Geometric Information Research Articles

All-Printed Finger-Inspired Tactile Sensor Array for Microscale Texture Detection and 3D Reconstruction.

Electronic skins are expected to replicate a human-like tactile sense, which significantly detects surface information, including geometry, material, and temperature. Although most texture features can be sensed in the horizontal direction, the lack of effective approaches for detecting vertical properties limits the development of artificial skin based on tactile sensors. In this study, an all-printed finger-inspired tactile sensor array is developed to realize the 3D detection and reconstruction of microscale structures. A beam structure with a suspended multilayer membrane is proposed, and a tactile sensor array of 12 units arranged in a dual-column layout is developed. This architecture enables the tactile sensor array to obtain comprehensive geometric information of micro-textures, including 3D morphology and clearance characteristics, and optimizes the 3D reconstruction patterns by self-calibration. Moreover, an innovative screen-printing technology incorporating multilayer printing and sacrificial-layer techniques is adopted to print the entire device. In additon, a Braille recognition system utilizing this tactile sensor array is developed to interpret Shakespeare's quotes printed in Grade 2 Braille. The abovementioned demonstrations reveal an attractive future vision for endowing bioinspired robots with the unique capability of touching and feeling the microscale real world and reconstructing it in the cyber world.

MSFA-Net: A Multiscale Feature Aggregation Network for Semantic Segmentation of Historical Building Point Clouds

In recent years, research on the preservation of historical architecture has gained significant attention, where the effectiveness of semantic segmentation is particularly crucial for subsequent repair, protection, and 3D reconstruction. Given the sparse and uneven nature of large-scale historical building point cloud scenes, most semantic segmentation methods opt to sample representative subsets of points, often leading to the loss of key features and insufficient segmentation accuracy of architectural components. Moreover, the geometric feature information at the junctions of components is cluttered and dense, resulting in poor edge segmentation. Based on this, this paper proposes a unique semantic segmentation network design called MSFA-Net. To obtain multiscale features and suppress irrelevant information, a double attention aggregation module is first introduced. Then, to enhance the model’s robustness and generalization capabilities, a contextual feature enhancement and edge interactive classifier module are proposed to train edge features and fuse the context data. Finally, to evaluate the performance of the proposed model, experiments were conducted on a self-curated ancient building dataset and the S3DIS dataset, achieving OA values of 95.2% and 88.7%, as well as mIoU values of 86.2% and 71.6%, respectively, further confirming the effectiveness and superiority of the proposed method.

SRX Net: A point cloud segmentation framework based on surface representation and X-Net

We propose a novel unified point cloud segmentation framework called SRX Net. This framework is composed of our proposed SurRep Group module and X-Net architecture, reconstructing point cloud segmentation models from two aspects: point cloud surface representation and network architecture. The SurRep Group can model the local surface structure of the point cloud through structures such as the Ellipsoid Surface Representation and Umbrella Surface Representation, providing rich geometric information to the network. The XNet establishes an inverse encoding-decoding path to deepen the modeling of shallow semantics, solving the interference of shallow semantics on deep semantics in prediction in the U-Net architecture. It also introduces a GLFEnhancement module to enhance each point’s perception of global information. As a unified framework, SRX Net can improve the semantic segmentation effects of various existing models. Extensive experimental results show that our model produces more accurate segmentation edges and significantly reduces discrete predicted points. Based on Point Transformer, our SRX-PT Net achieves state-of-the-art performance of 72.1 mIoU on S3DIS, Scannet V2, and WCS3D datasets, respectively.

Terahertz deep learning fusion computed tomography

Terahertz (THz) tomographic imaging based on time-resolved THz signals has raised significant attention due to its non-invasive, non-destructive, non-ionizing, material-classification, and ultrafast-frame-rate nature for object exploration and inspection. However, the material and geometric information of the tested objects is inherently embedded in the highly distorted THz time-domain signals, leading to substantial computational complexity and the necessity for intricate multi-physics models to extract the desired information. To address this challenge, we present a THz multi-dimensional tomographic framework and multi-scale spatio-spectral fusion Unet (MS3-Unet), capable of fusing and collaborating the THz signals across diverse signal domains. MS3-Unet employs multi-scale branches to extract spatio-spectral features, which are subsequently processed through element-wise adaptive filters and fused to achieve high-quality THz image restoration. Evaluated by geometry-variant objects, MS3-Unet outperforms other peer methods in PSNR and SSIM. In addition to the superior performance, the proposed framework additionally provides high scalable, adjustable, and accessible interface to collaborate with different user-defined models or methods.

QuanDB: a quantum chemical property database towards enhancing 3D molecular representation learning.

Previous studies have shown that the three-dimensional (3D) geometric and electronic structure of molecules play a crucial role in determining their key properties and intermolecular interactions. Therefore, it is necessary to establish a quantum chemical (QC) property database containing the most stable 3D geometric conformations and electronic structures of molecules. In this study, a high-quality QC property database, called QuanDB, was developed, which included structurally diverse molecular entities and featured a user-friendly interface. Currently, QuanDB contains 154,610 compounds sourced from public databases and scientific literature, with 10,125 scaffolds. The elemental composition comprises nine elements: H, C, O, N, P, S, F, Cl, and Br. For each molecule, QuanDB provides 53 global and 5 local QC properties and the most stable 3D conformation. These properties are divided into three categories: geometric structure, electronic structure, and thermodynamics. Geometric structure optimization and single point energy calculation at the theoretical level of B3LYP-D3(BJ)/6-311G(d)/SMD/water and B3LYP-D3(BJ)/def2-TZVP/SMD/water, respectively, were applied to ensure highly accurate calculations of QC properties, with the computational cost exceeding 107 core-hours. QuanDB provides high-value geometric and electronic structure information for use in molecular representation models, which are critical for machine-learning-based molecular design, thereby contributing to a comprehensive description of the chemical compound space. As a new high-quality dataset for QC properties, QuanDB is expected to become a benchmark tool for the training and optimization of machine learning models, thus further advancing the development of novel drugs and materials. QuanDB is freely available, without registration, at https://quandb.cmdrg.com/ .

A Method for Measuring Spatial Information of Area Maps Considering the Diversity of Node–Edge and Gestalt Principles

Existing methods for measuring the spatial information of area maps fail to take into account the diversity of adjacency relations and the heterogeneity of adjacency distances among area objects, resulting in insufficient measurement information. This article proposes a method for measuring area map information that considers the diversity of the node–edge and Gestalt principles. Firstly, this method utilizes the adjacency relations between the Voronoi diagram of area objects to construct an adjacency graph that characterizes the spatial distribution of area objects in area maps. This adjacency graph serves as the information representation of area maps. Secondly, the method selects four characteristic indicators, namely geometric information, node degree, adjacency distance, and adjacency strength, to represent the diversity of nodes and edges in the graph that affect spatial information. Finally, nodes in the adjacency graph are taken as the basic units, and the spatial information of area maps is comprehensively calculated by integrating the four characteristics that represent spatial information. To verify the validity and rationality of the proposed method, a dataset of continuously simplified area maps and a dataset of artificially simulated degrees of randomness were designed to evaluate the performance of the existing method and the method proposed in this paper. The results indicate that the correlation between the measurement results obtained by the method proposed in this paper and the degree of disorder is as high as 0.94, outperforming the existing representative methods. Additionally, the correlation between the measurement results of this method and the degree of simplification reaches 1, indicating that the variation range of the measured values is more consistent with the cognitive assumptions based on artificial simulations compared to the existing methods. The experimental results show that the method proposed in this paper is an effective metric approach for representing spatial information in area maps.

Ship Detection in Maritime Scenes under Adverse Weather Conditions

Point cloud-based detection focuses on land traffic, rarely marine, facing issues with ships: it struggles in bad weather due to reliance on adverse weather data and fails to detect ships effectively due to overlooking size and appearance differences. Addressing the above challenges, our work introduces point cloud data of marine scenarios under realistically simulated adverse weather conditions and a dedicated Ship Detector tailored for marine environments. To adapt to various maritime weather conditions, we simulate realistic rain and fog in collected marine scene point cloud data. Additionally, addressing the issue of losing geometric and height information during feature extraction for large objects, we propose a Ship Detector. It employs a dual-branch sparse convolution layer for extracting multi-scale 3D feature maps, effectively minimizing height information loss. Additionally, a multi-scale 2D convolution module is utilized, which encodes and decodes feature maps and directly employs 3D feature maps for target prediction. To reduce dependency on existing data and enhance model robustness, our training dataset includes simulated point cloud data representing adverse weather conditions. In maritime point cloud ship detection, our Ship Detector, compared to adjusted small object detectors, demonstrates the best performance.

HALNet: Partial Point Cloud Registration Based on Hybrid Attention and Deep Local Features

Point cloud registration is an important task in computer vision and robotics which is widely used in 3D reconstruction, target recognition, and other fields. At present, many registration methods based on deep learning have better registration accuracy in complete point cloud registration, but partial registration accuracy is poor. Therefore, a partial point cloud registration network, HALNet, is proposed. Firstly, a feature extraction network consisting mainly of adaptive graph convolution (AGConv), two-dimensional convolution, and convolution block attention (CBAM) is used to learn the features of the initial point cloud. Then the overlapping estimation is used to remove the non-overlapping points of the two point clouds, and the hybrid attention mechanism composed of self-attention and cross-attention is used to fuse the geometric information of the two point clouds. Finally, the rigid transformation is obtained by using the fully connected layer. Five methods with excellent registration performance were selected for comparison. Compared with SCANet, which has the best registration performance among the five methods, the RMSE(R) and MAE(R) of HALNet are reduced by 10.67% and 12.05%. In addition, the results of the ablation experiment verify that the hybrid attention mechanism and fully connected layer are conducive to improving registration performance.

Multimodal protein representation learning and target-aware variational auto-encoders for protein-binding ligand generation

Without knowledge of specific pockets, generating ligands based on the global structure of a protein target plays a crucial role in drug discovery as it helps reduce the search space for potential drug-like candidates in the pipeline. However, contemporary methods require optimizing tailored networks for each protein, which is arduous and costly. To address this issue, we introduce TargetVAE, a target-aware variational auto-encoder that generates ligands with desirable properties including high binding affinity and high synthesizability to arbitrary target proteins, guided by a multimodal deep neural network built based on geometric and sequence models, named Protein Multimodal Network (PMN), as the prior for the generative model. PMN unifies different representations of proteins (e.g. primary structure—sequence of amino acids, 3D tertiary structure, and residue-level graph) into a single representation. Our multimodal architecture learns from the entire protein structure and is able to capture their sequential, topological, and geometrical information by utilizing language modeling, graph neural networks, and geometric deep learning. We showcase the superiority of our approach by conducting extensive experiments and evaluations, including predicting protein-ligand binding affinity in the PBDBind v2020 dataset as well as the assessment of generative model quality, ligand generation for unseen targets, and docking score computation. Empirical results demonstrate the promising and competitive performance of our proposed approach. Our software package is publicly available at https://github.com/HySonLab/Ligand_Generation.

K-nearest-neighbors induced topological PCA for single cell RNA-sequence data analysis

Single-cell RNA sequencing (scRNA-seq) is widely used to reveal heterogeneity in cells, which has given us insights into cell–cell communication, cell differentiation, and differential gene expression. However, analyzing scRNA-seq data is a challenge due to sparsity and the large number of genes involved. Therefore, dimensionality reduction and feature selection are important for removing spurious signals and enhancing downstream analysis. Traditional PCA, a main workhorse in dimensionality reduction, lacks the ability to capture geometrical structure information embedded in the data, and previous graph Laplacian regularizations are limited by the analysis of only a single scale. We propose a topological Principal Components Analysis (tPCA) method by the combination of persistent Laplacian (PL) technique and L2,1 norm regularization to address multiscale and multiclass heterogeneity issues in data. We further introduce a k-Nearest-Neighbor (kNN) persistent Laplacian technique to improve the robustness of our persistent Laplacian method. The proposed kNN-PL is a new algebraic topology technique which addresses the many limitations of the traditional persistent homology. Rather than inducing filtration via the varying of a distance threshold, we introduced kNN-tPCA, where filtrations are achieved by varying the number of neighbors in a kNN network at each step, and find that this framework has significant implications for hyper-parameter tuning. We validate the efficacy of our proposed tPCA and kNN-tPCA methods on 11 diverse benchmark scRNA-seq datasets, and showcase that our methods outperform other unsupervised PCA enhancements from the literature, as well as popular Uniform Manifold Approximation (UMAP), t-Distributed Stochastic Neighbor Embedding (tSNE), and Projection Non-Negative Matrix Factorization (NMF) by significant margins. For example, tPCA provides up to 628%, 78%, and 149% improvements to UMAP, tSNE, and NMF, respectively on classification in the F1 metric, and kNN-tPCA offers 53%, 63%, and 32% improvements to UMAP, tSNE, and NMF, respectively on clustering in the ARI metric.

Surface geometry inversion of transient electromagnetic data

We investigate an emerging method called surface geometry inversion (SGI) for the inversion of transient electromagnetic (TEM) data. Conventional minimum-structure inversion methods parameterize the Earth model with many mesh cells within which the physical properties are constant and construct a physical property model that is usually smoothly varying as well as fitting the observations. With these smooth models, it is difficult to extract the interface between different geological units, and it can be especially difficult to target drill holes for thin, plate-like targets which are frequently encountered in mineral exploration. Our SGI parameterizes the model in terms of the coordinates of the nodes (vertices) used to connect together the surfaces that define the geological interfaces. The algorithm then inverts for the locations of these nodes, which directly provides geometric information about the target. This can be more useful than a fuzzy image of conductivity, especially for an exploration project. A genetic algorithm (GA) is used to solve the non-linear over-determined optimization problem. We use a finite-element solver to solve the TEM forward modeling problem of each candidate model in the GA population. Because forward modeling is independent for each model, we implement a hybrid MPI + OpenMP parallel method to improve computational efficiency. We investigate a new parameterization method specifically designed for thin, plate-like structures, that is more efficient and can effectively avoid self-intersection. We first illustrate the effectiveness of our SGI algorithm on a synthetic block model before testing the new parameterization method on a synthetic thin plate model. Finally, we apply our SGI to a real dataset collected for the exploration of thin graphitic faults. The constructed model from our SGI corresponds well with the drilling data.

Building facade structure extraction method based on three-dimensional laser point cloud by considering semantic information

ABSTRACT Building facade structures serve as important data support for three-dimensional (3D) building modelling. A building facade structure extraction method based on 3D Laser Point Cloud Data (LPCD) by considering semantic information is proposed. The proposed method mainly involves three steps. First, an improved 3D LPCD semantic segmentation method is introduced to extract and label point clouds as the building structure and walls. Second, structure line segments are recognized from the initial building facade structure based on the Regulated Block RANSAC (RB-RANSAC) algorithm. Third, geometric information such as distance, vector and positional relationship between structure line segments is considered to optimize the initial building facade structure. The proposed method can effectively extract and fit segment structures by considering the semantic and geometric information, obtaining significantly accurate and concise building facade structures. Case studies on 3D LPCD of local buildings and open-source datasets (Semantic3D) prove the extraction accuracy and efficiency of the proposed method.

Hi-GeoMVP: a hierarchical geometry-enhanced deep learning model for drug response prediction.

Personalized cancer treatments require accurate drug response predictions. Existing deep learning methods show promise but higher accuracy is needed to serve the purpose of precision medicine. The prediction accuracy can be improved with not only topology but geometrical information of drugs. A novel deep learning methodology for drug response prediction is presented, named Hi-GeoMVP. It synthesizes hierarchical drug representation with multi-omics data, leveraging graph neural networks and variational autoencoders for detailed drug and cell line representations. Multi-task learning is employed to make better prediction, while both 2D and 3D molecular representations capture comprehensive drug information. Testing on the GDSC dataset confirms Hi-GeoMVP's enhanced performance, surpassing prior state-of-the-art methods by improving the Pearson correlation coefficient from 0.934 to 0.941 and decreasing the root mean square error from 0.969 to 0.931. In the case of blind test, Hi-GeoMVP demonstrated robustness, outperforming the best previous models with a superior Pearson correlation coefficient in the drug-blind test. These results underscore Hi-GeoMVP's capabilities in drug response prediction, implying its potential for precision medicine. The source code is available at https://github.com/matcyr/Hi-GeoMVP. Supplementary data is available at Bioinformatics online.

Geometrically-informed predictive modeling of melt pool depth in laser powder bed fusion using deep MLP-CNN and metadata integration

The laser powder bed fusion (LPBF) process has the ability to manufacture intricate geometries. However, the fabrication of complex geometries using the LPBF process for industrial applications remains challenging in terms of achieving consistent microstructure and mechanical properties. Experimental investigations show that in addition to process parameters, geometrical factors such as shape and size of parts impact the thermal history, microstructure, defect structure, and thus mechanical and fatigue properties. As a result, the standardization, qualification, and certification of additively manufactured (AM-ed) parts encounters substantial obstacles posed by the obscure impact of design parameters on component quality. In this paper, an artificial intelligence framework is proposed to predict the melt pool depth of the additively manufactured parts considering the geometrical information of the parts. More specifically, a deep Multilayer Perceptron and Convolutional Neural Network (MLP-CNN) framework is designed to predict melt pool depth for any part geometries when printing metallic parts via LPBF using metadata (i.e., numerical and image data). Quite often the melt pool depth generated during the AM processes is employed as a surrogate for thermal, defect- and micro-structural signatures. In melt pool depth prediction of complex geometries in LPBF, a digital twin environment using a finite element model (FEM) is developed and validated using experimental melt pool measurements for different geometries within multi-tracks and layers. The FEM was in agreement with experimentation with an error of less than 15%. Through the process simulation, a large dataset of melt pool depths was obtained for various part geometries and different process parameters. Next, the MLP-CNN framework was established to identify the parallel impact of part design and process parameters on melt pool depths. To enhance the performance and robustness of this model, data augmentation has been implemented by rotating and transferring geometries to artificially expand the dataset. Data augmentation helps to mitigate overfitting and promote better generalization, especially in the context of limited training data. After training, the proposed model is found to give accurate melt pool prediction even for new geometries not considered during training. The fusion of CNN and MLP has led the melt pool predictions for unseen geometries with an accuracy of 95%.

Relationships of Fire Rate of Spread with Spectral and Geometric Features Derived from UAV-Based Photogrammetric Point Clouds

Unmanned aerial vehicles (UAVs) equipped with RGB, multispectral, or thermal cameras have demonstrated their potential to provide high-resolution data before, during, and after wildfires and prescribed burns. Pre-burn point clouds generated through the photogrammetric processing of UAV images contain geometrical and spectral information of vegetation, while active fire imagery allows for deriving fire behavior metrics. This paper focuses on characterizing the relationship between the fire rate of spread (RoS) in prescribed burns and a set of independent geometrical, spectral, and neighborhood variables extracted from UAV-derived point clouds. For this purpose, different flights were performed before and during the prescribed burning in seven grasslands and open forest plots. Variables extracted from the point cloud were interpolated to a grid, which was sized according to the RoS semivariogram. Random Forest regressions were applied, obtaining up to 0.56 of R2 in the different plots studied. Geometric variables from the point clouds, such as planarity and the spectral normalized blue–red difference index (NBRDI), are related to fire RoS. In analyzing the results, the minimum value of the eigenentropy (Eigenentropy_MIN), the mean value of the planarity (Planarity_MEAN), and percentile 75 of the NBRDI (NBRDI_P75) obtained the highest feature importance. Plot-specific analyses unveiled distinct combinations of geometric and spectral features, although certain features, such as Planarity_MEAN and the mean value of the grid obtained from the standard deviation of the distance between points (Dist_std_MEAN), consistently held high importance across all plots. The relationships between pre-burning UAV data and fire RoS can complement meteorological and topographic variables, enhancing wildfire and prescribed burn models.

Semi-automatic algorithm to build finite element numerical models of the human hearing system from Micro-CT data.

Finite Element modeling has been an extended methodology to build numerical model to simulate the behavior of the hearing system. Due to the complexity of the system and the difficulties to reduce the uncertainties of the geometric data, they result in computationally expensive models, sometimes generic, representative of average geometries. It makes it difficult to validate the model with direct experimental data from the same specimen or to establish a patient-oriented modeling strategy. In the present paper, a first attempt to automatize the process of model building is made. The source information is geometrical information obtained from CT of the different elements that compose the system. Importing that data, we have designed the complete procedure to build a model including tympanic membrane, ossicular chain and cavities. The methodology includes the proper coupling of all the elements and the generation of the corresponding finite element model. The whole automatic procedure is not complete, as we need to make some human-assisted decisions; however, the model development time is reduced from 4 weeks to approximately 3 days. The goal of the modeling algorithm is to build a Finite Element Model with a limited computational cost. Several tasks as contour identification or model decimation are designed and integrated in order to follow a semi-automated process that allows generating a patient-oriented model.

Minimum Information Variability in Linear Langevin Systems via Model Predictive Control.

Controlling the time evolution of a probability distribution that describes the dynamics of a given complex system is a challenging problem. Achieving success in this endeavour will benefit multiple practical scenarios, e.g., controlling mesoscopic systems. Here, we propose a control approach blending the model predictive control technique with insights from information geometry theory. Focusing on linear Langevin systems, we use model predictive control online optimisation capabilities to determine the system inputs that minimise deviations from the geodesic of the information length over time, ensuring dynamics with minimum "geometric information variability". We validate our methodology through numerical experimentation on the Ornstein-Uhlenbeck process and Kramers equation, demonstrating its feasibility. Furthermore, in the context of the Ornstein-Uhlenbeck process, we analyse the impact on the entropy production and entropy rate, providing a physical understanding of the effects of minimum information variability control.

Molecular hypergraph neural networks.

Graph neural networks (GNNs) have demonstrated promising performance across various chemistry-related tasks. However, conventional graphs only model the pairwise connectivity in molecules, failing to adequately represent higher order connections, such as multi-center bonds and conjugated structures. To tackle this challenge, we introduce molecular hypergraphs and propose Molecular Hypergraph Neural Networks (MHNNs) to predict the optoelectronic properties of organic semiconductors, where hyperedges represent conjugated structures. A general algorithm is designed for irregular high-order connections, which can efficiently operate on molecular hypergraphs with hyperedges of various orders. The results show that MHNN outperforms all baseline models on most tasks of organic photovoltaic, OCELOT chromophore v1, and PCQM4Mv2 datasets. Notably, MHNN achieves this without any 3D geometric information, surpassing the baseline model that utilizes atom positions. Moreover, MHNN achieves better performance than pretrained GNNs under limited training data, underscoring its excellent data efficiency. This work provides a new strategy for more general molecular representations and property prediction tasks related to high-order connections.

A geometric modelling approach to estimate apple fruit size by means of LiDAR 3D point clouds

ABSTRACT Remote sensing in agriculture aims to search new methods to monitor fruit at the tree, thus improving the estimation of yield-related variables. Light detection and range (LiDAR) scanning was introduced to obtain geometric and radiometric information from fruit surfaces by means of 3D point clouds. A geometric model to estimate apple size by means of segmented 3D point cloud of fruit is proposed in the present study. The model consists in the approximation of 3D point clouds to a reference shape given by 2D Fourier series expansion. Each point cloud was approximated to its reference shape using an iterative error minimization routine. The geometric model was applied to laboratory and field data of spheres and apples during fruit growth, ranging from 60 to 151 days after full bloom (DAFB). An overall RMSE between measured and predicted fruit radius of 20.1, 76.8, and 119.1% was found for the geometric model, mean, and maximum Euclidean distance approaches, respectively, including all studied growth periods in field conditions. Moreover, the linear regression on measured and predicted values showed considerably improved coefficient of determination ( R 2 ) of the geometric model in comparison to Euclidean distance calculations with R 2 values of 0.76 and 0.49 for laboratory and field scanned apples, respectively. The data processing method enables fruit monitoring and their application of terrestrial LiDAR sensing in precise orchard management.

Localization of asparagus spears using time-of-flight imaging for robotic harvesting

Purpose Time of flight (ToF) imaging is a promising emerging technology for the purposes of crop identification. This paper aim to presents localization system for identifying and localizing asparagus in the field based on point clouds from ToF imaging. Since the semantics are not included in the point cloud, it contains the geometric information of other objects such as stones and weeds other than asparagus spears. An approach is required for extracting the spear information so that a robotic system can be used for harvesting. Design/methodology/approach A real-time convolutional neural network (CNN)-based method is used for filtering the point cloud generated by a ToF camera, allowing subsequent processing methods to operate over smaller and more information-dense data sets, resulting in reduced processing time. The segmented point cloud can then be split into clusters of points representing each individual spear. Geometric filters are developed to eliminate the non-asparagus points in each cluster so that each spear can be modelled and localized. The spear information can then be used for harvesting decisions. Findings The localization system is integrated into a robotic harvesting prototype system. Several field trials have been conducted with satisfactory performance. The identification of a spear from the point cloud is the key to successful localization. Segmentation and clustering points into individual spears are two major failures for future improvements. Originality/value Most crop localizations in agricultural robotic applications using ToF imaging technology are implemented in a very controlled environment, such as a greenhouse. The target crop and the robotic system are stationary during the localization process. The novel proposed method for asparagus localization has been tested in outdoor farms and integrated with a robotic harvesting platform. Asparagus detection and localization are achieved in real time on a continuously moving robotic platform in a cluttered and unstructured environment.