Explore the vast range of titles available.

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer (PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

LiDAR is a commonly used sensor for autonomous driving to make accurate, robust, and fast decision-making when driving. The sensor is used in the perception system, especially object detection, to understand the driving environment. Although 2D object detection has succeeded during the deep-learning era, the lack of depth information limits understanding of the driving environment and object location. Three-dimensional sensors, such as LiDAR, give 3D information about the surrounding environment, which is essential for a 3D perception system. Despite the attention of the computer vision community to 3D object detection due to multiple applications in robotics and autonomous driving, there are challenges, such as scale change, sparsity, uneven distribution of LiDAR data, and occlusions. Different representations of LiDAR data and methods to minimize the effect of the sparsity of LiDAR data have been proposed. This survey presents the LiDAR-based 3D object detection and feature-extraction techniques for LiDAR data. The 3D coordinate systems differ in camera and LiDAR-based datasets and methods. Therefore, the commonly used 3D coordinate systems are summarized. Then, state-of-the-art LiDAR-based 3D object-detection methods are reviewed with a selected comparison among methods.

As unmanned aerial vehicles (UAVs) are increasingly employed across various industries, the demand for robust and accurate detection has become crucial. Light detection and ranging (LiDAR) has developed as a vital sensor technology due to its ability to provide rich 3D spatial information, particularly in applications such as security and airspace monitoring. This review systematically explores recent innovations in LiDAR-based drone detection, deeply focusing on the principles and components of LiDAR sensors, their classifications based on different parameters and scanning mechanisms, and the approaches for processing LiDAR data. The review briefly compares recent research works in LiDAR-based only and its fusion with other sensor modalities, the real-world applications of LiDAR with deep learning, as well as the major challenges in sensor fusion-based UAV detection.

This work presents an in-situ quality assessment and improvement technique using point cloud and AI for data processing and smart decision making in Additive Manufacturing (AM) fabrication to improve the quality and accuracy of fabricated artifacts. The top surface point-cloud containing top surface geometry and quality information is pre-processed and passed to an improved deep Hybrid Convolutional Auto-Encoder decoder (HCAE) model used to statistically describe the artifact's quality. The HCAE’s output is comprised of 9 × 9 segments, each including four channels with the segment's probability to contain one of four labels, Under-printed, Normally-printed, Over-printed, or Empty region. This data structure plays a significant role in command generation for fabrication process optimization. The HCAE’s accuracy and repeatability were measured by a multi-label multi-output metric developed in this study. The HCAE’s results are used to perform a real-time process adjustment by manipulating the future layer's fabrication through the G-code modification. By adjusting the machine's print speed and feed-rate, the controller exploits the subsequent layer’s deposition, grid-by-grid. The algorithm is then tested with two defective process plans: severe under-extrusion and over-extrusion conditions. Both test artifacts' quality advanced significantly and converged to an acceptable state by four iterations.

Three-dimensional object detection utilizing LiDAR point cloud data is an indispensable part of autonomous driving perception systems. Point cloud-based 3D object detection has been a better replacement for higher accuracy than cameras during nighttime. However, most LiDAR-based 3D object methods work in a supervised manner, which means their state-of-the-art performance relies heavily on a large-scale and well-labeled dataset, while these annotated datasets could be expensive to obtain and only accessible in the limited scenario. Transfer learning is a promising approach to reduce the large-scale training datasets requirement, but existing transfer learning object detectors are primarily for 2D object detection rather than 3D. In this work, we utilize the 3D point cloud data more effectively by representing the birds-eye-view (BEV) scene and propose a transfer learning based point cloud semantic segmentation for 3D object detection. The proposed model minimizes the need for large-scale training datasets and consequently reduces the training time. First, a preprocessing stage filters the raw point cloud data to a BEV map within a specific field of view. Second, the transfer learning stage uses knowledge from the previously learned classification task (with more data for training) and generalizes the semantic segmentation-based 2D object detection task. Finally, 2D detection results from the BEV image have been back-projected into 3D in the postprocessing stage. We verify results on two datasets: the KITTI 3D object detection dataset and the Ouster LiDAR-64 dataset, thus demonstrating that the proposed method is highly competitive in terms of mean average precision (mAP up to 70%) while still running at more than 30 frames per second (FPS).

Understanding 3D scenes is a critical prerequisite for autonomous agents. Recently, LiDAR and other sensors have made large amounts of data available in the form of temporal sequences of point cloud frames. In this work, we propose a novel problem—sequential scene flow estimation (SSFE)—that aims to predict 3D scene flow for all pairs of point clouds in a given sequence. This is unlike the previously studied problem of scene flow estimation which focuses on two frames. We introduce the SPCM-Net architecture, which solves this problem by computing multi-scale spatiotemporal correlations between neighboring point clouds and then aggregating the correlation across time with an order-invariant recurrent unit. Our experimental evaluation confirms that recurrent processing of point cloud sequences results in significantly better SSFE compared to using only two frames. Additionally, we demonstrate that this approach can be effectively modified for sequential point cloud forecasting (SPF), a related problem that demands forecasting future point cloud frames. Our experimental results are evaluated using a new benchmark for both SSFE and SPF consisting of synthetic and real datasets. Previously, datasets for scene flow estimation have been limited to two frames. We provide non-trivial extensions to these datasets for multi-frame estimation and prediction. Due to the difficulty of obtaining ground truth motion for real-world datasets, we use self-supervised training and evaluation metrics. We believe that this benchmark will be pivotal to future research in this area. All code for benchmark and models will be made accessible at (https://github.com/BestSonny/SPCM).

With the advancement of 3D sensing technologies, point clouds are gradually becoming the main type of data representation in applications such as autonomous driving, robotics, and augmented reality. Nevertheless, the irregularity inherent in point clouds presents numerous challenges for traditional deep learning frameworks. Graph neural networks (GNNs) have demonstrated their tremendous potential in processing graph-structured data and are widely applied in various domains including social media data analysis, molecular structure calculation, and computer vision. GNNs, with their capability to handle non-Euclidean data, offer a novel approach for addressing these challenges. Additionally, drawing inspiration from the achievements of transformers in natural language processing, graph transformers have propelled models towards global awareness, overcoming the limitations of local aggregation mechanisms inherent in early GNN architectures. This paper provides a comprehensive review of GNNs and graph-based methods in point cloud applications, adopting a task-oriented perspective to analyze this field. We categorize GNN methods for point clouds based on fundamental tasks, such as segmentation, classification, object detection, registration, and other related tasks. For each category, we summarize the existing mainstream methods, conduct a comprehensive analysis of their performance on various datasets, and discuss the development trends and future prospects of graph-based methods.

Remote sensing in structural diagnostics has recently been gaining attention. These techniques allow the creation of three-dimensional projections of the measured objects, and are relatively easy to use. One of the most popular branches of remote sensing is terrestrial laser scanning. Laser scanners are fast and efficient, gathering up to one million points per second. However, the weakness of terrestrial laser scanning is the troublesome processing of point clouds. Currently, many studies deal with the subject of point cloud processing in various areas, but it seems that there are not many clear procedures that we can use in practice, which indicates that point cloud processing is one of the biggest challenges of this issue. To tackle that challenge we propose a general framework for studying the structural deformations of bridges. We performed an advanced object shape analysis of a composite foot-bridge, which is subject to spatial deformations during the proof loading process. The added value of this work is the comprehensive procedure for bridge evaluation, and adaptation of the spheres translation method procedure for use in bridge engineering. The aforementioned method is accurate for the study of structural element deformation under monotonic load. The study also includes a comparative analysis between results from the spheres translation method, a total station, and a deflectometer. The results are characterized by a high degree of convergence and reveal the highly complex state of deformation more clearly than can be concluded from other measurement methods, proving that laser scanning is a good method for examining bridge structures with several competitive advantages over mainstream measurement methods.

Crop leaf length, perimeter, and area serve as vital phenotypic indicators of crop growth status, the measurement of which is important for crop monitoring and yield estimation. However, processing a leaf point cloud is often challenging due to cluttered, fluctuating, and uncertain points, which culminate in inaccurate measurements of leaf phenotypic parameters. To tackle this issue, the RKM-D point cloud method for measuring leaf phenotypic parameters is proposed, which is based on the fusion of improved Random Sample Consensus with a ground point removal (R) algorithm, the K-means clustering (K) algorithm, the Moving Least Squares (M) method, and the Euclidean distance (D) algorithm. Pepper leaves were obtained from three growth periods on the 14th, 28th, and 42nd days as experimental subjects, and a stereo camera was employed to capture point clouds. The experimental results reveal that the RKM-D point cloud method delivers high precision in measuring leaf phenotypic parameters. (i) For leaf length, the coefficient of determination (R2) surpasses 0.81, the mean absolute error (MAE) is less than 3.50 mm, the mean relative error (MRE) is less than 5.93%, and the root mean square error (RMSE) is less than 3.73 mm. (ii) For leaf perimeter, the R2 surpasses 0.82, the MAE is less than 7.30 mm, the MRE is less than 4.50%, and the RMSE is less than 8.37 mm. (iii) For leaf area, the R2 surpasses 0.97, the MAE is less than 64.66 mm2, the MRE is less than 4.96%, and the RMSE is less than 73.06 mm2. The results show that the proposed RKM-D point cloud method offers a robust solution for the precise measurement of crop leaf phenotypic parameters.

Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. However, objects in indoor scenes are usually related to each other and the scene, forming the contextual information. Based on this observation, we propose a novel 3D object detection network, which is built on the state-of-the-art VoteNet but takes into consideration of the contextual information at multiple levels for detection and recognition of 3D objects. To encode relationships between elements at different levels, we introduce three contextual sub-modules, capturing contextual information at patch, object, and scene levels respectively, and build them into the voting and classification stages of VoteNet. In addition, at the post-processing stage, we also consider the spatial diversity of detected objects and propose an improved 3D NMS (non-maximum suppression) method, namely Survival-Of-the-Best 3DNMS (SOB-3DNMS), to reduce false detections. Experiments demonstrate that our method is an effective way to promote detection accuracy, and has achieved new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet, when only taking point cloud data as input.