Taking Huancheng River in Hefei City as the study site, machine learning models such as linear regression, random forest, support vector regression, and lasso regression were utilized to establish the relationship between Landsat8 satellite data and water quality parameters, model the reflectance and water quality parameters of remote sensing image values, and compare the performance of four different models. Results showed that the random forest model performed best, and the accuracy of the inversion models for total nitrogen (TN), total phosphorus (TP), and ammonia nitrogen (NH3-N) was above 0.7. The concentration distribution map of water quality parameters showed that the pollution of TN and TP was the most significant in the northeast section of Huancheng River, while NH3-N was most present in the southwest section. The water eutrophication distribution map shows that the water body in the eastern section of the Huancheng River showed a moderate nutrition state.
Oxygen-releasing materials are often used in the treatment and restoration of urban waters as an important method to enhance dissolved oxygen. The development of materials with slow-release property can improve the durability and stability of oxygen release in practical engineering. This paper reviews the preparation methods and oxygen release performance of the slow-release oxygen materials reported in recent years. Moreover, the effects and mechanisms of slow-release oxygen materials on the occurrence, migration, and transformation of pollutants such as nutrients in sediments and overlying water of rivers and lakes are reviewed. Finally, prospects and suggestions for the application of slow-release oxygen materials in the remediation of rivers and lakes are proposed.
To judge ecosystem health of the shallow lakes along the shores of Taihu Lake in the process of ecological restoration, water body of Jinshugang polder was investigated during 2022. The comprehensive assessment index system of water ecological health was constructed, consisting of the target layer, criterion layer, and index layer, of which the criterion layer was composed of three items: function, integrity, and stability. The index layer was composed of 14 major items such as comprehensive water quality and nutritional status and 28 small items such as pH, temperature, and dissolved oxygen. The results showed that during the process of ecological restoration, functional evaluation index reached the highest in autumn, integrity evaluation index was better than that in spring and summer, stability evaluation index was the best in summer, with 70% of the points at the “healthy” level, and the comprehensive evaluation index of aquatic ecological health continued to increase. The results and system of comprehensive evaluation of water ecological health formulated for shallow lakes in Taihu Lake are not only important for subsequent restoration and management, but also provide a reference for water ecological restoration and evaluation of other lakes.
Industrial park wastewater is characterized by various components, changeable water quality, complex pollutant factors, poor biodegradability, and high emission standards. A full-scale industrial park wastewater treatment plant in Deqing was used as an example to investigate the technical-economic feasibility of a process combining hydrolysis acidification, anaerobic-anoxic-oxic-anoxic-oxic (A2/O+AO), and Fenton oxidation in treating wastewater from various enterprises, primarily printing and dyeing, food manufacturing, and metal processing factories. The effluent chemical oxygen demand, ammoniacal nitrogen, total nitrogen, and total phosphorus stably met the required discharge limits for Urban Sewage Treatment Plants (DB33/2169—2018), while other indicators reached Grade A standard for Urban Sewage Treatment Plants (GB18918—2002). The engineering investment and actual operation costs of the wastewater treatment plant were 8200 and 2.39 yuan/m3, respectively.
Suppressing water glint pollution from remote sensing images and reconstructing image information are effective ways to improve the quality of UAV (unmanned aerial vehicle) remote sensing information and increase water environment monitoring areas. It is difficult to apply traditional glint information reconstruction algorithms to UAV hyperspectral images. This study proposes an algorithm for automatic glint detection, removal, and information reconstruction. First, NDWI (normalized difference water index) was used to extract the water body, and the lowest value of the sum of grayscale images in the entire band was used as a threshold to segment the glint, and the Laplace operator was used to extract the glint texture. The difference between the two areas was calculated through multiple rounds of morphological expansion and threshold updates. The lowest difference occurrence frequency was obtained by voting, and the best threshold was obtained in reverse to remove the glint automatically. Then, we determined the matching bands based on principal component analysis and compared the minimum similarity of matching blocks of different sizes to obtain the best size of the image blocks. Finally, we used an improved Criminisi algorithm to reconstruct the flare removal region. The removal algorithm was applied to four real glint scenarios with a removal rate > 99%; the reconstruction algorithm results are superior to those of other algorithms both subjectively and objectively, and the difference between the variation coefficient of each band of the glint reconstruction for water and normal water was within 1%, indicating good spectral application capability.
In this study, constructed wetland structures were established using different substrates (gravel and aerated concrete), with or without cannas planting. Subsequently , the effects of different working conditions on rainwater runoff pollution were investigated through small experiments. The cost of the constructed wetland with aerated concrete and cannas (4.20 yuan/working condition) was slightly higher (1.00 ~ 2.90 yuan/working condition higher) than those under other working conditions. However, in both cycles of operation (i.e., alternating operation for 30 h and drying for 48 h), the average removal rates of ${\rm{NH}}_4^+ $-N, ${\rm{NO}}_3^- $-N, TN, ${\rm{PO}}_4^{3-} $, TP and CODCr were 73.3%, 47.0%, 85.4%, 56.4%, 76.0%, and 65.5%, respectively. These values were higher than those under other working conditions by an average of 10.9% ~ 18.8%. Thus, this constructed wetland structure had the best effect and the highest cost performance. Therefore, it is suitable for promotion and application.
In this study, a pilot-scale tidal-flow paddy wetland system based on multifunctional coupling was constructed to treat land-based aquaculture tailwater of Macrobrachium rosenbergii. This study explored the purification ability, CH4 emissions, arthropod diversity, and comprehensive benefits of the tidal-flow paddy wetland system to provide a scientific basis for the application of this system. The results showed that the tidal-flow paddy wetland system could effectively purify land-based aquaculture tailwater. The removal capacities of dissolved inorganic nitrogen, total nitrogen, dissolved inorganic phosphorus, and total phosphorus were approximately 54.3%, 44.9%, 42.9%, and 43.0%, respectively. Simultaneously, the system had no negative impact on the external environment and indirectly purifies river water. Compared with conventional paddy fields, the tidal-flow paddy wetland system reduced CO2 and CH4 emissions by 5.4% and 92.5%, respectively. Compared to conventional paddy fields during the flooding period, the abundance of the mcrA gene in the tidal-flow paddy wetland decreased by 82.3%. Moreover, the tidal-flow paddy wetland system improved biodiversity and natural enemy abundance/pest abundance, inhibited pest outbreaks, supported more species, and increased comprehensive benefits compared to the control.
Since the Yingwuzhou Wetland was established over five years ago, we have conducted comprehensive field investigation and monitoring. Constructing a reliable evaluation system with long-term monitoring data is important for the evaluation of coastal ecological restoration projects. Here, we used the emergy analysis method and collected the relevant data through field research, scientific monitoring, and literature review to construct an energy analysis structure chart and emergy value index system for the Yingwuzhou Wetland. The main emergy indexes, such as the natural assets and ecosystem services of the wetland, were analyzed, and its functional performance was compared for different restoration periods. The results show that the total emergy of the natural assets in the Yingwuzhou Wetland in 2021 was 8.92 × 1016 sej, which is equivalent to the emergy-monetary value of 2.247 × 105 yuan; the total emergy of ecosystem services was 8.88 × 1017 sej·a–1. After the implementation of restoration, the ecological quality of Yingwuzhou was significantly improved, and its natural assets and ecosystem service emergy were 5.01 and 5.73 times higher than those before restoration. The emergy self-support ratio (ESR) of the Yingwuzhou Wetland ecosystem was 0.47, and the emergy yield ratio (EYR) and emergy sustainable index (ESI) were 28.29 and 25.03, respectively, indicating that the wetland had high output efficiency and suitable space for sustainable development. This study shows that based on long-term monitoring data, the emergy analysis method can better reflect the effectiveness of coastal ecological restoration projects, and the evaluation system and method can provide reference for similar coastal restoration projects in the future.
Due to the influence of tidal processes, sampling and study of microplastics in estuarine areas have been hampered by inconsistent research methods and large data errors. In this study, whole-water depth sampling was conducted in the Jiulong River estuary using the pumping method in August of 2019. The abundances and distribution patterns of microplastics among different water layers and stations were analyzed and compared with research studies performed using different sampling methods. The results showed that the microplastic abundances in the surface, middle, and bottom waters of the Jiulong River estuary were markedly different and influenced by tidal effects. The abundances of microplastics obtained by different sampling methods were also significantly different. The abundance of microplastics in the surface water was significantly higher than the abundances in the middle and bottom waters near the source of pollution, and the abundances of microplastics in the middle and bottom waters were higher than the abundance in the surface water within the main estuary, which is subject to strong tidal action and has obvious stratification. The pumping method was more effective than the trawling method at retaining plastic fibers. The volume of water sample filtered by the pumping method and the size of the filtering mesh had significant effects on the abundances and sizes of the obtained microplastics. Different sampling methods lead to considerable differences in microplastic abundance results, and it is necessary to take tidal effects into account during microplastic monitoring in tidal estuaries. Therefore, it is recommended that operational monitoring and flux observations of microplastics in tidal estuaries be established and that sampling methods for observation of full tidal periods of flood and dry seasons and high and low tides should be used.
Large cascade reservoirs in basins impound water in late summer and early autumn and release water in the dry season of the following year. These activities affect seasonal river discharge into the sea which, in turn, affects saltwater intrusion in estuaries and the utilization of freshwater resources. This study evaluated the effective storage capacity of large cascade reservoirs and the value of cross-basin water transfers by the South-to-North Water Transfer Project in the Yangtze River Basin. The estuarine and coastal three-dimensional numerical model ECOM-si was used to simulate and analyze the impact of major projects on estuarine saltwater intrusion and freshwater resources. In 2020, the effective storage capacity of large reservoirs built in the middle and upper reaches of the Yangtze River Basin was 70.611 billion cubic meters with a mean reduction in monthly river discharge of 13,398 m3/s during the storage period of September to October. By 2035, the completion of additional reservoirs in the basin will raise the total effective storage capacity of these reservoirs to 94.388 billion cubic meters and reduce the average monthly runoff by 17909 m3/s during the storage period. Using data on average monthly river discharge measured at the Datong Hydrological Station from 1950 to 2020, and by taking into account variations in river discharge by major projects in the basin, the average monthly river discharge from August to October from 2020 to 2035 in regular- and extra dry hydrological years was calculated. Numerical simulation results show that saltwater intrusion from September to October will increase due to impoundment in cascade reservoirs and decreased river discharge. During regular hydrological years, freshwater can be obtained from the four water reservoirs in the South Branch of the Yangtze River Estuary from September to October. However, water from the Dongfengxisha, Taicang, Chenhang, and Qingcaosha reservoirs is unsuitable for water intake during these months, particularly in extremely dry years. In 2020, the total number of consecutive days with unsuitable water intake from the four reservoirs was 28.75, 24.99, 29.63, and 37.47 days, respectively, and is predicted to rise to 46.53, 44.18, 47.56, and 50.75 days, respectively, in 2035. The impoundment of basin reservoirs in late summer and early autumn during average- and extremely dry hydrological years exposes them to strong northerly winds which can significantly decrease water intake. Basin reservoirs should reduce storage capacity and release water during extremely dry years to ensure the safety of freshwater resources in the Yangtze River Estuary.
To clarify the effects of global warming on dark carbon fixation (DCF) in eutrophic estuaries, the rates of total DCF and DCF driven by ammonia-oxidizing microorganisms (DCFAOB) were studied under various water temperatures and nitrogen concentrations using 14C labeling (NaH14CO3) and the allylthiourea (ATU) inhibitor method. The Yangtze River Estuary was used as a study area and sampling locations were set up in the estuary and offshore locations. The DCF rates in the Yangtze River Estuary ranged from 0.23 to 0.33 μmolC·L–1·d–1 and that DCFAOB rates accounted for 4.13% to 43.61% of the DCF. Although DCF rates increase significantly under optimum temperatures, the increase was more obvious with changes in ambient temperature under low salinity. The optimum temperatures for DCF in areas of low and high salinity were found to be 30℃ and 25℃, respectively, with the addition of ammonia-nitrogen at these conditions significantly increasing the DCF rates. The results of this study reveal how dark carbon fixation in estuarine water can change when subjected to environmental temperature changes, thereby providing theoretical support and data references to aid in the comprehensive understanding and scientific assessment of carbon fixation and carbon sink flux in estuarine ecosystems.
Coastal salt marsh wetlands have high productivity and low decomposition rates owing to long-term flooding, and these wetlands store a large amount of soil organic carbon. As newly restored salt marsh wetlands develop, changes in vegetation growth traits, soil physicochemical properties, and organic carbon content affect their carbon sequestration function. In this study, using a restored salt marsh wetland in Hengsha (Chongming, Shanghai) as an example, changes in the vegetation growth characteristics and soil organic carbon content of different vegetation communities at varying developmental ages were analyzed using the spatiotemporal substitution method. Key factors affecting the carbon sequestration capacity of these restored wetlands were also identified. The results showed that the organic carbon content in newly restored salt marsh wetlands increased with developmental age over 0 ~ 20 years. Soil porosity and water content were effective indicators of soil organic carbon content changes. The newly restored wetlands had a high soil carbon density, with a total organic carbon density of (21.49 ± 3.67) tC·hm–2 in the 0 ~ 20 cm soil layer of the eight-year-old wetland, similar to that of the natural wetland. The vegetation growth and carbon sequestration capacity of Phragmites australis were higher than those of Scirpus mariqueter and their ecotone.
We explored nutrient distribution in water and heavy metal contamination in sediments after rice harvest in a rice-shrimp co-cropping system. Additionally, we assessed aquatic ecological risks by evaluating molecular ammonia toxicity and heavy metal levels in rice-shrimp fields and systematically analyzed the ecotoxicity of nutrients and heavy metals in water in the co-cropping system by monitoring physicochemical indices in water during the late cultivation period in four rice and shrimp co-cultivation fields. After rice harvesting, the water showed high pH (9.25) and the total nitrogen concentration, ammonia nitrogen, and COD reached 14.15, 11.49, and 92.01 mg/L, respectively. In perennial rice-shrimp co-cropping systems, elevated levels of ωAs (16.21 mg·kg–1) and ωCd (0.20 mg·kg–1) were found in sediments, exceeding natural baseline levels by 2.35 and 1.72 fold, respectively. Levels of other heavy metals were lower, in addition, the concentration of heavy metal was lower than the baseline levels of the sediments. The potential ecological risk index and our potential biological toxicity evaluation revealed low ecological risks posed by heavy metals in rice-shrimp co-cropping system sediments, which can be attributed to mineral elements required for Procambarus clarkii culture. In conclusion, co-cultivating rice with shrimp can potentially mitigate soil heavy metal pollution.
This study investigated the heavy metal distribution characteristics, assess the pollution status, and identify potential pollution sources. A total of 514 topsoil samples were collected in the public area of the industrial park, and 11 element concentrations were tested. The concentration distribution of heavy metals was characterized on the plane using Geographic Information Systems (GIS). Our research involved the application of various analytical methods, including single factor index analysis, potential ecological risk index assessment, and principal component analysis-absolute principal component scores-multiple linear regression (PCA-APCS-MLR). The results revealed that all 10 heavy metals, except for Cr (Ⅵ) which was below the detection limit, were detected in concentrations surpassing the background values. The regional proportion were Cu (86%) > Cd (71%) > Co (53%) > Ni (50%) > Be (45%) > As (42%) > Sb (40%) > Pb (23%) > V (16%) > Hg (4%), and the concentrations of all major elements were relatively high. Moreover, there were areas with extremely strong (Cd element proportion was 1.7%, Sb element proportion was 1.5%) and very strong (Cd element proportion is 1.0%, Sb element proportion is 0.2%) ecological risk levels. They were all located near large chemical enterprises on the northwest side of the park. The composite ecological risk index of heavy metals in surface soil belonged to moderate ecological hazards, and there was a certain degree of ecological hazard risk. The main heavy metal pollution sources in the surface soil of the study area included chemical and combustion sources, natural sources, and transportation sources, accounting for 27.2%, 17.0%, and 11.0% of the pollution load, respectively.
The impact of rapid development of coastal aquaculture on aquatic environments is an important topic in environmental science. Quantitative assessment of the impact of aquaculture on sediment heavy metal pollution has been challenging because of the complex conservative-nonconservative behavior of heavy metals in coastal brackish waters. In this study, Sansha Bay, Fujian Province, the world’s largest yellow croaker cage culture area, was used as a research area for offshore aquaculture. Using aquaculture data recorded by remote sensing images combined with the relationships between sedimentary heavy metals and salinity, this study sought to analyze the effects of aquaculture on sediment heavy metal pollution. The results showed that over the past 15 years, the area of cage culture in Sansha bay has increased from 9.1 km2 to 33.4 km2, and the maximum intensity of cage culture per square kilometer has increased from 3% to 22%. As a result, the average values of Cu, Zn, Cd, and Pb levels in the cuprophilic elements in the culture area increased by 44%, 11%, 15%, and 17%, respectively, compared to non-farmed areas, and the slope of the conservative regression line with an increase in salinity decreased by 27%, 35%, 18%, and 2%, respectively. The average values of the siderophile elements Cr, Mn, and Ni in the breeding area increased by 16%, 15%, and 29%, respectively, compared to those in non-farmed areas. The results of potential ecological risk evaluation showed that Cd is a potential environmental pollutant in the surface sediments of Sansha Bay, and Sansha Bay as a whole is at a medium ecological risk level.
To characterize the effects of stochastic environment and major mutation factors on populations, we consider a class facultative population system based on Markov chains and pure-jump stable processes. First of all, the existence and uniqueness of a global positive solution of the proposed model is discussed. Then, sufficient conditions for ergodicity are specified. Finally, conditions for positive recurrence of the model are presented.
An ${\rm{E}} $ -total coloring of a graph $G $ is an assignment of several colors to all vertices and edges of $G $ such that no two adjacent vertices receive the same color and no edge receive the same color as one of its endpoints. If $f $ is an ${\rm{E}} $ -total coloring of a graph $G $, the multiple color set of a vertex $x $ of $G $ under $f $ is the multiple set composed of colors of $x $ and the edges incident with $x $. If any two distinct vertices of $G $ have distinct multiple color sets under an ${\rm{E}} $ -total coloring $f $ of a graph $G $, then $f $ is called an ${\rm{E}} $ -total coloring of $G $ vertex-distinguished by multiple sets. An ${\rm{E}} $ -total chromatic number of $G $ vertex-distinguished by multiple sets is the minimum number of the colors required in an ${\rm{E}} $ -total coloring of $G $ vertex-distinguished by multiple sets. The ${\rm{E}} $ -total colorings of cycles and paths vertex-distinguished by multiple sets are discussed by use of the method of contradiction and the construction of concrete coloring. The optimal${\rm{E}} $ -total colorings of cycles and paths vertex-distinguished by multiple sets are given and the ${\rm{E}} $ -total chromatic numbers of cycles and paths vertex-distinguished by multiple sets are determined in this paper.
Tridiagonal sign pattern matrices and paw form sign pattern matrices were analyzed with respect to their potential for ensuring algebraic positivity. The necessary conditions allowing algebraic positivity of the two classes of sign pattern matrices were given using combinatorial matrix theory and graph theory. Finally, the equivalent conditions that would ensure algebraic positivity of tridiagonal sign pattern matrices and paw form sign pattern matrices of order $n $ were determined.
An involution ring is called a *r-clean ring if every element is the sum of a projection and a *-regular element. Some extensions of *r-clean rings are discussed, and a characterization of the element in a *-abelian *r-clean ring is given.
In this paper, some sufficient conditions for forced oscillation of impulsive multi-delay fractional partial differential equation solutions with damping term are established by using the method of differential inequalities under Robin and Dirichlet boundary conditions, an example is given to verify the validity of the main results.
With the popularization of university information system applications and the increase in their usage frequency, teachers and students have higher requirements for data consistency, accuracy, timeliness, and completeness. The original data synchronization scheme using extensible markup language (XML) for data synchronization has the disadvantages of low synchronization efficiency and difficulty of expansion. The open-source tool, DataX, can complete data synchronization between various heterogeneous databases without damaging the source database. This study used DataX to improve the original data synchronization scheme and proposed different data synchronization schemes for various business requirements and application scenarios in the foundation of university postgraduate information system construction. At the same time, in view of the shortcomings of DataX in which only one read can do one write during the start-up and execution, the method where one read can do multiple writes was designed. The comparison experiment shows that the optimized scheme can improve data synchronization efficiency, has better scalability, and can meet the data synchronization requirements of universities.
Review-based recommendations are mainly based on the exploitation of textual information that reflects the characteristics of items and user preferences. However, most existing approaches overlook the influence of information from hidden strangers on the selection of reviews for the target user. However, information from strangers can more accurately measure the relative feelings of the user and provide a complement to the target user’s expression, leading to more refined user modeling. Recently, several studies have attempted to incorporate similar information from strangers but ignore the use of information regarding other strangers. In this study, we proposed a stranger collaborative review-based recommendation model to make effective use of information from strangers by improving accurate modeling and enriching user modeling. Specifically, for capturing potential user preferences elaborately, we first designed a collaborative stranger attention module considering the textual similarities and preference interactions between the target user and the hidden strangers implied by the reviews. We then developed a collaborative gating module to dynamically integrate information from strangers at the preference level based on the characteristics of the target user-item pair, effectively filtering preferences of strangers and enriching target user modeling. Finally, we applied a latent factor model to accomplish the recommendation task. Experimental results have demonstrated the superiority of our model compared to state-of-the-art methods on real-world datasets from various sources.
This study explores the multimodal understanding and reasoning for one-stage visual grounding. Existing one-stage methods extract visual feature maps and textual features separately, and then, multimodal reasoning is performed to predict the bounding box of the referred object. These methods suffer from the following two weaknesses: Firstly, the pre-trained visual feature extractors introduce text-unrelated visual signals into the visual features that hinder multimodal interaction. Secondly, the reasoning process followed in these two methods lacks visual guidance for language modeling. It is clear from these shortcomings that the reasoning ability of existing one-stage methods is limited. We propose a low-level interaction to extract text-related visual feature maps, and a high-level interaction to incorporate visual features in guiding the language modeling and further performing multistep reasoning on visual features. Based on the proposed interactions, we present a novel network architecture called the dual-path multilevel interaction network (DPMIN). Furthermore, experiments on five commonly used visual grounding datasets are conducted. The results demonstrate the superior performance of the proposed method and its real-time applicability.
The demands of deep neural network models for computation and storage make them unsuitable for deployment on embedded devices with limited area and power. To solve this issue, stochastic computing reduces the storage and computational complexity of neural networks by representing data as a stochastic sequence, followed by arithmetic operations such as addition and multiplication through basic logic operation units. However, short stochastic sequences may cause discretization errors when converting network weights from floating point numbers to the stochastic sequence, which can reduce the inference accuracy of stochastic computing network models. Longer stochastic sequences can improve the representation range of stochastic sequences and alleviate this problem, but they also result in longer computational latency and higher energy consumption. We propose a design for a differentiable quantization function based on the Fourier transform. The function improves the matching of the model to stochastic sequences during the network’s training process, reducing the discretization error during data conversion. This ensures the accuracy of stochastic computational neural networks with short stochastic sequences. Additionally, we present an adder designed to enhance the accuracy of the operation unit and parallelize computations by chunking inputs, thereby reducing latency. Experimental results demonstrate a 20% improvement in model inference accuracy compared to other methods, as well as a 50% reduction in computational latency.
The surface structure of a container lock pin is complex, making it difficult to establish a point cloud model with a high surface feature integrity. Therefore, a multi-view and multi-attitude point cloud model reconstruction algorithm based on a turntable was proposed to restore the complete surface features of the locking pin. Considering that sensors at a fixed height are paired with rotating turntables in most scenarios, the collected surface features are usually somewhat missing. Initially, the algorithm uses the parameter calibration results of the turntable to realize the multi-view three-dimensional point cloud stitching, and establishes a fixed attitude point cloud model. Then, through the proposed improved spherical projection algorithm, the positioning of the locking pin on the turntable is selected to establish a point cloud model under another posture. Finally, the point cloud model with multiple attitudes is integrated to improve its surface characteristics. Experimental results show that the proposed algorithm can build a lock-pin point cloud model with high surface feature integrity.
Infrared small-target detection has always been an important technology in infrared tracking systems. The current infrared approaches for small-target detection in complex backgrounds are prone to generating false alarms and exhibit sluggish detection speeds from the perspective of the human visual system. Using the multiscale local contrast measure using a local energy factor (MLCM-LEF) method, an infrared small-target detection method based on a double-layer local energy factor is proposed. The target detection was performed from the perspectives of the local energy difference and local brightness difference. The double-layer local energy factor was used to describe the difference between the small target and the background from the energy perspective, and the weighted luminance difference factor was used to detect the target from the brightness angle. The infrared small target was extracted by a two-dimensional Gaussian fusion of the processing results of the two approaches. Finally, the image mean and standard deviation were used for adaptive threshold segmentation to extract the small infrared target. In experimental tests on public datasets, this method improved the performance in suppressing background compared with the MLCM-LEF algorithm, DLEF (double-layer local energy factor) reduced the detection of a single frame time by one-third.
Three-dimensional point cloud semantic segmentation is an essential task for 3D visual perception and has been widely used in autonomous driving, augmented reality, and robotics. However, most methods work under a fully-supervised setting, which heavily relies on fully annotated datasets. Many weakly-supervised methods have utilized the pseudo-labeling method to retrain the model and reduce the labeling time consumption. However, the previous methods have failed to address the conformation bias induced by false pseudo labels. In this study, we proposed a novel weakly-supervised 3D point cloud semantic segmentation method based on group contrastive learning, constructing contrast between positive and negative sample groups selected from pseudo labels. The pseudo labels will compete with each other within the group contrastive learning, reducing the gradient contribution of falsely predicted pseudo labels. Results on three large-scale datasets show that our method outperforms state-of-the-art weakly-supervised methods with minimal labeling annotations and even surpasses the performance of some classic fully-supervised methods.
The remarkable achievements of deep learning in computer vision have led to significant development in example-based texture synthesis. The texture synthesis model using neural networks mainly includes local components, such as convolution and up/down sampling, which is unsuitable for capturing irregular structural attributes in non-stationary textures. Inspired by the frequency and space domain duality, a non-stationary texture synthesis method based on hidden layer Fourier convolution is proposed in this study. The proposed method uses the generative adversarial network as the basic architecture, performs feature splitting along the channel in the hidden layer, and builds a local branch in the image domain and a global branch in the frequency domain to consider visual perception and structural information. Experimental results show that this method can handle structurally challenging non-stationary texture exemplars. Compared with state-of-the-art methods, the method yielded better results in the learning and expansion of large-scale structures.
The image caption generation algorithm based on decoupling commonsense association aims to eliminate the interference of commonsense association between various types of entities on the model reasoning, and improve the fluency and accuracy of the generated description. Aiming at the relationship sentences in the current image description that conform to common sense but do not conform to the image content, the algorithm first uses a novel training method to improve the attention of the relationship detection model to the real relationship in the image and improve the accuracy of relationship reasoning. Then, a relation-aware entity interaction method was used to carry out targeted information interaction for entities with relationships, and the relationship information was strengthened. The experimental results show that the proposed algorithm can correct some commonsense false relationships, generate more accurate image captions, and obtain better experimental results on various evaluation indicators.
This paper presents a method for skinning in character animation, utilizing implicit surfaces, which is designed to deform animated models with skeleton and associated skinning weights．This method reconstructs the mesh around a given skeleton with the Hermite radial basis function and Poisson-disk sampling on surfaces．This process transforms the character’s volume into a set of localized 3D scalar fields and preserves the original mesh properties．Field functions are then constructed and employed to refine the results obtained from the geometric skinning technique．The implicit method, combined with two types of combination operators, generates realistic skin deformations around the human skeleton model finally．The method does not cause candy twist and joint swelling problems, and can handle skin collision and muscle protrusions．Due to its post-processing feature, this method is very suitable for animation generation in standard production pipeline．
中国综合性科技类核心期刊(北大核心)
