SemFlow: Semantic-Driven Interpolation for Large Displacement Optical Flow
This paper presents a semantic-guided interpolation scheme (SemFlow) to handle motion boundaries and occlusions in large displacement optical flow. The basic idea is to segment images into superpixels and estimate their homographies for interpolation. In
Xianshun Wang +5 more
doaj +1 more source
A Vision‐Based Motion Compensation Method for Unmanned Aerial Vehicles
ABSTRACT In target tracking under background motion scenarios, background movement often significantly compromises detection and tracking accuracy. This paper proposes a visual motion compensation algorithm for unmanned aerial vehicles, integrating feature point detection, matching and robust geometric estimation methods.
Yiwei Wang, Weifeng Liu, Meng Zhou
wiley +1 more source
Accuracy Enhancement of Homography-Based Crack Width Calculation Using RGB-D Sensors
Accurate crack width measurement is important for structural condition assessment, but image-based methods are sensitive to oblique viewing angles and varying imaging distances.
Shijie Zhou +3 more
doaj +1 more source
Inspection method of images' overlap of UAV photogrammetry based on features matching
The overlapping degree of UAV aerial imagery is an important parameter in judging the quality of aerial photography. This paper applies the technology of image feature matching to realize the automatic inspection of low-altitude UAV aerial image overlap.
Li Jun, Huang Dengshan, Yang Peng
doaj +1 more source
An ASIFT-Based Local Registration Method for Satellite Imagery
Imagery registration is a fundamental step, which greatly affects later processes in image mosaic, multi-spectral image fusion, digital surface modelling, etc., where the final solution needs blending of pixel information from more than one images. It is
Xiangjun Wang +3 more
doaj +1 more source
Stay Local or Go Global: Geo‐Referenced Bounding Boxes for Tracking Wildlife in Thermal Drone Videos
An overview of the geo‐referenced drone‐based detection and tracking pipeline is presented. The workflow begins with flight execution, including mission planning, control, RTK‐based positioning and image metadata acquisition. In the pre‐processing stage, video synchronisation, frame extraction and camera‐calibration‐based undistortion are performed ...
Christoph Praschl +3 more
wiley +1 more source
Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration [PDF]
A novel Bayesian framework is proposed, which explicitly relates the homography of one video frame to the next through an affine transformation while explicitly modelling keypoint uncertainty.
Claasen, Paul J., de Villiers, J. P.
core +3 more sources
A Robust Deep Learning Framework for Steganography in 1D and 2D Barcodes
Barcodes are a key IoT technology for product identification and supply chain traceability, yet they are limited in data capacity and security. To address these limitations, we propose a barcode steganography framework based on image embedding and deep learning.
Yanfei Sun +3 more
wiley +1 more source
SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation
The traditional homography estimation pipeline consists of four main steps: feature detection, feature matching, outlier removal and transformation estimation. Recent deep learning models intend to address the homography estimation problem using a single
He, Zhenyu, Pei, Wenjie, Li, Yi
core
Asteroid Pose Estimation Method Based on Monocular Vision and Intelligent Perception
This paper proposes a pose estimation network based on geometric perception dual branch regression heads. By jointly optimizing rotation (Euler angle) and translation parameters and combining physical constraints to improve solution accuracy, the network achieves high‐precision solution of asteroid relative pose with a position estimation error of less
Chengbo Qiu +5 more
wiley +1 more source

