Joint Rain Streaks & Haze Removal Network for Object Detection

In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant challenge.The emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior knowledge.However,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational efficiency.In response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature maps.Our methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map information.During the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.

Red Tide Frequency Analysis Using the Extreme Value Theory

In recent years, the red tide erupted frequently, and caused a great economic loss. At present, most literatures emphasize the academic research on the growth mechanism of red tide alga. In order to find out the characters of red tide in detail and improve the precision of forecast, this paper gives some new approaches to dealing with the red tide. By the extreme values, we deal with the red tide frequency analysis and get the estimation of T-times red tide level U (T), which is the level once the consistence of red tide alga exceeds on the average in a period of T times.

Density estimation-based method to determine sample size for random sample partition of big data

Random sample partition(RSP)is a newly developed big data representation and management model to deal with big data approximate computation problems.Academic research and practical applications have confirmed that RSP is an efficient solution for big data processing and analysis.However,a challenge for implementing RSP is determining an appropriate sample size for RSP data blocks.While a large sample size increases the burden of big data computation,a small size will lead to insufficient distribution information for RSP data blocks.To address this problem,this paper presents a novel density estimation-based method(DEM)to determine the optimal sample size for RSP data blocks.First,a theoretical sample size is calculated based on the multivariate Dvoretzky-Kiefer-Wolfowitz(DKW)inequality by using the fixed-point iteration(FPI)method.Second,a practical sample size is determined by minimizing the validation error of a kernel density estimator(KDE)constructed on RSP data blocks for an increasing sample size.Finally,a series of persuasive experiments are conducted to validate the feasibility,rationality,and effectiveness of DEM.Experimental results show that(1)the iteration function of the FPI method is convergent for calculating the theoretical sample size from the multivariate DKW inequality;(2)the KDE constructed on RSP data blocks with sample size determined by DEM can yield a good approximation of the probability density function(p.d.f);and(3)DEM provides more accurate sample sizes than the existing sample size determination methods from the perspective of p.d.f.estimation.This demonstrates that DEM is a viable approach to deal with the sample size determination problem for big data RSP implementation.

A grid-based clustering algorithm for wild bird distribution

Advanced satellite tracking technologies provide biologists with long-term location sequence data to understand movement of wild birds then to find explicit correlation between dynamics of migratory birds and the spread of avian influenza. In this paper, we propose a hierarchical clustering algorithm based on a recursive grid partition and kernel density estimation （KDE） to hierarchically identify wild bird habitats with different densities. We hierarchically cluster the GPS data by taking into account the following observations： 1） the habitat variation on a variety of geospatial scales; 2） the spatial variation of the activity patterns of birds in different stages of the migration cycle. In addition, we measure the site fidelity of wild birds based on clustering. To assess effectiveness, we have evaluated our system using a large-scale GPS dataset collected from 59 birds over three years. As a result, our approach can identify the hierarchical habitats and distribution of wild birds more efficiently than several commonly used algorithms such as DBSCAN and DENCLUE.