spatial consistency
Recently Published Documents


TOTAL DOCUMENTS

193
(FIVE YEARS 89)

H-INDEX

14
(FIVE YEARS 5)

Symmetry ◽  
2022 ◽  
Vol 14 (1) ◽  
pp. 140
Author(s):  
Huixiang Shao ◽  
Zhijiang Zhang ◽  
Xiaoyu Feng ◽  
Dan Zeng

Point cloud registration is used to find a rigid transformation from the source point cloud to the target point cloud. The main challenge in the point cloud registration is in finding correct correspondences in complex scenes that may contain many noise and repetitive structures. At present, many existing methods use outlier rejections to help the network obtain more accurate correspondences, but they often ignore the spatial consistency between keypoints. Therefore, to address this issue, we propose a spatial consistency guided network using contrastive learning for point cloud registration (SCRnet), in which its overall stage is symmetrical. SCRnet consists of four blocks, namely feature extraction block, confidence estimation block, contrastive learning block and registration block. Firstly, we use mini-PointNet to extract coarse local and global features. Secondly, we propose confidence estimation block, which formulate outlier rejection as confidence estimation problem of keypoint correspondences. In addition, the local spatial features are encoded into the confidence estimation block, which makes the correspondence possess local spatial consistency. Moreover, we propose contrastive learning block by constructing positive point pairs and hard negative point pairs and using Point-Pair-INfoNCE contrastive loss, which can further remove hard outliers through global spatial consistency. Finally, the proposed registration block selects a set of matching points with high spatial consistency and uses these matching sets to calculate multiple transformations, then the best transformation can be identified by initial alignment and Iterative Closest Point (ICP) algorithm. Extensive experiments are conducted on KITTI and nuScenes dataset, which demonstrate the high accuracy and strong robustness of SCRnet on point cloud registration task.


2022 ◽  
Vol 183 ◽  
pp. 164-177
Author(s):  
Yongjun Zhang ◽  
Siyuan Zou ◽  
Xinyi Liu ◽  
Xu Huang ◽  
Yi Wan ◽  
...  

2021 ◽  
Author(s):  
Ben Kefford ◽  
Susan J. Nichols ◽  
Richard Duncan

Biodiversity is declining, typically because of multiple anthropogenic stressors. Cumulative effects of multiple stressors are classified as additive, when cumulative effects are as expected from the stressor’s singular effects, synergistic when greater than additive or antagonistic when less than additive. Less attention has been given to the consistency of cumulative effects. We analysed stream insects, Ephemeroptera, Plecoptera and Trichoptera (EPT) data from two habitats spanning a 3,600 km latitudinal (S11◦-S43◦) gradient in eastern Australia. We found that the cumulative effect of salinity and suspended sediments on EPT family richness was inconsistent with additive, synergistic or antagonistic effects, and the reduction EPT family richness from increasing both stressors varied (48-70%) depending on habitat (riffle vs. edge), water temperature and terrain slope. Studies of cumulative effects of multiple stressors at one location risk not describing cumulative effects elsewhere and ecologists should consider the spatial consistency of multiple stressors.


PLoS ONE ◽  
2021 ◽  
Vol 16 (11) ◽  
pp. e0259961
Author(s):  
Marlenne A. Rodríguez-Malagón ◽  
Cassie N. Speakman ◽  
Grace J. Sutton ◽  
Lauren P. Angel ◽  
John P. Y. Arnould

Stable isotope analyses, particularly of carbon (δ13C) and nitrogen (δ15N), are used to investigate ecological relationships among species. For marine predators, research has shown the main factors influencing their intra-specific and intra-individual isotopic variation are geographical movements and changes in the composition of diet over time. However, as the differences seen may be the result of changes in the prey items consumed, a change in feeding location or the combination of both, knowledge of the temporal and spatial consistency in the isotopic values of prey becomes crucial for making accurate inferences about predator diets. This study used an abundant marine predator, the Australasian gannet (Morus serrator), as prey sampler to investigate the annual variation in fish and squid prey isotope values over a four-year period (2012–2015) and the geographic variation between two sites with contrasting oceanographic conditions. Significant inter-annual variation was observed in δ13C and/or δ15N values of five of the eight prey species analysed. The strongest inter-annual variation in both δ13C and δ15N values occurred in 2015, which coincided with a strong El Niño-Southern Oscillation (ENSO). This may suggest a temporal fluctuation in the geographic source of prey or the origin of their nutrients. These results suggest that it is important to consider the potential significant differences in isotopic values within the prey assemblages that predators consume. This is important to improve the interpretation of marine predator isotope results when determining the influence of environmental variability on their diets.


2021 ◽  
Vol 11 (23) ◽  
pp. 11348
Author(s):  
Huaqiao Xing ◽  
Jingge Niu ◽  
Chang Liu ◽  
Bingyao Chen ◽  
Shiyong Yang ◽  
...  

Accurate and up-to-date forest monitoring plays a significant role in the country’s society and economy. Many open-access global forest datasets can be used to analyze the forest profile of countries around the world. However, discrepancies exist among these forest datasets due to their specific classification systems, methodologies, and remote sensing data sources, which makes end-users difficult to select an appropriate dataset in different regions. This study aims to explore the accuracy, consistency, and discrepancies of eight widely-used forest datasets in Myanmar, including Hansen2010, CCI-LC2015, FROM-GLC2015/2017, FROM-GLC10, GLC-FCS2015/2020, and GlobeLand30-2020. Firstly, accuracy assessment is conducted by using 934 forest and non-forest samples with four different years. Then, spatial consistency of these eight datasets is compared in area and spatial distribution. Finally, the factors influencing the spatial consistency are analyzed from the aspects of terrain and climate. The results indicate that in Myanmar the forest area derived from GlobeLand30 has the best accuracy, followed by FROM-GLC10 and FROM-GLC2017. The eight datasets differ in spatial detail, with the mountains of northern Myanmar having the highest consistency and the seaward areas of southwestern Myanmar having the highest inconsistency, such as Rakhine and the Ayeyarwady. In addition, it is found that the spatial consistency of the eight datasets is closely related to the terrain and climate. The highest consistency among the eight datasets is found in the range of 1000–3500 m above sea level and 26°–35° slope. In the subtropical highland climate (Cwb) zone, the percentage of complete consistency among the eight datasets is as high as 60.62%, which is the highest consistency among the six climatic zones in Myanmar. Therefore, forest mapping in Myanmar should devote more effort to low topography, seaward areas such as border states like Rakhine, Irrawaddy, Yangon, and Mon. This is because these areas have complex and diverse landscape types and are prone to confusion between forest types (e.g., grassland, shrub, and cropland). The approach can also be applied to other countries, which will help scholars to select the most suitable forest datasets in different regions for analysis, thus providing recommendations for relevant forest policies and planning in different countries.


Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6254
Author(s):  
Shaodi Yang ◽  
Yuqian Zhao ◽  
Miao Liao ◽  
Fan Zhang

Medical image registration is an essential technique to achieve spatial consistency geometric positions of different medical images obtained from single- or multi-sensor, such as computed tomography (CT), magnetic resonance (MR), and ultrasound (US) images. In this paper, an improved unsupervised learning-based framework is proposed for multi-organ registration on 3D abdominal CT images. First, the explored coarse-to-fine recursive cascaded network (RCN) modules are embedded into a basic U-net framework to achieve more accurate multi-organ registration results from 3D abdominal CT images. Then, a topology-preserving loss is added in the total loss function to avoid a distortion of the predicted transformation field. Four public databases are selected to validate the registration performances of the proposed method. The experimental results show that the proposed method is superior to some existing traditional and deep learning-based methods and is promising to meet the real-time and high-precision clinical registration requirements of 3D abdominal CT images.


2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Zhijun Wang

Since the artistry of the work cannot be accurately described, the identification of reproducible plagiarism is more difficult. The identification of reproducible plagiarism of digital image works requires in-depth research on the artistry of artistic works. In this paper, a remote judgment method for plagiarism of painting image style based on wireless network multitask learning is proposed. According to this new method, the uncertainty of painting image samples is removed based on multitask learning algorithm edge sampling. The deep-level details of the painting image are extracted through the multitask classification kernel function, and most of the pixels in the image are eliminated. When the clustering density is greater than the judgment threshold, it can be considered that the two images have spatial consistency. It can also be judged based on this that the two images are similar, that is, there is plagiarism in the painting. The experimental results show that the discrimination rate is always close to 100%, the misjudgment rate of plagiarism of painting images has been reduced, and the various indicators in the discrimination process are the lowest, which fully shows that a very satisfactory discrimination result can be obtained.


Land ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 822
Author(s):  
Ali Asghari ◽  
Mohsen Kalantari ◽  
Abbas Rajabifard

Among 3D models, Building Information Models (BIM) can potentially support the integrated management of buildings’ physical and legal aspects in cadastres. However, there is not a systematic approach to author the cadastral information into the BIM models. Moreover, the common approaches for data validation only check the final cadastral output, and they ignore the data generation steps as potential avenues for validation. Therefore, this study aims to develop the criteria and standards to check the spatial consistency and integrity of BIM-based cadastral data in the process of generating the data. The paper utilises a case study approach as its methodology to investigate the requirements of generating a BIM-based cadastral model and identify the issues within the process. The results include a formative assessment (i.e., multistep validation approach during the data generation) alongside a summative assessment (i.e., one-step validation approach at the end of data generation). This study found the summative assessment alone insufficient for 3D cadastral data validation. The paper concludes that a formative and summative assessment together can improve the validity of the data. The results will potentially bring more efficiency to modern land administration processes by avoiding the accumulation of errors in 3D cadastral data generation.


Author(s):  
Lianli Gao ◽  
Yaya Cheng ◽  
Qilong Zhang ◽  
Xing Xu ◽  
Jingkuan Song

By adding human-imperceptible perturbations to images, DNNs can be easily fooled. As one of the mainstream methods, feature space targeted attacks perturb images by modulating their intermediate feature maps, for the discrepancy between the intermediate source and target features is minimized. However, the current choice of pixel-wise Euclidean Distance to measure the discrepancy is questionable because it unreasonably imposes a spatial-consistency constraint on the source and target features. Intuitively, an image can be categorized as "cat'' no matter the cat is on the left or right of the image. To address this issue, we propose to measure this discrepancy using statistic alignment. Specifically, we design two novel approaches called Pair-wise Alignment Attack and Global-wise Alignment Attack, which attempt to measure similarities between feature maps by high-order statistics with translation invariance. Furthermore, we systematically analyze the layer-wise transferability with varied difficulties to obtain highly reliable attacks. Extensive experiments verify the effectiveness of our proposed method, and it outperforms the state-of-the-art algorithms by a large margin. Our code is publicly available at https://github.com/yaya-cheng/PAA-GAA.


2021 ◽  
Vol 652 ◽  
pp. A109
Author(s):  
P. M. Galán-de Anta ◽  
M. Sarzi ◽  
T. W. Spriggs ◽  
B. Nedelchev ◽  
F. Pinna ◽  
...  

Context. Extragalactic planetary nebulae (PNe) are useful distance indicators and are often used to trace the dark-matter content in external galaxies. At the same time, PNe can also be used as probes of their host galaxy stellar populations and to help understand the later stages of stellar evolution. Previous works have indicated that a specific number of PNe per stellar luminosity can vary across different galaxies and as a function of stellar-population properties, for instance increasing with decreasing stellar metallicity. Aims. In this study we further explore the importance of stellar metallicity in driving the properties of the PNe population in early-type galaxies, using three edge-on galaxies in the Fornax cluster offering a clear view into their predominantly metal-rich and metal-poor regions near the equatorial plane or both below and above it, respectively. Methods. Using very large telescope-multi unit spectroscopic explorer (VLT-MUSE) integral-field observations and dedicated PNe detection procedures, we constructed the PNe luminosity function and computed the luminosity-specific number of PNe α in both in- and off-plane regions of our edge-on systems. Results. Comparing these α values with metallicity measurements also based on the same MUSE data, we find no evidence for an increase in the specific abundance of PNe when transitioning between metal-rich and metal-poor regions. Conclusions. Our analysis highlights the importance of ensuring spatial consistency to avoid misleading results when investigating the link between PNe and their parent stellar populations, and suggest that in passively evolving systems variations in the specific number of PNe may pertain to rather extreme metallicity regimes found either in the innermost or outermost regions of galaxies.


Sign in / Sign up

Export Citation Format

Share Document