Estimating and approaching the maximum information rate of noninvasive visual brain-computer interface.

An essential priority of visual brain-computer interfaces (BCIs) is to enhance the information transfer rate (ITR) to achieve high-speed communication. Despite notable progress, noninvasive visual BCIs have encountered a plateau in ITRs, leaving it uncertain whether higher ITRs are achievable. In this study, we used information theory to study the characteristics and capacity of the visual-evoked channel, which leads us to investigate whether and how we can decode higher information rates in a visual BCI system. Using information theory, we estimate the upper and lower bounds of the information rate with the white noise (WN) stimulus. Consequently, we found out that the information rate is determined by the signal-to-noise ratio (SNR) in the frequency domain, which reflects the spectrum resources of the channel. Based on this discovery, we propose a broadband WN BCI by implementing stimuli on a broader frequency band than the steady-state visual evoked potentials (SSVEPs)-based BCI. Through validation, the broadband BCI outperforms the SSVEP BCI by an impressive 7 bps, setting a record of 50 bps. The integration of information theory and the decoding analysis presented in this study offers valuable insights applicable to general sensory-evoked BCIs, providing a potential direction of next-generation human-machine interaction systems.

EEG signatures of cognitive decline after mild SARS-CoV-2 infection: an age-dependent study.

BACKGROUND: Current research on the neurological impact of SARS-CoV-2 primarily focuses on the elderly or severely ill individuals. This study aims to explore the diverse neurological consequences of SARS-CoV-2 infection, with a particular focus on mildly affected children and adolescents. METHODS: A cohort study was conducted to collect pre- and post-infection resting-state electroencephalogram (EEG) data from 185 participants and 181 structured questionnaires of long-term symptoms across four distinct age groups. The goal was to comprehensively evaluate the impact of SARS-CoV-2 infection on these different age demographics. The study analyzed EEG changes of SARS-CoV-2 by potential biomarkers across age groups using both spatial and temporal approaches. RESULTS: Spatial analysis indicated that children and adolescents exhibit smaller changes in brain network and microstate patterns post-infection, implying a milder cognitive impact. Sequential linear analyses showed that SARS-CoV-2 infection is associated with a marked rise in low-complexity, synchronized neural activity within low-frequency EEG bands. This is evidenced by a significant increase in Hjorth activity within the theta band and Hjorth mobility in the delta band. Sequential nonlinear analysis indicated a significant reduction in the Hurst exponent across all age groups, pointing to increased chaos and complexity within the cognitive system following infection. Furthermore, linear regression analysis based on questionnaires established a significant positive relationship between the magnitude of changes in these neural indicators and the persistence of long-term symptoms post-infection. CONCLUSIONS: The findings underscore the enduring neurological impacts of SARS-CoV-2 infection, marked by cognitive decline and increased EEG disarray. Although children and adolescents experienced milder effects, cognitive decline and heightened low-frequency electrical activity were evident. These observations might contribute to understanding potential anxiety, insomnia, and neurodevelopmental implications.

EEG measurement for the effect of perceptual eye position and eye position training on comitant strabismus.

One of the clinical features of comitant strabismus is that the deviation angles in the first and second eye positions are equal. However, there has been no report of consistency in the electroencephalography (EEG) signals between the 2 positions. In order to address this issue, we developed a new paradigm based on perceptual eye position. We collected steady-state visual evoked potentials (SSVEPs) signals and resting-state EEG data before and after the eye position training. We found that SSVEP signals could characterize the suppression effect and eye position effect of comitant strabismus, that is, the SSVEP response of the dominant eye was stronger than that of the strabismus eye in the first eye position but not in the second eye position. Perceptual eye position training could modulate the frequency band activities in the occipital and surrounding areas. The changes in the visual function of comitant strabismus after training could also be characterized by SSVEP. There was a correlation between intermodulation frequency, power of parietal electrodes, and perceptual eye position, indicating that EEG might be a potential indicator for evaluating strabismus visual function.

A new strategy of using periphyton to simultaneously promote remediation of PAHs-contaminated soil and production of safer crops.

Contaminated farmland leads to serious problems for human health through biomagnification in the soil-crop-human chain. In this paper, we have established a new soil remediation strategy using periphyton for the production of safer rice. Four representative polycyclic aromatic hydrocarbons (PAHs), including phenanthrene (Phe), pyrene (Pyr), benzo[b]fluoranthene (BbF), and benzo[a]pyrene (BaP), were chosen to generate artificially contaminated soil. Pot experiments demonstrated that in comparison with rice cultivation in polluted soil with ΣPAHs (50 mg kg-1) but without periphyton, adding periphyton decreased ΣPAHs contents in both rice roots and shoots by 98.98% and 99.76%, respectively, and soil ΣPAHs removal reached 94.19%. Subsequently, risk assessment of ΣPAHs based on toxic equivalent concentration (TEQ), pollution load index (PLI), hazard index (HI), toxic unit for PAHs mixture (TUm), and incremental lifetime cancer risk (ILCR) indicated that periphyton lowered the ecological and carcinogenicity risks of PAHs. Besides, the role of periphyton in enhancing the rice productivity was revealed. The results indicated that periphyton alleviated the oxidative stress of PAHs on rice by reducing malondialdehyde (MDA) content and increasing total antioxidant capacity (T-AOC). Periphyton reduced the toxic stress of PAHs on the soil by promoting soil carbon cycling and metabolic activities as well. Periphyton also improved the soil's physicochemical properties, such as the percentage of soil aggregate, the contents of humic substances (HSs) and nutrients, which increased rice biomass. These findings confirmed that periphyton could improve rice productivity by enhancing soil quality and health. This study provides a new eco-friendly strategy for soil remediation and simultaneously enables the production of safe crops on contaminated land.

Improved YOLOv8-Based Target Precision Detection Algorithm for Train Wheel Tread Defects.

Train wheels are crucial components for ensuring the safety of trains. The accurate and fast identification of wheel tread defects is necessary for the timely maintenance of wheels, which is essential for achieving the premise of conditional repair. Image-based detection methods are commonly used for detecting tread defects, but they still have issues with the misdetection of water stains and the leaking of small defects. In this paper, we address the challenges posed by the detection of wheel tread defects by proposing improvements to the YOLOv8 model. Firstly, the impact of water stains on tread defect detection is avoided by optimising the structure of the detection layer. Secondly, an improved SPPCSPC module is introduced to enhance the detection of small targets. Finally, the SIoU loss function is used to accelerate the convergence speed of the network, which ensures defect recognition accuracy with high operational efficiency. Validation was performed on the constructed tread defect dataset. The results demonstrate that the enhanced YOLOv8 model in this paper outperforms the original network and significantly improves the tread defect detection indexes. The average precision, accuracy, and recall reached 96.95%, 96.30%, and 95.31%.

Clique-like Point Cloud Registration: A Flexible Sampling Registration Method Based on Clique-like for Low-Overlapping Point Cloud.

Three-dimensional point cloud registration is a critical task in 3D perception for sensors that aims to determine the optimal alignment between two point clouds by finding the best transformation. Existing methods like RANSAC and its variants often face challenges, such as sensitivity to low overlap rates, high computational costs, and susceptibility to outliers, leading to inaccurate results, especially in complex or noisy environments. In this paper, we introduce a novel 3D registration method, CL-PCR, inspired by the concept of maximal cliques and built upon the SC2-PCR framework. Our approach allows for the flexible use of smaller sampling subsets to extract more local consensus information, thereby generating accurate pose hypotheses even in scenarios with low overlap between point clouds. This method enhances robustness against low overlap and reduces the influence of outliers, addressing the limitations of traditional techniques. First, we construct a graph matrix to represent the compatibility relationships among the initial correspondences. Next, we build clique-likes subsets of various sizes within the graph matrix, each representing a consensus set. Then, we compute the transformation hypotheses for the subsets using the SVD algorithm and select the best hypothesis for registration based on evaluation metrics. Extensive experiments demonstrate the effectiveness of CL-PCR. In comparison experiments on the 3DMatch/3DLoMatch datasets using both FPFH and FCGF descriptors, our Fast-CL-PCRv1 outperforms state-of-the-art algorithms, achieving superior registration performance. Additionally, we validate the practicality and robustness of our method with real-world data.

FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization.

In recent years, a multitude of self-supervised anomaly detection algorithms have been proposed. Among them, PatchCore has emerged as one of the state-of-the-art methods on the widely used MVTec AD benchmark due to its efficient detection capabilities and cost-saving advantages in terms of labeled data. However, we have identified that the PatchCore similarity principal approach faces significant limitations in accurately locating anomalies when there are positional relationships between similar samples, such as rotation, flipping, or misaligned pixels. In real-world industrial scenarios, it is common for samples of the same class to be found in different positions. To address this challenge comprehensively, we introduce Feature-Level Registration PatchCore (FR-PatchCore), which serves as an extension of the PatchCore method. FR-PatchCore constructs a feature matrix that is extracted into the memory bank and continually updated using the optimal negative cosine similarity loss. Extensive evaluations conducted on the MVTec AD benchmark demonstrate that FR-PatchCore achieves an impressive image-level anomaly detection AUROC score of up to 98.81%. Additionally, we propose a novel method for computing the mask threshold that enables the model to scientifically determine the optimal threshold and accurately partition anomalous masks. Our results highlight not only the high generalizability but also substantial potential for industrial anomaly detection offered by FR-PatchCore.

Advancing Ultrasonic Defect Detection in High-Speed Wheels via UT-YOLO.

In the context of defect detection in high-speed railway train wheels, particularly in ultrasonic-testing B-scan images characterized by their small size and complexity, the need for a robust solution is paramount. The proposed algorithm, UT-YOLO, was meticulously designed to address the specific challenges presented by these images. UT-YOLO enhances its learning capacity, accuracy in detecting small targets, and overall processing speed by adopting optimized convolutional layers, a special layer design, and an attention mechanism. This algorithm exhibits superior performance on high-speed railway wheel UT datasets, indicating its potential. Crucially, UT-YOLO meets real-time processing requirements, positioning it as a practical solution for the dynamic and high-speed environment of railway inspections. In experimental evaluations, UT-YOLO exhibited good performance in best recall, mAP@0.5 and mAP@0.5:0.95 increased by 37%, 36%, and 43%, respectively; and its speed also met the needs of real-time performance. Moreover, an ultrasonic defect detection data set based on real wheels was created, and this research has been applied in actual scenarios and has helped to greatly improve manual detection efficiency.

High-Density Electroencephalogram Facilitates the Detection of Small Stimuli in Code-Modulated Visual Evoked Potential Brain-Computer Interfaces.

In recent years, there has been a considerable amount of research on visual evoked potential (VEP)-based brain-computer interfaces (BCIs). However, it remains a big challenge to detect VEPs elicited by small visual stimuli. To address this challenge, this study employed a 256-electrode high-density electroencephalogram (EEG) cap with 66 electrodes in the parietal and occipital lobes to record EEG signals. An online BCI system based on code-modulated VEP (C-VEP) was designed and implemented with thirty targets modulated by a time-shifted binary pseudo-random sequence. A task-discriminant component analysis (TDCA) algorithm was employed for feature extraction and classification. The offline and online experiments were designed to assess EEG responses and classification performance for comparison across four different stimulus sizes at visual angles of 0.5°, 1°, 2°, and 3°. By optimizing the data length for each subject in the online experiment, information transfer rates (ITRs) of 126.48 ± 14.14 bits/min, 221.73 ± 15.69 bits/min, 258.39 ± 9.28 bits/min, and 266.40 ± 6.52 bits/min were achieved for 0.5°, 1°, 2°, and 3°, respectively. This study further compared the EEG features and classification performance of the 66-electrode layout from the 256-electrode EEG cap, the 32-electrode layout from the 128-electrode EEG cap, and the 21-electrode layout from the 64-electrode EEG cap, elucidating the pivotal importance of a higher electrode density in enhancing the performance of C-VEP BCI systems using small stimuli.

One-Step Assembly of Versatile Multifunctional Coatings Based on Host-Guest and Polyphenol Chemistry.

Developing a facile, efficient, and versatile polyphenol coating strategy and exploring its novel applications are of great significance in the fields of material surfaces and interfaces. Herein, a one-step assembly strategy for constructing novel tannic acid (TA) coatings via a solvent evaporation method is reported using TA and polycyclodextrin (PCD) particles (TPP). TPP with a high phenolic group activity of 88% integrates the advantages of host-guest and polyphenol chemistry. The former can drive TPP dynamically assemble into a large and collective aggregation activated by high temperature or density, and the latter provides excellent adhesion properties to substrates (0.9 mg cm-2 ). TPP can assemble into a coating (TPC) rapidly on various substrates within 1 h at 37 °C while with a high availability of feed TPP (≈90%). The resulting TPC is not only high-temperature steam-sensitive for use as an anti-fake mask but also pH-sensitive for transforming into a free-standing film under physiological conditions. Moreover, various metal ions and functional particles can incorporate into TPC to extend its versatile properties including antibacterial activity, enhanced stability, and conductivity. This work expands the polyphenol coating strategy and builds up a one-step and efficient preparation platform of polyphenol coating for multiapplication prospects in various fields.

Scattered Train Bolt Point Cloud Segmentation Based on Hierarchical Multi-Scale Feature Learning.

In view of the difficulty of using raw 3D point clouds for component detection in the railway field, this paper designs a point cloud segmentation model based on deep learning together with a point cloud preprocessing mechanism. First, a special preprocessing algorithm is designed to resolve the problems of noise points, acquisition errors, and large data volume in the actual point cloud model of the bolt. The algorithm uses the point cloud adaptive weighted guided filtering for noise smoothing according to the noise characteristics. Then retaining the key points of the point cloud, this algorithm uses the octree to partition the point cloud and carries out iterative farthest point sampling in each partition for obtaining the standard point cloud model. The standard point cloud model is then subjected to hierarchical multi-scale feature extraction to obtain global features, which are combined with local features through a self-attention mechanism, while linear interpolation is used to further expand the perceptual field of local features of the model as a basis for segmentation, and finally the segmentation is completed. Experiments show that the proposed algorithm could deal with the scattered bolt point cloud well, realize the segmentation of train bolt and background, and could achieve high segmentation accuracy, which has important practical significance for train safety detection.

Dataset Evaluation Method and Application for Performance Testing of SSVEP-BCI Decoding Algorithm.

Steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems have been extensively researched over the past two decades, and multiple sets of standard datasets have been published and widely used. However, there are differences in sample distribution and collection equipment across different datasets, and there is a lack of a unified evaluation method. Most new SSVEP decoding algorithms are tested based on self-collected data or offline performance verification using one or two previous datasets, which can lead to performance differences when used in actual application scenarios. To address these issues, this paper proposed a SSVEP dataset evaluation method and analyzed six datasets with frequency and phase modulation paradigms to form an SSVEP algorithm evaluation dataset system. Finally, based on the above datasets, performance tests were carried out on the four existing SSVEP decoding algorithms. The findings reveal that the performance of the same algorithm varies significantly when tested on diverse datasets. Substantial performance variations were observed among subjects, ranging from the best-performing to the worst-performing. The above results demonstrate that the SSVEP dataset evaluation method can integrate six datasets to form a SSVEP algorithm performance testing dataset system. This system can test and verify the SSVEP decoding algorithm from different perspectives such as different subjects, different environments, and different equipment, which is helpful for the research of new SSVEP decoding algorithms and has significant reference value for other BCI application fields.

The 100 top-cited articles in uveitis from 1950 to 2022.

OBJECTIVES: This bibliometric analysis aimed to clarify research characteristics and trends in research on uveitis by analyzing the top 100 most-cited articles. METHODS: We used the Web of Science database to search articles published in English from January 1, 1950, to February 10, 2022, without other restrictions. The 100 most-cited articles related to uveitis were screened. The publication year, institution, author, journal, country, research topic, and research type of each article were analyzed. RESULTS: The citations of the top 100 articles ranged from 144 to 2292 times. The years 2004 and 2005 included the largest number of articles published, with 17 in total. Most of the papers were published in Ophthalmology (n = 19), a specialized ophthalmology journal. The top 100 articles originated from 14 countries, with the most from the USA (n = 44). Twenty research institutions and 18 authors contributed two or more articles, with the National Eye Institute (USA) (n = 10) and Robert B. Nussenblatt (n = 10) contributing the most. The types of studies were mainly clinical studies (n = 64), focusing on the treatment of uveitis (n = 36). CONCLUSION: This study summarizes and analyzes the research characteristics and trends of uveitis. The contribution of the USA is explained, the past and current treatments of uveitis are emphasized, and the directions of future research are clarified.

Tyrosine-Based Dual-Functional Interface for Trapping and On-Site Photo-Induced Covalent Immobilization of Proteins.

Tyrosine, a simple and well-available natural amino acid, is featured by the small size of the compound that contains multiple reactive groups. This study developed an efficient bioconjugation strategy using tyrosine-based dual-functional interfaces. When tyrosine molecules are immobilized on the surface of a supporting material through amino groups, their carboxyl groups can function as an attracting trap due to their anionic nature at neutral pH and ability to chelate nickel(II) ions (Ni2+), allowing the capture and enrichment of cationic proteins and histidine (His)-tagged proteins on the surface. The trapped proteins can be further covalently immobilized on site through ruthenium-mediated photochemical cross-linking, which has been found to be highly efficient and can be completed within minutes. This strategy was successfully applied to two different material systems. We found that tyrosine-modified agarose beads had a binding capacity of the His-tagged enhanced green fluorescent protein comparable to that of commonly used nitrilotriacetic acid-based resins, and further covalent coupling via dityrosine cross-linking achieved a yield of 85% within 5 min, without compromising much on its fluorescence activity. On the surface of tyrosine-modified 316L stainless steel, lysozyme was captured through electrostatic interaction and further immobilized. The resultant surface exhibited remarkable antibacterial activity against both Staphylococcus aureus and Escherichia coli. Such a tyrosine-based capture-then-coupling method is featured by its simplicity, high coupling efficiency, and high utilization rate of target molecules, making it particularly suitable for the proteins that are highly priced or vulnerable to general immobilization chemistry.

Nondestructive analysis of rolling contact fatigue cracks using induced scanning thermography.

Rolling contact fatigue (RCF) produced by wheel-rail interaction is now considered to be a critical factor that causes failure. Throughout this work, induced scanning thermography (IST) for detecting RCF defects at different depths is investigated. The original thermal sequences could not utilize the features at the heat dissipation stage; thus, a data reconstruction method, including principal component analysis (PCA) and Tucker factorization, was employed to extract the spatial and time patterns. In addition, detectability was evaluated across a range of speed studies. The Tucker-PCA combination algorithms obtained defects with improved quality, showing a clear boundary over the velocity range of 1-4km/h, which dramatically suppressed background noise. A unique gradient response characteristic in the cooling phase was summarized and utilized through experimental verification in order to recognize defect width.

Quantitative vessel density analysis of macular and peripapillary areas by optical coherence tomography angiography in adults with primary nephrotic syndrome.

PURPOSE: To compare the microvascular parameters of macular and peripapillary areas in adults with primary nephrotic syndrome (PNS) and healthy controls (HCs). METHODS: In this cross-sectional study, optical coherence tomography angiography (OCTA) was used to evaluate the changes in retinal microvascular in 37 adult patients with PNS and 30 HCs in this study. All subjects underwent OCTA for measuring vascular density (VD), perfusion density (PD), and foveal avascular zone (FAZ) in the superficial capillary plexus (SCP) and optical coherence tomography (OCT) for measuring central macular thickness (CMT) and retinal nerve fiber layer (RNFL) thickness. The following clinical data of the PNS group were collected: hemoglobin, platelet, total protein, albumin, prealbumin, creatinine, urea nitrogen, glomerular filtration rate, blood lipid, urinary protein, urine microalbumin, urine microalbumin/creatinine, 24-h urine volume, and 24-h urine protein quantification. The OCTA data were compared between patients with PNS and HCs, and the correlation between the OCTA data and clinical data was analyzed in the PNS group. RESULTS: VD and PD in the macular area of the PNS group were significantly lower than those in the HC group (VD: 17.025 ± 2.229 vs. 18.290 ± 0.721, P = 0.001; PD: 0.417 ± 0.058 vs. 0.450 ± 0.019, P = 0.003). No significant differences in the FAZ area and perioptic disc microvascular parameters were observed between the two groups, and patients in the PNS group showed consistent changes in the left and right eyes. VD and PD in the central macular area were positively correlated with plasma prealbumin level (VD: ρ = 0.541, P = 0.001; PD: ρ = 0.562, P < 0.001) and negatively correlated with urinary protein level (VD: ρ = -0.579, P < 0.001; PD: ρ = -0.596, P < 0.001). CONCLUSIONS: In adult patients with PNS, the decrease in VD and PD was mainly occurred in the macular area. Partly vascular density of the macular area was positively correlated with plasma prealbumin level and negatively correlated with urinary protein level. OCTA provides a convenient, non-invasive and effective method for evaluating and monitoring retinal microcirculation damage in patients with PNS.

Effect of Sirt3 on retinal pigment epithelial cells in high glucose through Foxo3a/ PINK1-Parkin pathway mediated mitophagy.

Sirt3 is closely associated with mitophagy. This study aimed to investigate the effect and potential mechanism of Sirt3 on mitophagy in retinal pigment epithelium (RPE) in a high glucose environment. The expression levels of Sirt3, Foxo3a, PINK1, Parkin and LC3B in RPE subjected to high-glucose (HG, 30 mM D-glucose) conditions were detected by RT-PCR and western blotting. Dichloro-dihydro-fluorescein diacetate (DCFH-DA) staining was used to detect the level of reactive oxygen species (ROS) in RPE treated with HG. MitoTracker and LysoTracker probes were used to label mitochondria and lysosomes, respectively, to observe the occurrence of autophagy. Sirt3-dependent regulation of mitophagy through the Foxo3a/PINK1-Parkin pathway was further investigated by virus transfection-mediated Sirt3 overexpression and PINK1 silencing. The effect of Sirt3 overexpression on apoptosis was detected by flow cytometry. The Sirt3 expression was decreased, the Foxo3a/PINK1-Parkin pathway was inhibited, intracellular ROS level was increased, and mitophagy was attenuated in RPE under HG condition. Sirt3 overexpression activated the Foxo3a/PINK1-Parkin signaling pathway and mitophagy, and inhibited cell apoptosis. Silencing PINK1 inhibited the effect of Sirt3 overexpression on mitophagy. In summary, Sirt3 can activate mitophagy through the Foxo3a/PINK1-Parkin pathway and reduce HG-induced apoptosis of RPE. This study provides a new direction to understand the pathogenesis and develop a potential therapeutic target for diabetic retinopathy.

MAFFNet: real-time multi-level attention feature fusion network with RGB-D semantic segmentation for autonomous driving.

Compared with RGB semantic segmentation, RGB-D semantic segmentation can combine the geometric depth information to effectively improve the segmentation accuracy. Considering the application of RGB-D semantic segmentation in autonomous driving, we design a real-time semantic segmentation network, that is, MAFFNet, which can effectively extract depth features and combine the complementary information in RGB and depth. We also design a multi-level attention feature fusion module that can excavate the available context information of RGB and depth features. At the same time, its inference speed can also meet the demands of autonomous driving. Experiments show that our network achieves excellent performance of 74.4% mIoU and an inference speed of 15.9 Hz at a full resolution of 2048×1024 on the cityscapes dataset. Using multi-source learning, we mixed the cityscapes and lost and found as the multi-dataset. Our network is also superior to previous algorithms in using the multi-dataset to detect small obstacles outside the road.

Automated Detection of Epiretinal Membranes in OCT Images Using Deep Learning.

INTRODUCTION: Development and validation of a deep learning algorithm to automatedly identify and locate ERM regions in OCT images. METHODS: OCT images of 468 eyes were retrospectively collected from a total of 404 ERM patients. One expert manually annotated the ERM regions for all images. A total of 422 images (90%) and the rest 46 images (10%) were used as the training dataset and validation dataset for deep learning algorithm training and validation, respectively. One senior and one junior clinician read the images. The diagnostic results were compared. RESULTS: The algorithm accurately segmented and located the ERM regions in OCT images. The image-level accuracy was 95.65%, and the ERM region-level accuracy was 90.14%, respectively. In comparison experiments, the accuracies of the junior clinician improved from 85.00% and 61.29% without the assistance of the algorithm to 100.00% and 90.32% with the assistance of the algorithm. The corresponding results of the senior clinician were 96.15%, 95.00% without the assistance of the algorithm, and 96.15%, 97.50% with the assistance of the algorithm. CONCLUSIONS: The developed deep learning algorithm can accurately segmenting ERM regions in OCT images. This deep learning approach may help clinicians in clinical diagnosis with better accuracy and efficiency.

Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors.

Establishing an effective local feature descriptor and using an accurate key point matching algorithm are two crucial tasks in recognizing and registering on the 3D point cloud. Because the descriptors need to keep enough descriptive ability against the effect of noise, occlusion, and incomplete regions in the point cloud, a suitable key point matching algorithm can get more precise matched pairs. To obtain an effective descriptor, this paper proposes a Multi-Statistics Histogram Descriptor (MSHD) that combines spatial distribution and geometric attributes features. Furthermore, based on deep learning, we developed a new key point matching algorithm that could identify more corresponding point pairs than the existing methods. Our method is evaluated based on Stanford 3D dataset and four real component point cloud dataset from the train bottom. The experimental results demonstrate the superiority of MSHD because its descriptive ability and robustness to noise and mesh resolution are greater than those of carefully selected baselines (e.g., FPFH, SHOT, RoPS, and SpinImage descriptors). Importantly, it has been confirmed that the error of rotation and translation matrix is much smaller based on our key point matching algorithm, and the precise corresponding point pairs can be captured, resulting in enhanced recognition and registration for three-dimensional surface matching.