Skip to Content

200 Results Found

  • Article
  • Open Access
3 Citations
5,753 Views
14 Pages

1 April 2023

Flow motion with complex patterns, such as vortex, stagnant flow, and seepage, put forward higher spatial resolution requirements for particle image velocimetry (PIV). With the development of deep learning technology in optical flow estimation, many...

(This article belongs to the Section Hydraulics and Hydrodynamics)
  • Article
  • Open Access
42 Citations
6,056 Views
21 Pages

2 February 2021

Given the scarcity of annotated datasets, learning the context-dependency of anomalous events as well as mitigating false alarms represent challenges in the task of anomalous activity detection. We propose a framework, Deep-network with Multiple Rank...

(This article belongs to the Special Issue Computing and Artificial Intelligence for Visual Data Analysis)
  • Article
  • Open Access
16 Citations
6,695 Views
13 Pages

6 May 2021

The quantification of blood flow velocity in the human conjunctiva is clinically essential for assessing microvascular hemodynamics. Since the conjunctival microvessel is imaged in several seconds, eye motion during image acquisition causes motion ar...

(This article belongs to the Special Issue Computer Aided Diagnosis Sensors)
  • Review
  • Open Access
41 Citations
12,940 Views
43 Pages

A Review of Deep Learning-Based Vehicle Motion Prediction for Autonomous Driving

  • Renbo Huang,
  • Guirong Zhuo,
  • Lu Xiong,
  • Shouyi Lu and
  • Wei Tian

10 October 2023

Autonomous driving vehicles can effectively improve traffic conditions and promote the development of intelligent transportation systems. An autonomous vehicle can be divided into four parts: environment perception, motion prediction, motion planning...

(This article belongs to the Section Sustainable Transportation)
  • Article
  • Open Access
20 Citations
5,536 Views
25 Pages

26 May 2022

Crowded event entrances could threaten the comfort and safety of pedestrians, especially when some pedestrians push others or use gaps in crowds to gain faster access to an event. Studying and understanding pushing dynamics leads to designing and bui...

(This article belongs to the Collection Advances in Deep-Learning-Based Sensing, Imaging, and Video Processing)
  • Article
  • Open Access
4 Citations
2,779 Views
18 Pages

21 November 2023

Over the past four decades, Arctic sea ice coverage has steadily declined. This loss of sea ice has amplified solar radiation and heat absorption from the ocean, exacerbating both polar ice loss and global warming. It has also accelerated changes in...

(This article belongs to the Special Issue Recent Advances in Sea Ice Research Using Satellite Data)
  • Article
  • Open Access
8 Citations
2,064 Views
22 Pages

A Lightweight Dual-Stream Network with an Adaptive Strategy for Efficient Micro-Expression Recognition

  • Xinyu Liu,
  • Ju Zhou,
  • Feng Chen,
  • Shigang Li and ,
  • Hanpu Wang,
  • Yingjuan Jia and
  • Yuhao Shan
  • + 2 authors+ 0 author

1 May 2025

Micro-expressions (MEs), characterized by their brief duration and subtle facial muscle movements, pose significant challenges for accurate recognition. These ultra-fast signals, typically captured by high-speed vision sensors, require specialized co...

(This article belongs to the Special Issue Sensing Technologies Applied in Human Emotion and Facial Expression Recognition)
  • Article
  • Open Access
10 Citations
2,904 Views
20 Pages

Study on Flow Characteristics of Hydraulic Suction of Seabed Ore Particles

  • Qiu Xia,
  • Hao Jia,
  • Jiuchun Sun,
  • Xiaoguang Xi and
  • Jingyu Cui

2 May 2023

Efficient and environmentally friendly ore collecting operation requires that the ore collecting head can provide just enough suction to start the ore particles in different working conditions. In this work, computational fluid dynamics and discrete...

(This article belongs to the Special Issue Advanced Simulation and Experiment Methods of Flow Instability in Hydraulic Machinery)
  • Article
  • Open Access
1 Citations
2,392 Views
25 Pages

Hierarchical Motion Field Alignment for Robust Optical Flow Estimation

  • Dianbo Ma,
  • Kousuke Imamura,
  • Ziyan Gao,
  • Xiangjie Wang and
  • Satoshi Yamane

22 April 2025

Optical flow estimation is a fundamental and long-standing task in computer vision, facilitating the understanding of motion within visual scenes. In this study, we aim to improve optical flow estimation, particularly in challenging scenarios involvi...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
11 Citations
2,928 Views
25 Pages

ReLU, Sparseness, and the Encoding of Optic Flow in Neural Networks

  • Oliver W. Layton,
  • Siyuan Peng and
  • Scott T. Steinmetz

22 November 2024

Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present s...

(This article belongs to the Section Navigation and Positioning)
  • Article
  • Open Access
29 Citations
6,923 Views
11 Pages

Respiration Monitoring for Premature Neonates in NICU

  • Yue Sun,
  • Wenjin Wang,
  • Xi Long,
  • Mohammed Meftah and ,
  • Tao Tan,
  • Caifeng Shan,
  • Ronald M. Aarts and
  • Peter H. N. de With
  • + 3 authors+ 0 author

2 December 2019

In this paper, we investigate an automated pipeline to estimate respiration signals from videos for premature infants in neonatal intensive care units (NICUs). Two flow estimation methods, namely the conventional optical flow- and deep learning-based...

(This article belongs to the Section Applied Physics General)
  • Article
  • Open Access
19 Citations
6,611 Views
13 Pages

9 February 2023

P-wave first-motion polarity is important for the inversion of earthquake focal mechanism solutions. The focal mechanism solution can further contribute to our understanding of the source rupture process, the fault structure, and the regional stress...

(This article belongs to the Special Issue Machine Learning Applications in Seismology)
  • Article
  • Open Access
501 Views
17 Pages

Particle image velocimetry (PIV), as a widely used technique for measuring flow velocity fields and characterizing flow behavior, is widely used across various fluid mechanics applications, such as aerodynamics and fluid mechanics. However, the exist...

(This article belongs to the Section Computational Engineering)
  • Communication
  • Open Access
31 Citations
8,938 Views
13 Pages

Leveraging Deep Learning for Visual Odometry Using Optical Flow

  • Tejas Pandey,
  • Dexmont Pena,
  • Jonathan Byrne and
  • David Moloney

12 February 2021

In this paper, we study deep learning approaches for monocular visual odometry (VO). Deep learning solutions have shown to be effective in VO applications, replacing the need for highly engineered steps, such as feature extraction and outlier rejecti...

(This article belongs to the Section Optical Sensors)
  • Article
  • Open Access
848 Views
20 Pages

Effect of Submarine Speed on Its Motion in Internal Solitary Waves

  • Maolin Wang,
  • Hui Du,
  • Shaodong Wang,
  • Tianyu Zhang and ,
  • Pu Xuan,
  • Pai Peng,
  • Ruipeng Li and
  • Zhan Wang
  • + 3 authors+ 0 author

Although extensive research has been carried out on the load characteristics of fixed submarines in internal solitary waves, there is still insufficient understanding of the effect of submarine speed on its motion in internal solitary waves. A rapid...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
1,220 Views
19 Pages

Dynamic objects present a major challenge for visual simultaneous localization and mapping (Visual SLAM), as feature measurements originating from moving regions can corrupt camera pose estimation and lead to inaccurate maps. In this paper, we propos...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
5 Citations
5,456 Views
11 Pages

9 May 2023

We present a novel stereo visual odometry (VO) model that utilizes both optical flow and depth information. While some existing monocular VO methods demonstrate superior performance, they require extra frames or information to initialize the model in...

(This article belongs to the Special Issue Robotics and Industrial Automation: From Methods to Applications)
  • Article
  • Open Access
7 Citations
2,636 Views
19 Pages

1 October 2025

Accurate and reliable vehicle localization is essential for autonomous driving in complex outdoor environments. Traditional feature-based visual–inertial odometry (VIO) suffers from sparse features and sensitivity to illumination, limiting robu...

(This article belongs to the Special Issue AI-Driving for Autonomous Vehicles)
  • Article
  • Open Access
4 Citations
4,302 Views
16 Pages

Deep HDR Deghosting by Motion-Attention Fusion Network

  • Yifan Xiao,
  • Peter Veelaert and
  • Wilfried Philips

16 October 2022

Multi-exposure image fusion (MEF) methods for high dynamic range (HDR) imaging suffer from ghosting artifacts when dealing with moving objects in dynamic scenes. The state-of-the-art methods use optical flow to align low dynamic range (LDR) images be...

(This article belongs to the Section Internet of Things)
  • Article
  • Open Access
2 Citations
2,334 Views
18 Pages

Dynamic Response Simulation for a Novel Single-Point Mooring Gravity-Type Deep-Water Net Cage Under Irregular Wave and Current

  • Guoliang Pang,
  • Chengyu Wan,
  • Liuyang Sui,
  • Shiyao Zhu and ,
  • Hangfei Liu,
  • Gen Li,
  • Taiping Yuan,
  • Yu Hu,
  • Qiyou Tao and
  • Xiaohua Huang
  • + 5 authors+ 0 author

4 February 2025

This study investigated the structural response characteristics of a novel single-point mooring gravity-type deep-water (SPM-GDW) net cage under irregular waves and currents. A hydrodynamic numerical model of the cage was created and validated throug...

(This article belongs to the Special Issue Advances in Applied Marine Sciences and Engineering—2nd Edition)
  • Article
  • Open Access
1 Citations
7,907 Views
12 Pages

After Total Knee Arthroplasty, Monitored Active Ankle Pumping Improves Lower Leg Circulation More Than Unmonitored Pumping: A Pilot Study

  • Ming-Chou Ku,
  • Yuan-Hsin Tsai,
  • Po-Cheng Cheng,
  • Ting-I Yang and ,
  • Hui-Wen Ho,
  • Min-Fei Liao,
  • Yu-Tzu Tseng,
  • Ming-Tsung Lee and
  • Yen-Nien Chen
  • + 4 authors+ 0 author

8 September 2022

(1) Background: deep venous thrombosis (DVT) has long been recognized as the most devastating complication after total knee replacement (TKR). To prevent DVT, intermittent pneumatic compression to improve venous return in the lower leg has been advoc...

(This article belongs to the Section Applied Biosciences and Bioengineering)
  • Article
  • Open Access
26 Citations
15,474 Views
26 Pages

DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors

  • Anargyros Chatzitofis,
  • Dimitrios Zarpalas,
  • Stefanos Kollias and
  • Petros Daras

11 January 2019

In this paper, a marker-based, single-person optical motion capture method (DeepMoCap) is proposed using multiple spatio-temporally aligned infrared-depth sensors and retro-reflective straps and patches (reflectors). DeepMoCap explores motion capture...

(This article belongs to the Special Issue Depth Sensors and 3D Vision)
  • Article
  • Open Access
1,225 Views
16 Pages

Background/Objectives: In laparoscopic and robot-assisted surgery, bleeding may rapidly impair operative-field readability and procedural safety. In the broader Robin Heart teleoperation framework, interpretation of such events is relevant not only f...

(This article belongs to the Special Issue The Application of Artificial Intelligence in Surgical Procedures)
  • Article
  • Open Access
2,235 Views
19 Pages

Vortex-Induced Vibration of Deep-Sea Mining Pipes: Analysis Using the Slicing Method

  • Xiangzhao Wu,
  • Song Sang,
  • Youwei Du,
  • Fugang Liu and
  • Jintao Zhang

20 December 2024

Deep-sea mining pipes are different from traditional ocean risers articulated at both ends: they are free-suspended, weakly constrained at the bottom, and have an intermediate silo at the end, compared to which relatively little research has been car...

  • Article
  • Open Access
963 Views
21 Pages

Dense Optical Flow Retrieval of Wildfire Smoke Plume Motion from Spaceborne and Airborne Imagery

  • Igor Yanovsky,
  • Nicholas LaHaye,
  • Olga V. Kalashnikova,
  • Derek J. Posselt and
  • William C. Porter

6 June 2026

This paper evaluates a dense, total-variation-based optical flow method for retrieving wildfire smoke plume motion vectors from geostationary, deep-space, and airborne remote sensing imagery. Using multiple major fire events, we assess the robustness...

  • Article
  • Open Access
34 Citations
5,052 Views
21 Pages

A Novel Change Detection Method for Natural Disaster Detection and Segmentation from Video Sequence

  • Huijiao Qiao,
  • Xue Wan,
  • Youchuan Wan,
  • Shengyang Li and
  • Wanfeng Zhang

7 September 2020

Change detection (CD) is critical for natural disaster detection, monitoring and evaluation. Video satellites, new types of satellites being launched recently, are able to record the motion change during natural disasters. This raises a new problem f...

(This article belongs to the Special Issue Innovations in Photogrammetry and Remote Sensing: Modern Sensors, New Processing Strategies and Frontiers in Applications)
  • Proceeding Paper
  • Open Access
694 Views
9 Pages

Transonic buffet is a critical self-sustained shock/boundary-layer instability limiting the flight envelope of modern transport aircraft. This study investigates the interaction between shock buffet and forced wing motion on the Airbus XRF-1 wind tun...

(This article belongs to the Proceedings of The 15th EASN International Conference on “Innovation in Aviation & Space Towards Sustainability Today & Tomorrow”)
  • Article
  • Open Access
15 Citations
3,874 Views
17 Pages

31 October 2021

In deep ocean transportation pipeline, the swirling internal flow has a significant impact on the marine minerals transportation efficiency and safety. Therefore, the present work investigates various swirl flow motions for the slurry transport chara...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
15 Citations
5,422 Views
19 Pages

Traffic Anomaly Prediction System Using Predictive Network

  • Waqar Riaz,
  • Chenqiang Gao,
  • Abdullah Azeem,
  • Saifullah and ,
  • Jamshaid Allah Bux and
  • Asif Ullah
  • + 1 author+ 0 author

18 January 2022

Anomaly anticipation in traffic scenarios is one of the primary challenges in action recognition. It is believed that greater accuracy can be obtained by the use of semantic details and motion information along with the input frames. Most state-of-th...

(This article belongs to the Special Issue Computer Vision and Image Processing)
  • Article
  • Open Access
9 Citations
4,548 Views
15 Pages

27 May 2021

Motion in videos refers to the pattern of the apparent movement of objects, surfaces, and edges over image sequences caused by the relative movement between a camera and a scene. Motion, as well as scene appearance, are essential features to estimate...

(This article belongs to the Section Vehicular Sensing)
  • Article
  • Open Access
14 Citations
5,092 Views
18 Pages

Optical Flow-Based Obstacle Detection for Mid-Air Collision Avoidance

  • Daniel Vera-Yanez,
  • António Pereira,
  • Nuno Rodrigues,
  • José Pascual Molina and ,
  • Arturo S. García and
  • Antonio Fernández-Caballero
  • + 1 author+ 0 author

9 May 2024

The sky may seem big enough for two flying vehicles to collide, but the facts show that mid-air collisions still occur occasionally and are a significant concern. Pilots learn manual tactics to avoid collisions, such as see-and-avoid, but these rules...

(This article belongs to the Section Optical Sensors)
  • Article
  • Open Access
8 Citations
2,956 Views
18 Pages

23 May 2022

A pressure-controlled jet crushing tool (PJCT) for the exploitation of deep-sea natural gas hydrate (NGH) was invented to achieve sediment crushing and cavity creation. The opening and closing of tool is controlled by changing the internal flow rate...

(This article belongs to the Topic Processing, Analysis, Modelling and Mechanics of Materials and Structures)
  • Article
  • Open Access
5 Citations
9,783 Views
34 Pages

12 December 2018

Optical flow is defined as the motion field of pixels between two consecutive images. Traditionally, in order to estimate pixel motion field (or optical flow), an energy model is proposed. This energy model is composed of (i) a data term and (ii) a r...

(This article belongs to the Special Issue Information Technology: New Generations (ITNG 2018))
  • Article
  • Open Access
2 Citations
4,429 Views
22 Pages

Motion Capture in Mixed-Reality Applications: A Deep Denoising Approach

  • André Correia Gonçalves,
  • Rui Jesus and
  • Pedro Mendes Jorge

Motion capture is a fundamental technique in the development of video games and in film production to animate a virtual character based on the movements of an actor, creating more realistic animations in a short amount of time. One of the ways to obt...

  • Article
  • Open Access
16 Citations
3,619 Views
20 Pages

Two-Stage Video Violence Detection Framework Using GMFlow and CBAM-Enhanced ResNet3D

  • Mohamed Mahmoud,
  • Bilel Yagoub,
  • Mostafa Farouk Senussi,
  • Mahmoud Abdalla and ,
  • Mahmoud Salaheldin Kasem and
  • Hyun-Soo Kang
  • + 1 author+ 0 author

8 April 2025

Video violence detection has gained significant attention in recent years due to its applications in surveillance and security. This paper proposes a two-stage framework for detecting violent actions in video sequences. The first stage leverages GMFl...

(This article belongs to the Special Issue Advanced Research in Neural Networks, Machine Learning, and Image Processing)
  • Article
  • Open Access
32 Citations
9,598 Views
17 Pages

Prediction of Short-Time Cloud Motion Using a Deep-Learning Model

  • Xinyue Su,
  • Tiejian Li,
  • Chenge An and
  • Guangqian Wang

26 October 2020

A cloud image can provide significant information, such as precipitation and solar irradiation. Predicting short-time cloud motion from images is the primary means of making intra-hour irradiation forecasts for solar-energy production and is also imp...

(This article belongs to the Special Issue Artificial Intelligence and Machine Learning: Application in Predictive Hydrological Models)
  • Article
  • Open Access
20 Citations
3,851 Views
16 Pages

Numerical Analysis of Single-Particle Motion Using CFD-DEM in Varying-Curvature Elbows

  • Chao Ning,
  • Yalin Li,
  • Ping Huang,
  • Hongbo Shi and
  • Haichao Sun

Centrifugal pumps are the critical components in deep-sea mining. In order to investigate the particle motion in the curved channel of the impeller, three different types of curvature conform to blade profile to simplify the impeller design of pumps....

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
58 Citations
5,550 Views
19 Pages

Experimental Research on Hydraulic Collecting Spherical Particles in Deep Sea Mining

  • Guocheng Zhao,
  • Longfei Xiao,
  • Tao Peng and
  • Mingyuan Zhang

25 July 2018

Hydraulic collecting is the key technology in deep sea mining and dredging engineering. It determines economic benefits of the project and environmental issues. However, mechanistic studies of hydraulic collecting are rarely described. In this study,...

  • Feature Paper
  • Article
  • Open Access
8 Citations
2,188 Views
15 Pages

25 August 2024

Deep-sea minerals are regarded as the most economically viable and promising mineral resource. Vertical hydraulic lifting represents one of the most promising methods for deep-sea mining lifting systems. To mitigate the potential for clogging due to...

(This article belongs to the Section K: State-of-the-Art Energy Related Technologies)
  • Feature Paper
  • Review
  • Open Access
5 Citations
3,315 Views
22 Pages

Gas–liquid mixtures are present in numerous industrial applications, such as in the process industry, oil production and transport with natural gas, deep-sea extraction, and irrigation. Any pump may have to carry multiphase flows. However, the...

(This article belongs to the Special Issue Advances in Critical Aspects of Turbomachinery Components and Systems)
  • Article
  • Open Access
51 Citations
5,193 Views
19 Pages

Research of Particle Motion in a Two-Stage Slurry Transport Pump for Deep-Ocean Mining by the CFD-DEM Method

  • Xianghui Su,
  • Zhenji Tang,
  • Yi Li,
  • Zuchao Zhu and ,
  • Kamila Mianowicz and
  • Peter Balaz
  • + 1 author+ 0 author

19 December 2020

The slurry transport pump is the key equipment of deep-ocean mining systems. The motion law of coarse particles in the pump is not clear enough. In this paper, a hydraulic model of a laboratory-scale two-stage slurry transport pump is constructed, an...

  • Article
  • Open Access
19 Citations
5,927 Views
28 Pages

A Hierarchical Deep Fusion Framework for Egocentric Activity Recognition using a Wearable Hybrid Sensor System

  • Haibin Yu,
  • Guoxiong Pan,
  • Mian Pan,
  • Chong Li and ,
  • Wenyan Jia,
  • Li Zhang and
  • Mingui Sun
  • + 2 authors+ 0 author

28 January 2019

Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its wide applicability in medical care, smart homes, and security monitoring. In this study,...

(This article belongs to the Special Issue Computational Intelligence-Based Sensors)
  • Article
  • Open Access
842 Views
20 Pages

Underwater Moving Target Localization Based on High-Density Pressure Array Sensing

  • Jiamin Chen,
  • Yilin Li,
  • Ruixin Chen,
  • Wenjun Li and ,
  • Keqiang Yue and
  • Ruixue Li
  • + 1 author+ 0 author

The artificial lateral line sensing principle provides a promising approach for underwater target perception and the navigation of underwater vehicles in complex flow environments. However, the highly nonlinear hydrodynamic mechanisms in complex flow...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
25 Citations
5,602 Views
32 Pages

Towing Analysis and Validation of a Fully Assembled Floating Offshore Wind Turbine Based on an Experimental Study

  • Rahul Chitteth Ramachandran,
  • Jorrit-Jan Serraris,
  • Jaume Hernandez Montfort,
  • Erik-Jan De Ridder and ,
  • Cian Desmond and
  • Jimmy Murphy
  • + 1 author+ 0 author

The offshore wind sector is moving into deep waters and using floating platforms to harness the higher wind speeds in exposed locations. There are various floating platform types currently in development, but semi-submersibles are considered the most...

(This article belongs to the Section Marine Energy)
  • Review
  • Open Access
76 Citations
7,113 Views
48 Pages

Flow-Induced Vibrations of Single and Multiple Heated Circular Cylinders: A Review

  • Ussama Ali,
  • Md. Islam,
  • Isam Janajreh,
  • Yap Fatt and
  • Md. Mahbub Alam

16 December 2021

This study is an effort to encapsulate the fundamentals and major findings in the area of fluid-solid interaction, particularly the flow-induced vibrations (FIV). Periodic flow separation and vortex shedding stretching downstream induce dynamic fluid...

(This article belongs to the Special Issue Wake, Energy, and Heat 2021)
  • Article
  • Open Access
81 Citations
9,899 Views
23 Pages

30 January 2020

This study presents a new concept design combining multiple megawatt (MW) vertical-axis wind turbines (VAWTs) and a solar array with a floating steel fish-farming cage. This combined wind–solar–aquaculture (WSA) system is intended to util...

(This article belongs to the Special Issue Foundation Systems for Offshore Wind Turbines)
  • Article
  • Open Access
1,012 Views
15 Pages

24 April 2026

Camera rotation estimation is a key component in video stabilization and motion analysis. In many practical scenarios, inertial measurements are unavailable or temporally unreliable, while classical geometric pipelines degrade under blur, low texture...

(This article belongs to the Section Optical Sensors)
  • Article
  • Open Access
22 Citations
4,532 Views
16 Pages

TSML: A New Pig Behavior Recognition Method Based on Two-Stream Mutual Learning Network

  • Wangli Hao,
  • Kai Zhang,
  • Li Zhang,
  • Meng Han and ,
  • Wangbao Hao,
  • Fuzhong Li and
  • Guoqiang Yang
  • + 2 authors+ 0 author

26 May 2023

Changes in pig behavior are crucial information in the livestock breeding process, and automatic pig behavior recognition is a vital method for improving pig welfare. However, most methods for pig behavior recognition rely on human observation and de...

(This article belongs to the Special Issue Smart Mobile and Sensing Applications)
  • Article
  • Open Access
5 Citations
1,744 Views
20 Pages

20 March 2025

In dredging operations, the efficient transportation of dredged materials presents a significant and intricate challenge. This study focuses on the motion and resistance characteristics of coarse-grained dredged materials during pipeline conveyance....

  • Article
  • Open Access
86 Views
22 Pages

Video Stabilization Based on Key-Structure Semantic Constraints and Grid Motion Fusion

  • Xiaobing Yu,
  • Yuqing Zhang,
  • Chao Zheng,
  • Zhihui Fan and
  • Tianming Zhan

5 November 2026

To address video jitter and key-structure positional drift in industrial surveillance scenarios, this paper proposes a video stabilization method based on key-structure semantic constraints and grid motion fusion. First, Segment Anything Model 3 (SAM...

of 4