Últimas publicaciones y patentes sobre SLAM 3D

Localización y mapeo simultáneos (SLAM)

Consejo: además de esta selección sobre Aeronáutica, puede buscar y filtrar nuestros:
    * herramienta gratuita de búsqueda de publicaciones * por autor, tema, palabras clave, fecha o revista.
    * herramienta gratuita de búsqueda de patentes * para patentes en inglés de la Oficina Europea de Patentes.

This is our latest selection of worldwide publications and patents in english on 3D SLAM, between many scientific online journals, classified and focused on SLAM, LiDAR, point cloud, scan matching, feature extraction, loop closure, simultaneous localization, localization and mapping, odometry, Kalman filter, object detection, iterative closest point, voxel grid and 3D reconstruction.

Absolute Depth Estimation for Monocular Visual Simultaneous Localization and Mapping in Complex Environments

Published on 2025-10-21 by Kaijun Zhou, Zifei Yu, Xiancheng Zhou, Ping Tan, Yunpeng Yin, Huanxin Luo @MDPI

Abstract: Aiming to address the problems of scale uncertainty and dynamic object interference in monocular visual simultaneous localization and mapping (SLAM), this paper proposes an absolute depth estimation network-based monocular visual SLAM method, namely, ADEmono-SLAM. Firstly, some detail features including oriented fast and rotated brief (ORB) features of input image are extracted. An object depth map is obtained through an absolute depth estimation network, and some reliable feature points are obt[...]


Our summary: This paper presents ADEmono-SLAM, a method for absolute depth estimation in monocular visual SLAM. It addresses scale uncertainty and dynamic object interference through a depth estimation network and a dynamic interference filtering algorithm. Experimental results demonstrate improved pose estimation accuracy and reduced error in complex environments.

Depth Estimation, Monocular SLAM, Dynamic Interference, Feature Extraction

Publication

An Accurate Battery Capacity and State-of-Health (SoH) Estimation Tool for Energy Storage Systems

Published on 2025-10-21 by Fazal Ur Rehman, Concettina Buccella, Carlo Cecati @MDPI

Abstract: In battery energy storage systems, accurately estimating battery capacity and state of health is crucial to ensure satisfactory operation and system efficiency and reliability. However, these tasks present particular challenges under irregular charge–discharge conditions, such as those encountered in renewable energy integration and electric vehicles, where heterogeneous cycling accelerates degradation. This study introduces a hybrid deep learning framework to address these challen[...]


Our summary: This study presents a hybrid deep learning framework, CBATE-Net, for accurate battery capacity and state-of-health estimation. It utilizes convolutional layers, bidirectional recurrent units, and a temporal attention mechanism to address challenges in energy storage systems. The model demonstrates improved stability and accuracy in predicting capacity fade, making it suitable for real-world applications.

Battery capacity, State-of-health, Deep learning, Energy storage

Publication

Chest X-Ray Medical Report Generation Using a CNN—Transformer Model with Maximum Attention

Published on 2025-10-21 by Hsih, Lin, Hsieh @MDPI

Abstract: Medical imaging, particularly chest X-rays, plays a vital role in radiological diagnosis. However, interpreting these images and generating detailed diagnostic reports is a time-consuming task for clinicians. To address this challenge, this study proposes an automated image captioning framework for chest X-ray images, aiming to reduce clinical workload and enhance diagnostic efficiency. The proposed approach employs convolutional neural networks (CNNs) for visual feature extraction and a modifie[...]


Our summary: This study presents an automated framework for generating diagnostic reports from chest X-ray images using a CNN-Transformer model. It evaluates various CNN architectures for feature extraction and employs attention mechanisms for optimal report generation. Results show the proposed approach outperforms baseline models in generating accurate medical image captions.

CNN, Transformer, Medical Imaging, Report Generation

Publication

Reconstruction of Building LIDAR Point Cloud Based on Geometric Primitive Constrained Optimization

Published on 2025-10-21 by Haoyu Li, Tao Liu, Ruiqi Shen, Zhengling Lei @MDPI

Abstract: This study proposes a 3D reconstruction method for LIDAR building point clouds using geometric primitive constrained optimization. It addresses challenges such as low accuracy, high complexity, and slow modeling. This new algorithm studies the reconstruction of point clouds at the level of geometric primitives and is an incremental joint optimization method based on the GPU rendering pipeline. Firstly, the building point cloud collected by the LIDAR laser scanner was preprocessed, and an initial[...]


Our summary: 3D reconstruction method for LIDAR building point clouds using geometric primitive constrained optimization. Addresses challenges of low accuracy, high complexity, and slow modeling. Incremental joint optimization method based on GPU rendering pipeline.

LIDAR, Point Cloud, Geometric Primitive, Optimization

Publication

A Feature-Enhancement 6D Pose Estimation Method for Weakly Textured and Occluded Targets

Published on 2025-10-21 by Xiaoqing Liu, Kaijun Zhou, Qingyuan Zeng, Peng Li @MDPI

Abstract: To achieve real-time and accurate pose estimation for weakly textured or occluded targets, this study proposes a feature-enhancement 6D pose estimation method based on DenseFusion. Firstly, in the image feature extraction stage, skip connections and attention modules, which could effectively fuse deep and shallow features, are introduced to enhance the richness and effectiveness of image features. Secondly, in the point cloud feature extraction stage, PointNet is applied to the initial feature e[...]


Our summary: This study presents a novel 6D pose estimation method for weakly textured and occluded targets using DenseFusion. The method improves feature extraction through skip connections, attention modules, and PointNet for point clouds. Experimental results demonstrate significant performance improvements over traditional methods in real-time accuracy.

6D Pose Estimation, DenseFusion, Point Cloud, Feature Enhancement

Publication

Fast CU Division Algorithm for Different Occupancy Types of CUs in Geometric Videos

Published on 2025-10-21 by Nana Li, Tiantian Zhang, Jinchao Zhao, Qiuwen Zhang @MDPI

Abstract: Video-based point cloud compression (V-PCC) is a 3D point cloud compression standard that first projects the point cloud from 3D space onto 2D space, thereby generating geometric and attribute videos, and then encodes the geometric and attribute videos using high-efficiency video coding (HEVC). In the whole coding process, the coding of geometric videos is extremely time-consuming, mainly because the division of geometric video coding units has high computational complexity. In order to effectiv[...]


Our summary: A fast segmentation algorithm is proposed to reduce the coding complexity of geometric videos in video-based point cloud compression. The algorithm categorizes coding units based on occupancy types and employs visual perception factors for efficient processing. Experimental results indicate significant reductions in coding time while maintaining quality, with time savings of up to 58.71%.

CU Division, Video-based Point Cloud Compression, Geometric Video Coding, Segmentation Algorithm

Publication

Point cloud data transmission device, point cloud data transmission method, point cloud data reception device, and point cloud data reception method

Patent published on the 2025-09-18 in US under Ref US2025294168 by LG ELECTRONICS INC [KR] (Oh Hyunmook [kr])

Abstract: A point cloud data transmission method according to embodiments may comprise the steps of: encoding geometry data of point cloud data; encoding attribute data of the point cloud data on the basis of the geometry data; and transmitting the encoded geometry data, the encoded attribute data, and signaling information.[...]


Our summary: The method involves encoding geometry and attribute data of point cloud data. It transmits the encoded data along with signaling information. The process ensures efficient transmission of point cloud data.

point cloud, data transmission, encoding, reception

Patent

Positional encoding for point cloud compression

Patent published on the 2025-09-18 in US under Ref US2025294186 by QUALCOMM INCORPORATED [US] (Akhtar Anique [us], Van Der Auwera Geert [us], Hooda Reetu [us], Karczewicz Marta [us])

Abstract: A point cloud encoder is configured to receive a frame of point cloud data and encode coordinates of a geometry of the frame of point cloud data using a deep learning network. The deep learning network includes one or more layers configured to generate first features for the coordinates of the geometry, and at least one positional encoding layer configured to generate second features for the coordinates of the geometry and combine the first features with the second features to generate higher-di[...]


Our summary: A point cloud encoder processes a frame of point cloud data using a deep learning network. It generates first features from geometry coordinates and second features through a positional encoding layer. The encoder outputs an encoded tensor with combined higher-dimensional features.

positional encoding, point cloud compression, deep learning, feature generation

Patent

Table of Contents
    Agregue un encabezado para comenzar a generar la tabla de contenido

    DISPONIBLE PARA NUEVOS RETOS
    Ingeniero Mecánico, Gerente de Proyectos, Ingeniería de Procesos o I+D
    Desarrollo eficaz de productos

    Disponible para un nuevo desafío a corto plazo.
    Contáctame en LinkedIn
    Integración de electrónica de metal y plástico, diseño a coste, GMP, ergonomía, dispositivos y consumibles de volumen medio a alto, fabricación eficiente, industrias reguladas, CE y FDA, CAD, Solidworks, cinturón negro Lean Sigma, ISO 13485 médico

    Estamos buscando un nuevo patrocinador

     

    ¿Su empresa o institución se dedica a la técnica, la ciencia o la investigación?
    > Envíanos un mensaje <

    Temas tratados: SLAM 3D, LiDAR, nube de puntos, coincidencia de escaneado, extracción de características, cierre de bucles, localización simultánea, localización y cartografía, odometría, filtro de Kalman, detección de objetos, punto más cercano iterativo, cuadrícula de vóxeles, reconstrucción 3D, ISO 19117, ISO 19115, ISO 5721, ISO 19111 e ISO 19113.

    Contexto histórico

    1964
    1970
    1970
    1974-11-15
    1980
    1980
    1984
    1963
    1968
    1970
    1970
    1980
    1980
    1980
    1984

    (Si la fecha es desconocida o no es relevante, por ejemplo "mecánica de fluidos", se proporciona una estimación redondeada de su aparición notable)

    Scroll al inicio

    También te puede interesar