Accurate estimation of 3D object pose is highly desirable in a wide range of applications, such as robotics and augmented reality. Although significant advancement has been made for pose estimation, there is room for further improvement. Recent pose estimation systems utilize an iterative refinement process to revise the predicted pose to obtain a better final output. However, such refinement process only takes account of geometric features for pose revision during the iteration. Motivated by this approach, this paper designs a novel iterative refinement process that deals with both color and geometric features for object pose refinement. Experiments show that the proposed method is able to reach 94.74% and 93.2% in ADD(-S) metric with only 2 iterations, outperforming the state-of-the-art methods on the LINEMOD and YCB-Video datasets, respectively.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7436036 | PMC |
| http://dx.doi.org/10.3390/s20154114 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
PC-CS-YOLO: High-Precision Obstacle Detection for Visually Impaired Safety.
Sensors (Basel)
January 2025
Engineering Training Center, Nantong University, Nantong 226019, China.
The issue of obstacle avoidance and safety for visually impaired individuals has been a major topic of research. However, complex street environments still pose significant challenges for blind obstacle detection systems. Existing solutions often fail to provide real-time, accurate obstacle avoidance decisions.
View Article and Find Full Text PDFSix-Dimensional Pose Estimation of Molecular Sieve Drying Package Based on Red Green Blue-Depth Camera.
Sensors (Basel)
January 2025
College of Metrology Measurement and Instrument, China Jiliang University, Hangzhou 310018, China.
This paper aims to address the challenge of precise robotic grasping of molecular sieve drying bags during automated packaging by proposing a six-dimensional (6D) pose estimation method based on an red green blue-depth (RGB-D) camera. The method consists of three components: point cloud pre-segmentation, target extraction, and pose estimation. A minimum bounding box-based pre-segmentation method was designed to minimize the impact of packaging wrinkles and skirt curling.
View Article and Find Full Text PDFEmbedded Ileal Fish Bone Removed via Deep Enteroscopy in a Patient with Abdominal Pain and Hematochezia: A Case Report.
Medicina (Kaunas)
December 2024
Division of Gastroenterology, Department of Medicine, Tri-Service General Hospital, National Defense Medical Center, No. 325, Section 2, Chenggong Road, Neihu District, Taipei City 114202, Taiwan.
Ingestion of foreign bodies is a prevalent issue in clinical practice, with fish bones being the predominant cause. While the upper gastrointestinal tract is commonly affected, small intestine impactions pose significant diagnostic challenges due to nonspecific symptoms and lack of awareness of foreign body ingestion. Herein, we describe a case presenting with recurrent, unexplained abdominal pain and hematochezia.
View Article and Find Full Text PDFRobotic versus manual disinfection of global priority pathogens at COVID-19 dedicated hospitals.
Am J Infect Control
January 2025
Central Department of Microbiology, Tribhuvan University, Kirtipur, Kathmandu, Nepal. Electronic address:
Background: Twelve bacterial families were identified as global priority pathogens by the World Health Organization in 2017, recognizing the greatest threat they pose to human health and the declining antibiotic efficacy. Robotics has emerged as a swift and contactless tool for disinfecting bacterial surface contamination in healthcare facilities, however, head-to-head comparison of disinfection efficacy of robotic versus manual disinfections is limited. This study aimed at comparing how robotic disinfection performs over manual disinfection against the global priority pathogens in the healthcare setting.
View Article and Find Full Text PDFA fast monocular 6D pose estimation method for textureless objects based on perceptual hashing and template matching.
Front Robot AI
January 2025
Department of Materials and Production, Aalborg University, Aalborg, Denmark.
Object pose estimation is essential for computer vision applications such as quality inspection, robotic bin picking, and warehouse logistics. However, this task often requires expensive equipment such as 3D cameras or Lidar sensors, as well as significant computational resources. Many state-of-the-art methods for 6D pose estimation depend on deep neural networks, which are computationally demanding and require GPUs for real-time performance.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!