A Global Registration Method for Satellite Image Series

2021 ◽  
Author(s):  
Charles Hessel ◽  
Carlo De Franchis ◽  
Gabriele Facciolo ◽  
Jean-Michel Morel
Keyword(s):  
Satellite Image ◽  
Registration Method ◽  
Image Series ◽  
Global Registration

scholarly journals Deep-learning-based flexible pipeline for segmenting and tracking cells in 3D image time series for whole brain imaging

2018 ◽  
Author(s):  
Chentao Wen ◽  
Takuya Miura ◽  
Yukako Fujie ◽  
Takayuki Teramoto ◽  
Takeshi Ishihara ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Imaging ◽  
Data Augmentation ◽  
Sampling Rate ◽  
Artificial Noise ◽  
3D Image ◽  
Whole Brain ◽  
Registration Method ◽  
Point Set Registration ◽  
Image Series

AbstractThe brain is a complex system that operates based on coordinated neuronal activities. Brain-wide cellular calcium imaging techniques have quickly advanced in recent years and become powerful tools for understanding the neuronal activities of small animal models. The whole brain imaging generally requires to extract the neuronal activities from three-dimensional (3D) image series. Unfortunately, the 3D image series are obtained under imaging conditions different among laboratories and extracting neuronal activities from the data requires multiple processes. Therefore researchers need to develop their own software, which has prevented the application of whole-brain imaging experiments in more laboratories. Here, we combined traditional image processing techniques with the powerful deep-learning method which can be flexibly modified to fit 3D image data in the nematode Caenorhabditis elegans obtained under different conditions. We first trained the 3D U-net deep network to classify each pixel into cell and non-cell categories. Cells merged as a whole region were further separated into individual cells by watershed segmentation. The cells were then tracked in 3D space over time with the combination of a feedforward network and a point set registration method to use local and global relative positions of the cells, respectively. Remarkably, one manually annotated 3D image combined with data augmentation was sufficient for training the deep networks to obtain satisfactory tracking results. Our method correctly tracked more than 98% of neurons in three different image datasets and successfully extracted brain-wide neuronal activities. Our method worked well even when the sampling rate was reduced: 86% correct in case 4/5 frames were removed, and when artificial noise was added into the raw images: 91% correct in case 35 times of background-level noise was added. Our results proved that deep learning is widely applicable to different datasets and can help us in establishing a flexible pipeline for extracting whole brain activities.

scholarly journals Well-Distributed Feature Extraction for Image Registration Using Histogram Matching

2019 ◽  
Vol 9 (17) ◽  
pp. 3487 ◽  
Author(s):  
Muhammad Tariq Mahmood ◽  
Ik Hyun Lee
Keyword(s):  
High Resolution ◽  
Image Registration ◽  
Satellite Image ◽  
Computational Cost ◽  
Control Points ◽  
Scale Invariant ◽  
Registration Method ◽  
Histogram Matching ◽  
Spatial Alignment ◽  
High Resolution Satellite Imagery

Image registration is a spatial alignment of corresponding images of the same scene acquired from different views, sensors, and time intervals. Especially, satellite image registration is a challenging task due to the high resolution of images. In addition, demands for high resolution satellite imagery are increased for more detailed and precise information in land planning, urban planning, and Earth observation. Commonly, feature-based methods are applied for image registration. In these methods, first control or key points are detected using feature detector such as scale-invariant feature transform (SIFT). The numbers and the distribution of these control points are important for the remaining steps of registration. These methods provide reasonable performance; however, they suffer from high computational cost and irregular distribution of control points. To overcome these limitations, we propose an area-based registration method using histogram matching and zero mean normalized cross-correlation (ZNCC). In multi-spectral satellite images, first, different spectral responses are adjusted by using histogram matching. Then, ZNCC is utilized to extract well-distributed control points. In addition, fast Fourier transform (FFT) and block-wise processing are applied to reduce the computational cost. The proposed method is evaluated through various input datasets. The results demonstrate its efficacy and accuracy in image registration.

scholarly journals Global Registration of Terrestrial Laser Scanner Point Clouds Using Plane-to-Plane Correspondences

2020 ◽  
Vol 12 (7) ◽  
pp. 1127
Author(s):  
Nadisson Luis Pavan ◽  
Daniel Rodrigues dos Santos ◽  
Kourosh Khoshelham
Keyword(s):  
Laser Scanner ◽  
Point Clouds ◽  
Information Modeling ◽  
Coordinate Frame ◽  
Complex Numbers ◽  
Terrestrial Laser Scanner ◽  
Registration Method ◽  
Matching Algorithm ◽  
Global Registration ◽  
Global Consistency

Registration of point clouds is a central problem in many mapping and monitoring applications, such as outdoor and indoor mapping, high-speed railway track inspection, heritage documentation, building information modeling, and others. However, ensuring the global consistency of the registration is still a challenging task when there are multiple point clouds because the different scans should be transformed into a common coordinate frame. The aim of this paper is the registration of multiple terrestrial laser scanner point clouds. We present a plane-based matching algorithm to find plane-to-plane correspondences using a new parametrization based on complex numbers. The multiplication of complex numbers is based on analysis of the quadrants to avoid the ambiguity in the calculation of the rotation angle formed between normal vectors of adjacent planes. As a matching step may contain several matrix operations, our strategy is applied to reduce the number of mathematical operations. We also design a novel method for global refinement of terrestrial laser scanner data based on plane-to-plane correspondences. The rotation parameters are globally refined using operations of quaternion multiplication, while the translation parameters are refined using the parameters of planes. The global refinement is done non-iteratively. The experimental results show that the proposed plane-based matching algorithm efficiently finds plane correspondences in partial overlapping scans providing approximate values for the global registration, and indicate that an accuracy better than 8 cm can be achieved by using our global fine plane-to-plane registration method.

Automatic Detection of Anomalous Time Trends from Satellite Image Series to Support Agricultural Monitoring

2021 ◽  
Author(s):  
Corrado Avolio ◽  
Alessia Tricomi ◽  
Massimo Zavagli ◽  
Laura De Vendictis ◽  
Fabio Volpe ◽  
...  
Keyword(s):  
Time Trends ◽  
Satellite Image ◽  
Automatic Detection ◽  
Image Series

Crop Yield Estimation Using Multi-Source Satellite Image Series and Deep Learning

2020 ◽  
Author(s):  
Gohar Ghazaryan ◽  
Sergii Skakun ◽  
Simon Konig ◽  
Ehsan Eyshi Rezaei ◽  
Stefan Siebert ◽  
...  
Keyword(s):  
Deep Learning ◽  
Crop Yield ◽  
Satellite Image ◽  
Yield Estimation ◽  
Image Series

scholarly journals A GLOBAL REGISTRATION ALGORITHM OF THE SINGLE-CLOSED RING MULTI-STATIONS POINT CLOUD

2018 ◽  
Vol XLII-3 ◽  
pp. 2093-2100
Author(s):  
R. Yang ◽  
L. Pan ◽  
Z. Xiang ◽  
H. Zeng
Keyword(s):  
Point Cloud ◽  
Simulation Experiment ◽  
Rotation Matrix ◽  
Registration Method ◽  
Registration Algorithm ◽  
Global Registration ◽  
Closed Ring ◽  
Definition Of ◽  
Station Point ◽  
Implementation Steps

Aimed at the global registration problem of the single-closed ring multi-stations point cloud, a formula in order to calculate the error of rotation matrix was constructed according to the definition of error. The global registration algorithm of multi-station point cloud was derived to minimize the error of rotation matrix. And fast-computing formulas of transformation matrix with whose implementation steps and simulation experiment scheme was given. Compared three different processing schemes of multi-station point cloud, the experimental results showed that the effectiveness of the new global registration method was verified, and it could effectively complete the global registration of point cloud.

scholarly journals Learned Representation of Satellite Image Series for Data Compression

2020 ◽  
Vol 12 (3) ◽  
pp. 497 ◽  
Author(s):  
Liang Liao ◽  
Jing Xiao ◽  
Yating Li ◽  
Mi Wang ◽  
Ruimin Hu
Keyword(s):  
Reference Frames ◽  
Satellite Image ◽  
Representation Learning ◽  
Video Data ◽  
Image Series ◽  
Representation Model ◽  
Video Frames ◽  
Main Challenge ◽  
Reference Images ◽  
Historical Image

Real-time transmission of satellite video data is one of the fundamentals in the applications of video satellite. Making use of the historical information to eliminate the long-term background redundancy (LBR) is considered to be a crucial way to bridge the gap between the compressed data rate and the bandwidth between the satellite and the Earth. The main challenge lies in how to deal with the variant image pixel values caused by the change of shooting conditions while keeping the structure of the same landscape unchanged. In this paper, we propose a representation learning based method to model the complex evolution of the landscape appearance under different conditions by making use of the historical image series. Under this representation model, the image is disentangled into the content part and the style part. The former represents the consistent landscape structure, while the latter represents the conditional parameters of the environment. To utilize the knowledge learned from the historical image series, we generate synthetic reference frames for the compression of video frames through image translation by the representation model. The synthetic reference frames can highly boost the compression efficiency by changing the original intra-frame prediction to inter-frame prediction for the intra-coded picture (I frame). Experimental results show that the proposed representation learning-based compression method can save an average of 44.22% bits over HEVC, which is significantly higher than that using references generated under the same conditions. Bitrate savings reached 18.07% when applied to satellite video data with arbitrarily collected reference images.

scholarly journals HEALPix-IA: A Global Registration Algorithm for Initial Alignment

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 427 ◽  
Author(s):  
Yongzhuo Gao ◽  
Zhijiang Du ◽  
Wei Xu ◽  
Mingyang Li ◽  
Wei Dong
Keyword(s):  
Point Cloud ◽  
Cross Correlation ◽  
Correlation Method ◽  
Real Data ◽  
Initial Guess ◽  
Convergence Time ◽  
Image Method ◽  
Initial Alignment ◽  
Registration Method ◽  
Global Registration

Methods of point cloud registration based on ICP algorithm are always limited by convergence rate, which is related to initial guess. A good initial alignment transformation can sharply reduce convergence time and raise efficiency. In this paper, we propose a global registration method to estimate the initial alignment transformation based on HEALPix (Hierarchical Equal Area isoLatitude Pixelation of a sphere), an algorithm for spherical projections. We adopt EGI (Extended Gaussian Image) method to map the normals of the point cloud and estimate the transformation with optimized point correspondence. Cross-correlation method is used to search the best alignment results in consideration of the accuracy and robustness of the algorithm. The efficiency and accuracy of the proposed algorithm were verified with created model and real data from various sensors in comparison with similar methods.

Sign in / Sign up

Export Citation Format

Share Document