completion job. We also use an affinity matrix to keep the original depth values in order to make the RGB image simply act as a guide without modifying the original pixel depth. We tested and assessed our algorithm on the KITTI dataset, and it outperformed the existing network in outdoor situations.
Distances are the basic measures used in data clustering. The selection of the distance has a significant impact on the final result. Euclidean distances do not accurately reflect the actual geometrical properties of complex shape and structure, while the geodesic distance may give full consideration to their geometry. Therefore, in the registration process, geodesic distance is more appropriate in such cases. In this study, a multi-view point cloud registration method is proposed to solve the problem of low registration accuracy of objects with complex shape and structure. The method transforms the registration problem into a clustering problem, and the rigid transformation is updated while updating the centroids. Clustering and rigid transformation are alternately applied to the point cloud to achieve final registration results. The proposed method is validated by experiments using data from Stanford University's public datasets. Experimental results show better accuracy and robustness of the proposed method.
KEYWORDS: Clouds, Image segmentation, 3D modeling, Data modeling, Detection and tracking algorithms, Feature extraction, Neural networks, 3D acquisition, Statistical modeling, Process modeling
The segmentation of a point cloud on the roof plane is of great significance to the reconstruction of building models. However, the traditional segmentation methods segment the aerial point cloud of the roof, which cannot fully express the geometric structure of the roof, whereas the deep learning-based methods have problems such as too much manual annotation and training time. In this work, a plane segmentation method for a building roof based on the PointNet network combined with the random sample consensus (RANSAC) algorithm is proposed to directly segment the whole point cloud of the building, but it is not limited to the point cloud of the roof. With the proposed framework, the roof part is extracted from the building by an improved PointNet network, and then the roof semantic point cloud is segmented by the RANSAC algorithm to complete the roof extraction. Based on the experimental results gained from multiple building point clouds, it is shown that the proposed method achieves the segmentation of a roof on most multi-plane roof building point clouds and that it has strong practical value.
YOLO is a milestone algorithm of object detection, which is the first One-stage detector in deep learning era. In spite of its great improvement of detection speed, the detection accuracy is somewhat insufficient, especially for small targets. In this paper, U-shaped module based on YOLOv4 (U-YOLO) is proposed. First, multi-level features extracted by CSPDarknet using Feature Pyramid Network (FPN) are fused. Then, the fused features is fed into multiple U-shaped modules. Finally, feature maps consisting of the features from different U-shaped modules are gathered up to construct a feature pyramid for object detection. Experiment shows that the U-shaped module can improve the accuracy of YOLOv4.
The current 3D point cloud feature extraction algorithms are mostly based on geometric features of points. And the distribution of feature points is so messy to accurately locate. This paper proposes a point cloud feature extraction algorithm using 2D-3D transformation. By selecting three pairs of 2D image and 3D point cloud feature points, the conversion matrix of image and point cloud coordinates is calculated to establish a mapping relationship and then we realize the extraction of point cloud features. Experimental results show that compared with other algorithms, the algorithm proposed in this paper can extract the detailed features of point cloud more accurately.
This paper presents a 3D reconstruction method fusing structure from motion and laser scanning method. The precision of the 3D reconstruction is improved by combining point cloud obtained from different sensors. First, a scaled principal component analysis-iterative closest point (a scaled-PCA-ICP) algorithm is proposed to do the registration that can overcome the influence of large scale variance. Then, with the large scale factor, a recalculated registration center is proposed by region segmentation to realize the point cloud registration again. Finally, the two-view point clouds are robustly matched using the proposed optimization method to complete 3D color reconstruction of the outdoor large scenes. The proposed 3D reconstruction method is evaluated on the non-synchronous database of the real-world multi-view vision sequences obtained in an outdoor environment and laser scanner. The experiment results show improvements in both accuracy and efficiency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.