Search Results (6)

With the development of the intelligent vision industry, ship detection and identification technology has gradually become a research hotspot in the field of marine insurance and port logistics. However, due to the interference of rain, haze, waves, light, and other bad weather, the robustness and effectiveness of existing detection algorithms remain a continuous challenge. For this reason, an improved YOLOv8n algorithm is proposed for the detection of ship targets under unforeseen environmental conditions. In the proposed method, the efficient multi-scale attention module (C2f_EMAM) is introduced to integrate the context information of different scales so that the convolutional neural network can generate better pixel-level attention to high-level feature maps. In addition, a fully-concatenate bi-directional feature pyramid network (Concatenate_FBiFPN) is adopted to replace the simple superposition/addition of feature map, which can better solve the problem of feature propagation and information flow in target detection. An improved spatial pyramid pooling fast structure (SPPF2+1) is also designed to emphasize low-level pooling features and reduce the pooling depth to accommodate the information characteristics of the ship. A comparison experiment was conducted between other mainstream methods and our proposed algorithm. Results showed that our proposed algorithm outperformed other models by achieving 99.4% of accuracy, 98.2% of precision, 98.5% of recall, 99.1% of mAP@.5, and 85.4% of mAP@.5:.95 on the SeaShips dataset. Full article

This study aimed to analyze the trend in land surface temperature (LST) over time using the entire archive of the available cloud-free Landsat images from 1986 to 2022 for Jordan and its nine local climate zones (LCZs). Two primary datasets were used (i) Landsat-5; -8 imagery, and (ii) map of LCZs of Jordan. All LST images were clipped, preprocessed, and checked for cloud contamination and bad pixels using the quality control bands. Then, time-series of monthly LST images were generated through compositing and mosaicking processes using cloud computing functions and Java scripts in Google Earth Engine (GEE). The Mann–Kendall (MK) test and Sen’s slope estimator (SSE) were used to detect and quantify the magnitude of LST trends. Results showed a warming trend in the maximum LST values for all LCZs while there was annual fluctuation in the trend line of the minimum LST values in the nine zones. The monthly average LST values showed a consistent upward trajectory, indicating a warming condition, but with variations in the magnitude. The annual rate of change in LST for the LCZs showed that the three Saharan zones are experiencing the highest rate of increase at 0.0184 K/year for Saharan Mediterranean Warm (SMW), 0.0185 K/year for Saharan Mediterranean Cool (SMC), and 0.0169 K/year for Saharan Mediterranean very Warm (SMvW), indicating rapid warming in these regions. The three arid zones came in the middle, with values of 0.0156 K/year for Arid Mediterranean Warm (AMW), 0.0151 for Arid Mediterranean very Warm (AMvW), and 0.0139 for Arid Mediterranean Cool (AMC), suggesting a slower warming trend. The two semi-arid zones and the sub-humid zone showed lower values at 0.0138, 0.0127, and 0.0117 K/year for the Semi-arid Mediterranean Cool (SaMC), Semi-arid Mediterranean Warm (SaMW) zones, and Semi-humid Mediterranean (ShM) zones, respectively, suggesting the lowest rate of change compared to other zones. These findings would provide an overall understanding of LST change and its impact in Jordan’s LCZs for sustainable development and water resources demand and management. Full article

Earth Observation satellite imaging helps building diagnosis during a disaster. Several models are put forward on the xBD dataset, which can be divided into two levels: the building level and the pixel level. Models from two levels evolve into several versions that will be reviewed in this paper. There are four key challenges hindering researchers from moving forward on this task, and this paper tries to give technical solutions. First, metrics on different levels could not be compared directly. We put forward a fairer metric and give a method to convert between metrics of two levels. Secondly, drone images may be another important source, but drone data may have only a post-disaster image. This paper shows and compares methods of directly detecting and generating. Thirdly, the class imbalance is a typical feature of the xBD dataset and leads to a bad F1 score for minor damage and major damage. This paper provides four specific data resampling strategies, which are Main-Label Over-Sampling (MLOS), Discrimination After Cropping (DAC), Dilation of Area with Minority (DAM) and Synthetic Minority Over-Sampling Technique (SMOTE), as well as cost-sensitive re-weighting schemes. Fourthly, faster prediction meets the need for a real-time situation. This paper recommends three specific methods, feature-map subtraction, parameter sharing, and knowledge distillation. Finally, we developed our AI-driven Damage Diagnose Platform (ADDP). This paper introduces the structure of ADDP and technical details. Customized settings, interface preview, and upload and download satellite images are major services our platform provides. Full article

The evaluation of disparity (range) maps includes the selection of an objective image quality (or error) measure. Among existing measures, the percentage of bad matched pixels is commonly used. However, it requires a disparity error tolerance and ignores the relationship between range and disparity. In this research, twelve error measures are characterized in order to provide the bases to select accurate stereo algorithms during the evaluation process. Adaptations of objective quality measures for disparity maps’ accuracy evaluation are proposed. The adapted objective measures operate in a manner similar to the original objective measures, but allow special handling of missing data. Additionally, the adapted objective measures are sensitive to errors in range and surface structure, which cannot be measured using the bad matched pixels. Their utility was demonstrated by evaluating a set of 50 stereo disparity algorithms known in the literature. Consistency evaluation of the proposed measures was performed using the two conceptually different stereo algorithm evaluation methodologies—ordinary ranking and partition and grouping of the algorithms with comparable accuracy. The evaluation results showed that partition and grouping make a fair judgment about disparity algorithms’ accuracy. Full article

A machine learning approach was developed to improve the bad pixel maps that mask damaged or unusable pixels in the imaging spectrometers of National Aeronautics and Space Administration (NASA) Orbiting Carbon Observatory-2 (OCO-2) and Orbiting Carbon Observatory-3 (OCO-3). The OCO-2 and OCO-3 instruments use nearly 500,000 pixels to record high resolution spectra in three infrared wavelength ranges. These spectra are analyzed to retrieve estimates of the column-average carbon dioxide (XCO${}_2$) concentration in Earth’s atmosphere. To meet mission requirements, these XCO${}_2$ estimates must have accuracies exceeding 0.25%, and small uncertainties in the bias or gain of even one detector pixel can add significant error to the retrieved XCO${}_2$ estimates. Thus, anomalous pixels are identified and removed from the data stream by applying a bad pixel map prior to further processing. To develop these maps, we first characterize each pixel’s behavior through a collection of interpretable and statistically well-defined metrics. These features and a prior map are then used as inputs in a Random Forest classifier to assign a likelihood that a given pixel is bad. Consequently, the likelihoods are analyzed and thresholds are chosen to produce a new bad pixel map. The machine learning approach adopted here has improved data quality by identifying hundreds of new bad pixels in each detector. Such an approach can be generalized to other instruments that require independent calibration of many individual elements. Full article

Albedo is a key variable in the response of glaciers to climate. In Iceland, large albedo variations of the ice caps may be caused by the deposition of volcanic ash (tephra). Sparse in situ measurements are insufficient to characterize the spatial variation of albedo over the ice caps due to their large size. Here we evaluated the latest MCD43 MODIS albedo product (collection 6) to monitor albedo changes over the Icelandic ice caps using albedo measurements from ten automatic weather stations on Vatnajökull and Langjökull. Furthermore, we examined the influence of the albedo variability within MODIS pixels by comparing the results with a collection of Landsat scenes. The results indicate a good ability of the MODIS product to characterize the seasonal and interannual albedo changes with correlation coefficients ranging from 0.47 to 0.90 (median 0.84) and small biases ranging from −0.07 to 0.09. The root-mean square errors (RMSE) ranging from 0.08 to 0.21, are larger than that from previous studies, but we did not discard the retrievals flagged as bad quality to maximize the amount of observations given the frequent cloud obstruction in Iceland. We found a positive but non-significant relationship between the RMSE and the subpixel variability as indicated by the standard deviation of the Landsat albedo within a MODIS pixel (R = 0.48). The summer albedo maps and time series computed from the MODIS product show that the albedo decreased significantly after the 2010 Eyjafjallajökull and 2011 Grímsvötn eruptions on all the main ice caps except the northernmost Drangajökull. A strong reduction of the summer albedo by up to 0.6 is observed over large regions of the accumulation areas. These data can be assimilated in an energy and mass balance model to better understand the relative influence of the volcanic and climate forcing to the ongoing mass losses of Icelandic ice caps. Full article