Medical image segmentation is a crucial step toward automatic clinical diagnosis, which has received growing interest. Although some existing methods based on convolutional neural networks or transformers have achieved remarkable success in this task, they still show limitations in effectively modeling the relationships among different objects in images. In this paper, we propose a novel deep learning based model to address this issue by leveraging a vision graph neural network (ViG). Our model, MedSegViG, mainly consists of a hierarchical ViG encoder and a lightweight convolutional decoder. The hierarchical encoder extracts multi-level features from the image and captures the object relationships with graph neural networks. The lightweight decoder then fuses these features and generates the corresponding segmentation map. Extensive experiments are conducted on seven datasets for three typical medical image segmentation tasks: polyp segmentation, skin lesion segmentation, and retinal vessel segmentation. The results demonstrate the superiority of our MedSegViG over state-of-the-art models across various tasks and datasets. The code is released on https://github.com/Xinhong-Li/MedSegViG.

Target detection is a critical task in interpreting hyperspectral remote sensing images. Small target (such as airplanes) detection is challenging, especially in large-scale complex scenes with high spectral variability of different land cover types. In this paper, we propose a transfer learning-based, large-scale, robust hyperspectral target detector (TLH2TD) to improve the accuracy of hyperspectral target detection (HTD) in large-scale complex scenes. TLH2TD learns the spatial features of hyperspectral targets from high-resolution remote sensing images and achieves high-precision HTD with fused spatial-spectral features. It comprises three parts: (1) The coupled target-background sample expansion (CTBSE) module is designed to expand the labeled hyperspectral target and background samples with sufficient high-resolution, labeled RGB images and a few labeled hyperspectral samples. (2) The hard positive and negative example mining (HPNEM) module trains the hard positive and negative samples to enhance the discriminative ability of the network, addressing the problem of inadequate sample training in large-scale hyperspectral images (HSIs). (3) The spatial-spectral weighted subspace (SSWS) module is designed to fuse the spatial features extracted from the target detection network and the spectral features based on the Mahalanobis distance. The results show that: (1) The TLH2TD achieves average area under the curve (AUC) values of 0.96, 0.96, and 0.93 on small-sized, medium-sized, and large-sized HSIs, respectively, achieving the highest accuracy compared with other HTD algorithms. (2) The TLH2TD exhibits the highest detection time efficiency for medium-sized and large-sized HSIs. (3) For large-sized HSIs, when most HTD algorithms fail, TLH2TD exhibits significantly higher accuracy and time efficiency than other methods. This is an important achievement to meet the robust target detection tasks of large-scale hyperspectral remote sensing images.

Dichotomous image segmentation (DIS) has a wide range of real-world applications and gained increasing research attention in recent years. In this paper, we propose to tackle DIS with informative frequency priors. Our model, called FP-DIS, stems from the fact that prior knowledge in the frequency domain can provide valuable cues to identify fine-grained object boundaries. Specifically, we propose a frequency prior generator to jointly utilize a fixed filter and learnable filters to extract informative frequency priors. Before embedding the frequency priors into the network, we first harmonize the multi-scale side-out features to reduce their heterogeneity. This is achieved by our feature harmonization module, which is based on a gating mechanism to harmonize the grouped features. Finally, we propose a frequency prior embedding module to embed the frequency priors into multi-scale features through an adaptive modulation strategy. Extensive experiments on the benchmark dataset, DIS5K, demonstrate that our FP-DIS outperforms state-of-the-art methods by a large margin in terms of key evaluation metrics.

A framework based on color feature extraction of social media photos and correlation analysis with air quality parameters is proposed to monitor environmental change. More specifically, photos of the Beijing Olympic Park from Panoramio website have been analyzed as a case study. The aerosol optical depth data at 500 nm wavelength (AOD 500) obtained from sun-photometer observation network station has been used as reference. Results show a proof of concept that social media photos have an interesting potential for air pollution estimate and remote sensing parameter validation with a low cost.

This paper proposes a method on detecting specific type of collapsed built-up structures using only post-event images. Its essence lies in fusing morphological texture and spectral information through a nonlinear function to characterize debris of collapsed built-up structures. Experiments are carried out on an image after the 2010 Yushu earthquake. Results show that the method can well extract collapsed brick built-up structures and it has an advantage of handling complex scenes in urban areas compared to state-of-the-art methods.

The Three Gorges Reservoir is the largest water resource project in west China. With water environment change greatly, water quality of the Three Gorges Reservoir needs monitoring urgently. With the properties of high spatial resolution, multi-angle observation and hyperspectral imagery, CHRIS offers a precious data resource for monitoring water quality. We apply CHRIS imagery to detect total suspended substance concentration of the Three Gorges. The method is simplified bio-optic model. The results showed the distribution total suspended substance concentration in the Three Gorges at 17thApril of 2007, which agree with the actual situation. The total suspended substance concentrations retrieved by the near-infrared method are quite close to the measured data. This study could be helpful to monitor water quality with hyperspectral remote sensing imagery just having near-infrared channels.

When calculating water leaving radiance or remote sensing reflectance from water surface measured spectra, the results are affected by the reflected skylight, which are the product of skylight radiance and the air-water surface reflectance of skylight. The skylight radiance can be measured over water surface by spectrometer. But the air-water surface reflectance is affected by multi factors, and is hard to be determined. Presently, there are some methods to estimate the value of air-water surface reflectance of skylight over ocean waters. However, when calculating the air-water surface reflectance of skylight over turbid inland waters, these methods all have some problems. In this paper, we develop an improved method to calculate air-water surface reflectance of skylight over turbid inland waters. This method is based on the spectral characteristics of turbid inland waters that water leaving radiance in shortwave infrared wavelength region can be assumed zero, which is verified by the data acquired in Taihu Lake on April 25 to 27, 2007. In this method, two atmospheric windows (1190 ~ 1330 nm and 1500 ~ 1700 nm) in shortwave infrared wavelength region are used. The main strategy of this method is to use the data in 1190 ~ 1330 nm wavelength region to calculate air-water surface reflectance of skylight first. When no reasonable result is obtained, the data in 1500 ~ 1700 nm wavelength region is used. With this method, the air-water surface reflectances of skylight on the 31 sampling stations are calculated. Then, water leaving radiance and remote sensing reflectance are calculated. The results of air-water surface reflectance of skylight and remote sensing reflectance on the 31 sampling stations are reasonable. Then, the advantages and limitations of the improved method are analyzed.

In late June 2008, Enteromorpha prolifera (E.P) bloomed in Qingdao marine, including Qingdao Olympic Sailing Center. The large scale and the fast extending speed of the E.P bloom were rare in history. The E.P bloomed just before Beijing 2008 Olympics, so it attracted the most attention around the world. Monitoring E.P from remote sensing data has the advantages of rapidness, wide coverage, low cost. But commonly used optical remote sensing is easily affected by cloud, which limits the monitoring timelines. In this paper, the theory of E.P monitoring from optical remote sensing and SAR remote sensing were analyzed. Then, the technical routes of E.P monitoring by exploiting the synergy of active and passive remote sensing data were presented. Because the SAR images are not affected by cloud, the timelines can be increased exploiting the by synergy of active and passive remote sensing data. MODIS and RADARSAT were used to monitor E.P. The monitoring results were used to analyze the beginning and spread of E.P. The monitoring results from MODIS and RADARSAT were compared.

This paper creates an operational swift solution for automatic analyzing water quality in case II waters. The HJ-1 satellites of China was successfully launched, this provides a good opportunity for case II water (inland and coastal water) environment monitoring. However, there is no operational monitoring system in China and abroad. The traditional processing methods were developed for expert users, which including many complex operations and user interaction, not suitable for business operation. To overcome this problem, an automatic monitoring procedure was developed by us. With this approach, one can get monitoring reports from original HJ-1 satellites images or MODIS images with ¿one-click¿. That means, you do not have to concern the complex data processing procedure, and what you need to do is specify the water quality monitoring area, the specific space-borne sensor and the remote sensing images. According to the study area, sensor type and image file, the operational procedure will automatically get parameters from the integrated XML files and database indexed by area and sensor type. The processing procedure does not need any user intervention, which greatly improve the processing efficiency. This paper gives a complete flow chart of data processing in the automatic monitoring mode using XML files and databases. Moreover, in order to verify the ability of the operational monitoring approach, experiments were conducted in Tai'hu, Chao'hu, and Dian'chi lakes using MODIS QKM images and the HJ-1 multi-spectral images. Tests show both the efficiency and accuracy of this approach is relatively high.

The aerosol optical depth (AOD) measured by sun photometer is obtained after subtracting the Rayleigh optical depth, ozone optical depth and other absorption gas optical depth from total optical depth. Wherein, it was according to Beer's attenuation law. However, the band filter function of sun photometers should be considered when retrieving AODs. In this paper, it was systemically analyzed the influence of sun photometer filter function on retrieving aerosol optical depth. Numerous study showed that the band filter function has a significant impact on retrieving AODs: 1)The uncertainty of AODs may become large when the filter function is not well desgined; 2) Under large zenith observation condition, it may introduce non-neglected errors if Rayleigh scattering optical depth is calculated directly at central wavelength without filter function considered; 3) The band weighted absorption coefficients of O3and NO2almost hold constant when gas amounts increase, except for questionable designed band filter; 4) These weak absorption optical depths can not be ignored such as H2O absorption optical depths in 1020nm &1640nm band and CH4, CO2absorption optical depths in 1640nm band.