arXiv subjects

Hongbin Ma

Publications and source records attributed to Hongbin Ma.

16 recordsLinked to original sources

arXiv2026

Analysis and Design of Double-Transmitting Coil Systems based on Parity-Time Symmetry

The wireless power transfer (WPT) system based on parity-time (PT) symmetry has the advantages of robustness, stability, and efficient power transmission. However, traditional PT symmetry structures have limited voltage power output and are susceptible to horizontal misalignment effects. Multiple transmission coils have been proven to improve the power and misalignment tolerance of WPT systems, but variations in inter-coil coupling significantly affect transmission power. Towards this end, this article proposes a double-transmitting coil WPT system based on PT symmetry, which is innovative in that a novel negative resistance structure based on operational amplifier (OA) is proposed, and the parallel structure of double-transmitting coil is applied to this negative resistance structure. Compared with the traditional WPT system based on a single-transmitting coil PT, this system improves the power and misalignment tolerance in the PT symmetry region. The large-sized and small-sized receiving coils increase the load power to 313% and 185% respectively. Moreover, in the symmetry region, the displacement of the receiving coil in the horizontal and vertical directions results in variations of the equivalent coupling coefficient, which can achieve stable power transmission in three dimensions. The voltage fluctuation rate of both receiving coils does not exceed 3.4%, greatly improving the degree of freedom of the receiving system.

physics.app-ph↗

arXiv2025

Advancing Accessibility: Augmented Reality Solutions for the Blind and Disabled in Bangladesh

Augmented Reality (AR) technology holds immense potential to transform the lives of blind and disabled individuals by offering enhanced interaction with their surroundings and providing real-time, accessible information. Globally, AR applications are being developed with features such as audio descriptions of environments, object recognition, and navigational aids, specifically designed to support the visually impaired. These innovations are paving the way for increased independence, mobility, and overall quality of life for millions of people worldwide. In Bangladesh, the adoption of AR technology for the blind and disabled is still in its early stages, primarily due to limited accessibility resources and infrastructure challenges. However, with the growing penetration of smartphones and continuous advancements in AR technologies, there is a promising opportunity for these solutions to be adapted, localized, and scaled within the country. This paper reviews the current state of AR technologies for the visually impaired on a global scale, explores their potential application in Bangladesh, and delves into the challenges and opportunities for broader implementation in this context.

cs.HC↗

arXiv2025

A Historical Interaction-Enhanced Shapley Policy Gradient Algorithm for Multi-Agent Credit Assignment

Multi-agent reinforcement learning (MARL) has demonstrated remarkable performance in multi-agent collaboration problems and has become a prominent topic in artificial intelligence research in recent years. However, traditional credit assignment schemes in MARL cannot reliably capture individual contributions in strongly coupled tasks while maintaining training stability, which leads to limited generalization capabilities and hinders algorithm performance. To address these challenges, we propose a Historical Interaction-Enhanced Shapley Policy Gradient Algorithm (HIS) for Multi-Agent Credit Assignment, which employs a hybrid credit assignment mechanism to balance base rewards with individual contribution incentives. By utilizing historical interaction data to calculate the Shapley value in a sample-efficient manner, HIS enhances the agent's ability to perceive its own contribution, while retaining the global reward to maintain training stability. Additionally, we provide theoretical guarantees for the hybrid credit assignment mechanism, ensuring that the assignment results it generates are both efficient and stable. We evaluate the proposed algorithm in three widely used continuous-action benchmark environments: Multi-Agent Particle Environment, Multi-Agent MuJoCo, and Bi-DexHands. Experimental results demonstrate that HIS outperforms state-of-the-art methods, particularly excelling in strongly coupled, complex collaborative tasks.

cs.MA↗

arXiv2024

Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework

Due to the density inconsistency and distribution difference between cross-source point clouds, previous methods fail in cross-source point cloud registration. We propose a density-robust feature extraction and matching scheme to achieve robust and accurate cross-source registration. To address the density inconsistency between cross-source data, we introduce a density-robust encoder for extracting density-robust features. To tackle the issue of challenging feature matching and few correct correspondences, we adopt a loose-to-strict matching pipeline with a ``loose generation, strict selection'' idea. Under it, we employ a one-to-many strategy to loosely generate initial correspondences. Subsequently, high-quality correspondences are strictly selected to achieve robust registration through sparse matching and dense matching. On the challenging Kinect-LiDAR scene in the cross-source 3DCSR dataset, our method improves feature matching recall by 63.5 percentage points (pp) and registration recall by 57.6 pp. It also achieves the best performance on 3DMatch, while maintaining robustness under diverse downsampling densities.

cs.CV↗

arXiv2024

LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention

Feature upsampling is an essential operation in constructing deep convolutional neural networks. However, existing upsamplers either lack specific feature guidance or necessitate the utilization of high-resolution feature maps, resulting in a loss of performance and flexibility. In this paper, we find that the local self-attention naturally has the feature guidance capability, and its computational paradigm aligns closely with the essence of feature upsampling (\ie feature reassembly of neighboring points). Therefore, we introduce local self-attention into the upsampling task and demonstrate that the majority of existing upsamplers can be regarded as special cases of upsamplers based on local self-attention. Considering the potential semantic gap between upsampled points and their neighboring points, we further introduce the deformation mechanism into the upsampler based on local self-attention, thereby proposing LDA-AQU. As a novel dynamic kernel-based upsampler, LDA-AQU utilizes the feature of queries to guide the model in adaptively adjusting the position and aggregation weight of neighboring points, thereby meeting the upsampling requirements across various complex scenarios. In addition, LDA-AQU is lightweight and can be easily integrated into various model architectures. We evaluate the effectiveness of LDA-AQU across four dense prediction tasks: object detection, instance segmentation, panoptic segmentation, and semantic segmentation. LDA-AQU consistently outperforms previous state-of-the-art upsamplers, achieving performance enhancements of 1.7 AP, 1.5 AP, 2.0 PQ, and 2.5 mIoU compared to the baseline models in the aforementioned four tasks, respectively. Code is available at \url{https://github.com/duzw9311/LDA-AQU}.

cs.CV↗

arXiv2024

Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images

Object detection in aerial images has always been a challenging task due to the generally small size of the objects. Most current detectors prioritize the development of new detection frameworks, often overlooking research on fundamental components such as feature pyramid networks. In this paper, we introduce the Cross-Layer Feature Pyramid Transformer (CFPT), a novel upsampler-free feature pyramid network designed specifically for small object detection in aerial images. CFPT incorporates two meticulously designed attention blocks with linear computational complexity: Cross-Layer Channel-Wise Attention (CCA) and Cross-Layer Spatial-Wise Attention (CSA). CCA achieves cross-layer interaction by dividing channel-wise token groups to perceive cross-layer global information along the spatial dimension, while CSA enables cross-layer interaction by dividing spatial-wise token groups to perceive cross-layer global information along the channel dimension. By integrating these modules, CFPT enables efficient cross-layer interaction in a single step, thereby avoiding the semantic gap and information loss associated with element-wise summation and layer-by-layer transmission. In addition, CFPT incorporates global contextual information, which improves detection performance for small objects. To further enhance location awareness during cross-layer interaction, we propose the Cross-Layer Consistent Relative Positional Encoding (CCPE) based on inter-layer mutual receptive fields. We evaluate the effectiveness of CFPT on three challenging object detection datasets in aerial images: VisDrone2019-DET, TinyPerson, and xView. Extensive experiments demonstrate that CFPT outperforms state-of-the-art feature pyramid networks while incurring lower computational costs. The code is available at https://github.com/duzw9311/CFPT.

cs.CV↗

arXiv2024

SGOR: Outlier Removal by Leveraging Semantic and Geometric Information for Robust Point Cloud Registration

In this paper, we introduce a new outlier removal method that fully leverages geometric and semantic information, to achieve robust registration. Current semantic-based registration methods only use semantics for point-to-point or instance semantic correspondence generation, which has two problems. First, these methods are highly dependent on the correctness of semantics. They perform poorly in scenarios with incorrect semantics and sparse semantics. Second, the use of semantics is limited only to the correspondence generation, resulting in bad performance in the weak geometry scene. To solve these problems, on the one hand, we propose secondary ground segmentation and loose semantic consistency based on regional voting. It improves the robustness to semantic correctness by reducing the dependence on single-point semantics. On the other hand, we propose semantic-geometric consistency for outlier removal, which makes full use of semantic information and significantly improves the quality of correspondences. In addition, a two-stage hypothesis verification is proposed, which solves the problem of incorrect transformation selection in the weak geometry scene. In the outdoor dataset, our method demonstrates superior performance, boosting a 22.5 percentage points improvement in registration recall and achieving better robustness under various conditions. Our code is available.

cs.CV↗

arXiv2024

Intelligent mechanical metamaterials towards learning static and dynamic behaviors

The exploration of intelligent machines has recently spurred the development of physical neural networks, a class of intelligent metamaterials capable of learning, whether in silico or in situ, from observed data. In this study, we introduce a back-propagation framework for lattice-based mechanical neural networks (MNNs) to achieve prescribed static and dynamic performance. This approach leverages the steady states of nodes for back-propagation, efficiently updating the learning degrees of freedom without prior knowledge of input loading. One-dimensional MNNs, trained with back-propagation in silico, can exhibit the desired behaviors on demand function as intelligent mechanical machines. The framework is then employed for the precise morphing control of the two-dimensional MNNs subjected to different static loads. Moreover, the intelligent MNNs are trained to execute classical machine learning tasks such as regression to tackle various deformation control tasks. Finally, the disordered MNNs are constructed and trained to demonstrate pre-programmed wave bandgap control ability, illustrating the versatility of the proposed approach as a platform for physical learning. Our approach presents an efficient pathway for the design of intelligent mechanical metamaterials for a wide range of static and dynamic target functionalities, positioning them as powerful engines for physical learning.

physics.app-ph↗

arXiv2024

VRHCF: Cross-Source Point Cloud Registration via Voxel Representation and Hierarchical Correspondence Filtering

Addressing the challenges posed by the substantial gap in point cloud data collected from diverse sensors, achieving robust cross-source point cloud registration becomes a formidable task. In response, we present a novel framework for point cloud registration with broad applicability, suitable for both homologous and cross-source registration scenarios. To tackle the issues arising from different densities and distributions in cross-source point cloud data, we introduce a feature representation based on spherical voxels. Furthermore, addressing the challenge of numerous outliers and mismatches in cross-source registration, we propose a hierarchical correspondence filtering approach. This method progressively filters out mismatches, yielding a set of high-quality correspondences. Our method exhibits versatile applicability and excels in both traditional homologous registration and challenging cross-source registration scenarios. Specifically, in homologous registration using the 3DMatch dataset, we achieve the highest registration recall of 95.1% and an inlier ratio of 87.8%. In cross-source point cloud registration, our method attains the best RR on the 3DCSR dataset, demonstrating a 9.3 percentage points improvement. The code is available at https://github.com/GuiyuZhao/VRHCF.

cs.CV↗

arXiv2024

Real-Time Object Detection in Occluded Environment with Background Cluttering Effects Using Deep Learning

Detection of small, undetermined moving objects or objects in an occluded environment with a cluttered background is the main problem of computer vision. This greatly affects the detection accuracy of deep learning models. To overcome these problems, we concentrate on deep learning models for real-time detection of cars and tanks in an occluded environment with a cluttered background employing SSD and YOLO algorithms and improved precision of detection and reduce problems faced by these models. The developed method makes the custom dataset and employs a preprocessing technique to clean the noisy dataset. For training the developed model we apply the data augmentation technique to balance and diversify the data. We fine-tuned, trained, and evaluated these models on the established dataset by applying these techniques and highlighting the results we got more accurately than without applying these techniques. The accuracy and frame per second of the SSD-Mobilenet v2 model are higher than YOLO V3 and YOLO V4. Furthermore, by employing various techniques like data enhancement, noise reduction, parameter optimization, and model fusion we improve the effectiveness of detection and recognition. We further added a counting algorithm, and target attributes experimental comparison, and made a graphical user interface system for the developed model with features of object counting, alerts, status, resolution, and frame per second. Subsequently, to justify the importance of the developed method analysis of YOLO V3, V4, and SSD were incorporated. Which resulted in the overall completion of the proposed method.

cs.CV↗

arXiv2023

SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration

Point cloud registration is to estimate a transformation to align point clouds collected in different perspectives. In learning-based point cloud registration, a robust descriptor is vital for high-accuracy registration. However, most methods are susceptible to noise and have poor generalization ability on unseen datasets. Motivated by this, we introduce SphereNet to learn a noise-robust and unseen-general descriptor for point cloud registration. In our method, first, the spheroid generator builds a geometric domain based on spherical voxelization to encode initial features. Then, the spherical interpolation of the sphere is introduced to realize robustness against noise. Finally, a new spherical convolutional neural network with spherical integrity padding completes the extraction of descriptors, which reduces the loss of features and fully captures the geometric features. To evaluate our methods, a new benchmark 3DMatch-noise with strong noise is introduced. Extensive experiments are carried out on both indoor and outdoor datasets. Under high-intensity noise, SphereNet increases the feature matching recall by more than 25 percentage points on 3DMatch-noise. In addition, it sets a new state-of-the-art performance for the 3DMatch and 3DLoMatch benchmarks with 93.5\% and 75.6\% registration recall and also has the best generalization ability on unseen datasets.

cs.CV↗

arXiv2022

Experimental Comparison of SNR and RSSI for LoRa-ESL Based on Machine Clustering and Arithmetic Distribution

LoRa lacks the sensing capabilities of channel status. Received signal strength indicator (RSSI) decreases due to collision, interference, and near-far effect while for signal-to-noise ratio (SNR), the packets are rejected by decreasing the transmission power (TP) at a higher spreading factor (SF). To overcome these challenges in the case of electric shelf label (ESL) to minimize the dependency on retransmission and acknowledgment, the end devices (EDs) are allocated around gateways (GWs) based on machine clustering with dynamic SF for SNR while dynamic TP for RSSI. The experimental results determined that the RSSI approach is more dominant than SNR because of determining the exact locality of the ED that diminished the capture effect. Arithmetic distribution of EDs for various GWs in different clusters helps to minify the near-far effect. The resultant received power (RP) at each cluster is higher for most of the connected EDs than the threshold RP.

eess.SP↗

arXiv2022

Embedded Design of Automatic Pesticide Spraying Robot Control System

In agriculture, crops need to apply pesticide spraying flow control precisely to reduce costs, protect the environment, and increase yield production. Although there have several variable control methods for spraying flow control because indirect control flow techniques and having a slow response could cause inaccuracy and mismanagement, also noted that those systems also suffer from complicated design and debugging, etc. In this paper, an embedded design of the fuzzy PID variable spraying control method is adopted. The experimental results show that the overshoot of Proportional Integral Derivative (PID) control is 10.76%, and the overshoot of fuzzy PID control is 7.17% which can meet the requirements of an advanced spray control flow system. For further investigation, a novel spray flow control method based on Programmable Logic Control (PLC) is proposed in this paper.

cs.RO↗

arXiv2022

Analysis of the Production Strategy of Mask Types in the COVID-19 Environment

Since the outbreak of the COVID-19 in December 2019, medical protective equipment such as disposable medical masks and KN95 masks have become essential resources for the public. Enterprises in all sectors of society have also transformed the production of medical masks. After the outbreak, how to choose the right time to produce medical protective masks, and what type of medical masks to produce will play a positive role in preventing and controlling the epidemic in a short time. In this regard, the evolutionary game competition analysis will be conducted through the relevant data of disposable medical masks and KN95 masks to determine the appropriate nodes for the production of corresponding mask types. After the research and analysis of the production strategy of mask types, it has a positive effect on how to guide the resumption of work and production.

cs.CV↗

arXiv2022

Analysis of OODA Loop based on Adversarial for Complex Game Environments

To address the problem of imperfect confrontation strategy caused by the lack of information of game environment in the simulation of non-complete information dynamic countermeasure modeling for intelligent game, the hierarchical analysis game strategy of confrontation model based on OODA ring (Observation, Orientation, Decision, Action) theory is proposed. At the same time, taking into account the trend of unmanned future warfare, NetLogo software simulation is used to construct a dynamic derivation of the confrontation between two tanks. In the validation process, the OODA loop theory is used to describe the operation process of the complex system between red and blue sides, and the four-step cycle of observation, judgment, decision and execution is carried out according to the number of armor of both sides, and then the OODA loop system adjusts the judgment and decision time coefficients for the next confrontation cycle according to the results of the first cycle. Compared with traditional simulation methods that consider objective factors such as loss rate and support rate, the OODA-loop-based hierarchical game analysis can analyze the confrontation situation more comprehensively.

cs.AI↗

arXiv2021

Neural Network Structure Design based on N-Gauss Activation Function

Recent work has shown that the activation function of the convolutional neural network can meet the Lipschitz condition, then the corresponding convolutional neural network structure can be constructed according to the scale of the data set, and the data set can be trained more deeply, more accurately and more effectively. In this article, we have accepted the experimental results and introduced the core block N-Gauss, N-Gauss, and Swish (Conv1, Conv2, FC1) neural network structure design to train MNIST, CIFAR10, and CIFAR100 respectively. Experiments show that N-Gauss gives full play to the main role of nonlinear modeling of activation functions, so that deep convolutional neural networks have hierarchical nonlinear mapping learning capabilities. At the same time, the training ability of N-Gauss on simple one-dimensional channel small data sets is equivalent to the performance of ReLU and Swish.

cs.CV↗