A5076450290- Autonomous Vehicle Technology and Safety
- Video Surveillance and Tracking Methods
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Industrial Vision Systems and Defect Detection
- Handwritten Text Recognition Techniques
- Advanced Vision and Imaging
- Robotic Path Planning Algorithms
- Medical Image Segmentation Techniques
- IPv6, Mobility, Handover, Networks, Security
- Robotics and Sensor-Based Localization
- Vehicle emissions and performance
- Advanced Measurement and Detection Methods
- Optical measurement and interference techniques
- Network Security and Intrusion Detection
- Robot Manipulation and Learning
- Image and Object Detection Techniques
- Simulation and Modeling Applications
- Computer Graphics and Visualization Techniques
- Mobile Agent-Based Network Management
- Augmented Reality Applications
- Advanced Decision-Making Techniques
- Vehicle License Plate Recognition
- Advanced Image Processing Techniques
Loma Linda University
2017-2025
Shandong University of Technology
2017-2024
University of Electronic Science and Technology of China
2004-2024
Anhui University
2024
Nanjing Medical University
2023
Jiangsu Province Hospital
2023
Jinhua Polytechnic
2023
Beijing Institute of Technology
2020-2022
Chongqing University of Technology
2021
Changchun University of Science and Technology
2020
We propose a method for text retrieval from document images without the use of OCR. Documents are segmented into character objects. Image features, namely vertical traverse density (VTD) and horizontal (HTD), extracted. An n-gram-based vector is constructed each based on these features. Text similarity between documents then measured by calculating dot product vectors. Testing with seven corpora imaged textual in English Chinese as well UW1 (University Washington 1) database confirms...
We present a new image editing method, particularly effective for sharpening major edges by increasing the steepness of transition while eliminating manageable degree low-amplitude structures. The seemingly contradictive effect is achieved in an optimization framework making use L0 gradient minimization, which can globally control how many non-zero gradients are resulted to approximate prominent structure sparsity-control manner. Unlike other edge-preserving smoothing approaches, our method...
With the development of immersive video, delivery and storage 3D content have become important research areas. While compression methods for meshes point clouds, two main representations content, are actively studied, there few studies their perceptual quality none that consider observation distance. In this paper, we study compressed sequences, both cloud mesh-based compression. We explore impact bit rate distance on quality. Evaluation is carried out by collecting viewer opinion scores...
Purpose The purpose of this study is to investigate the key characteristics artificial intelligence (AI) in organizational settings, analyze its capacity reduce customer service jobs favor more advanced roles and efficacy candidate screening by emphasizing performance. Design/methodology/approach A comprehensive analysis 40 papers performed using PRISMA method based on data from Web Science, Scopus, Emerald Google Scholar. Findings findings show optimized human resource management operations...
Cotton modified with a cationic reagent has been dyed by an exhaustion process using nanoscale pigment dispersions. Pigment uptake, colour yield and fastness properties on cotton were measured. Uptake of was found to be closely related the concentration reagent, pH pretreatment bath, temperature time cationisation. These factors also influenced fabric. Nanoscale dispersions gave much higher than conventional cotton. Fastness acceptable for wash‐down effects. It is clear that exhaust dyeing...
Operational Transformation (OT) is a collaboration-enabling technology and increasingly adopted in wide range of real-world applications. One long-lasting issue OT research detecting resolving puzzles -- subtle characteristic collaborative editing scenarios which an system may fail. After many years extensive search research, variety intricate have been de-tected resolved. However, it remains open whether all puzzles, under certain well-defined conditions, discovered. To address this issue,...
Currently, most neuroblastoma patients are treated according to the Children's Oncology Group (COG) risk group assignment; however, neuroblastoma's heterogeneity renders only a few predictors for treatment response, resulting in excessive treatment. Here, we sought couple COG classification with tumor intracellular microbiome, which is part of molecular signature tumor. We determine that an intra-tumor microbial gene abundance score, namely M-score, separates high COG-risk into two...
The mobile IP protocol has been designed to address the problem of roaming between networks. However, as nodes moves networks, signaling overhead causes significant disruption real time data traffic. localized mobility management (LMM) proposed enhance handoff performance networks within same domain. By introducing concept local agent (LMA), a node visiting foreign domain is exempted from sending frequent update its home and correspondent nodes, when movement limited visited As multiple LMAs...
Traffic-sign detection and recognition (TSDR) is crucial to avoiding harm pedestrians, especially children, from intelligent connected vehicles has become a research hotspot. However, due motion blurring, partial occlusion, smaller sign sizes, pedestrian TSDR faces increasingly significant challenges. To overcome these difficulties, CTM-YOLOv8n model proposed based on the YOLOv8n model. With aim of extracting spatial features more efficiently making network faster, C2f Faster module...
We developed a unique robotic manipulation system that accurately singulates surgical instruments in cluttered environment. A novel single-view computer vision algorithm identifies the next instrument to grip from pile and compliant electromagnetic gripper picks up identified instrument. System is validated through extensive experiments. This research was motivated by challenges of perioperative process hospitals today. Current counting, sorting, sterilization highly labor intensive....
Nowadays, the constantly expanding coverage of expressways leads to an astronomical volume daily high-speed traffic. In order address poor real-time performance traditional traffic statistics and low accuracy in detection densely distributed small targets for original algorithms, this paper proposes a vehicle analysis system that is based on DeepSORT YOLOv5. More specifically, YOLOv5 adopted detect target, Kalman filter employed prediction update, Hungarian algorithm applied trajectory...
Road obstacle detection is an important component of intelligent assisted driving technology. Existing methods ignore the direction generalized detection. This paper proposes method based on fusion roadside units and vehicle mounted cameras illustrates feasibility a combined monocular camera inertial measurement unit (IMU) (RSU) method. A vision IMU with background difference to achieve classification while reducing spatial complexity area. In recognition stage, VIDAR (Vision-IMU...
We propose a watermarking scheme for color images based on local quaternion Fourier spectral analysis (LQFSA).The merits of the proposed include: 1) Quaternion transform is defined in 4D vector space and thus provides larger embedding scope watermark than conventional monochannel transformation techniques. 2) improve imperceptibility with regard to human vision properties through LQFSA. 3) introduce invariant feature (IFT) geometric correction so as enhance robustness extensive attacks,...
The basic problem in target motion analysis (TMA) is to estimate the trajectory of an object from noise corrupted measurement data. position and velocity emitter source can be determined bearing angle measurements a passive observer. paper introduces recently developed unscented Kalman filter (UKF) application bearings-only tracking. What more, UKF compared traditional extended (EKF). Simulation shows that method performs very well even under adverse circumstances noisy environment.
Abstract A synthesized cationic reagent named polyamide‐epichlorohydrin (PAE) was used to cationize cotton fabrics which were dyed with nanoscale pigments after PAE modification. The results showed that when the concentration below 7% (owf), K/S value increased nearly linearly increasing of concentration, and excess did not increase further. With pH cationization bath, first then decreased, maximum appeared at 9–10. Cotton cationized 80°C for 20 min exhibited best cationizing result. Both...
There are various types of obstacles in an emergency, and the traffic environment is complicated. It critical to detect accurately quickly order improve safety. The obstacle detection algorithm based on deep learning cannot all because it requires pre-training. VIDAR (Vision-IMU-based Detection Range method) can any three-dimensional obstacles, but at a slow rate. In this paper, improved machine learning-based method (hereinafter referred as IVM) proposed. proposed method, morphological...
Vehicle handing stability under the combined acceleration steering and braking conditions has a great impact on vehicle safety. Therefore, coupled driving/braking control is essential. Thus, novel controller based differential flatness region proposed. First, reference state variables are calculated established dynamics bifurcation analysis. Then, flatness-based designed which can ensure by controlling states approaching their references. Based driver preview model, keep good path tracking...
In this paper, we introduced a robotic system using humanoid robot, Baxter research to pick-up surgical tools from tray and place the into different trays according types of tools. The pick-n-place manipulation is integrated with vision component special magnet gripper governed by finite state machine. This vision-based allows robot check which tool on top in tray, find grasping points tools, grab gripper, them trays. Major technologies used include: vision, force control, feedback, motion...