Localization of Thermal Wellbore Defects Using Machine Learning

Defect detection and localization are key to preventing environmentally damaging wellbore leakages in both geothermal and oil/gas applications. In this work, a multi-step, machine learning approach is used to localize two types of thermal defects within a wellbore model. This approach includes a COMSOL heat transfer simulation to generate base data, a neural network to classify defect orientations, and a localization algorithm to synthesize sensor estimations into a predicted location. A small-scale physical wellbore test bed was created to verify the approach using experimental data. The classification and localization results were quantified using this experimental data. The classification predicted all experimental defect orientations correctly. The localization algorithm predicted the defect location with an average root mean square error of 1.49 in. The core contributions of this work are 1) the overall localization architecture, 2) the use of centroid-guided mean-shift clustering for localization, and 3) the experimental validation and quantification of performance.

APLICAÇÃO DE APRENDIZADO DE MÁQUINA COM DADOS DE SENSORIAMENTO REMOTO PARA O MAPEAMENTO DE FLORESTAS URBANAS

As florestas urbanas fornecem vários benefícios para as cidades, incluindo redução das temperaturas, melhorias na qualidade do ar, saúde e lazer da população e proteção de bacias hidrográficas, tornando assim um dos indicadores mais importantes da qualidade ambiental e sustentabilidade urbana. Campo Grande, no Mato Grosso do Sul, possui o título de "Tree Cities of the World", que reconhece as cidades mais comprometidas com a preservação das florestas urbanas e o desenvolvimento sustentável, portanto o mapeamento e monitoramento servem como ferramenta de auxílio para os governos e tomadores de decisão. O presente trabalho consistiu em combinar imagens de sensoriamento remoto de alta resolução e algoritmo de aprendizado de máquina (machine learning) para mapear florestas urbanas. O estudo foi realizado na Bacia hidrográfica do Prosa, Campo Grande, Mato Grosso do Sul, Brazil, considerando imagens do Google Earth de 14 de maio de 2020. Para fins de classificação, adotou-se o algoritmo Random Forest associado com segmentação prévia da imagem com a técnica mean shift. Como resultado, obteve-se um percentual de 18,31% de vegetação arbórea na bacia e a métrica F1 superior a 85%, possibilitando, assim, um mapeamento acurado e atualizado de florestas urbanas. PALAVRAS-CHAVE: árvores. random forest. classificação supervisionada. arcgis pro.

Visual Sequence Algorithm for Moving Object Tracking and Detection in Images

Objective. The effects of different algorithms on detecting and tracking moving objects in images based on computer vision technology are studied, and the best algorithm scheme is confirmed. Methods. An automatic moving target detection and tracking algorithm based on the improved frame difference method and mean-shift was proposed to test whether the improved algorithm has improved the detection and tracking effect of moving targets. The algorithm improves the traditional three-frame difference method and introduces a single Gaussian background model to participate in target detection. The improved frame difference method is used to detect the target, and the position window and center of the target are determined. Combined with the mean-shift algorithm, it is determined whether the template needs to be updated according to whether it exceeds the set threshold so that the algorithm can automatically track the moving target. Results. The position and size of the search window change as the target location and size change. The Bhattacharyya similarity measure ρ (y) exceeds the threshold r, and the target detection algorithm is successfully restarted. Conclusion. The algorithm for automatic detection and tracking of moving objects based on the improved frame difference method and mean-shift is fast and has high accuracy.

Virtual interaction algorithm of cultural heritage based on multi feature fusion

During the traditional cultural heritage virtual interaction algorithm in the interaction action recognition, the database is too single, resulting in low recognition accuracy, recognition time-consumer and other issues. Therefore, this paper introduces the multi feature fusion method to optimize the cultural heritage virtual interaction algorithm. Kinect bone tracking technology is applied to identify the movement of the tracking object, 20 joints of the human body are tracked, and interactive action recognition is realized according to the fingertip candidate points. In order to carry out the judgment virtual interactive operation of subsequent recognition actions, a multi feature fusion database is established. The mean shift is used to derive the moving mean of the target’s action position and to track the interactive object. The Euclidean distance formula is used to train samples of multi feature fusion database data to realize the judgment of recognition action and virtual interaction. In order to verify the feasibility of the research algorithm, the virtual interactive script of ink painting in a cultural heritage museum is used to simulate the research algorithm, and a comparative experiment is designed. The experimental results show that the proposed algorithm is superior to the traditional virtual interactive algorithm in recognition accuracy and efficiency, which proves the feasibility of this method.

Research on target tracking algorithm based on mean shift with adaptive bandwidth

The traditional mean shift algorithm used fixed kernels or symmetric kernel function, which will cause the target tracking lost or failure. The target tracking algorithm based on mean shift with adaptive bandwidth was proposed. Firstly, the signed distance constraint function was introduced to produce the anisotropic kernel function based on signed distance kernel function. This anisotropic kernel function satisfies that the value of the region function outside the target is zero, which provides accurate tracking window for the target tracking. Secondly, calculate the mean shift window center of anisotropic kernel function template, the theory basis is the sum of vector weights from the sample point in the tracking window to the center point is zero. Thirdly, anisotropic kernel function templates adaptive update implementation by similarity threshold to limit the change of the template between two sequential pictures, so as to realize real-time precise tracking. Finally, the contrast experimental results show that our algorithm has good accuracy and high real time.

Crown closure segmentation on wetland lowland forest using the mean shift algorithm

The availability of high and very high-resolution imagery is helpful for forest inventory, particularly to measure the stand variables such as canopy dimensions, canopy density, and crown closure. This paper describes the examination of mean shift (MS) algorithm on wetland lowland forest. The study objective was to find the optimal parameters for crown closure segmentation Pleiades-1B and SPOT-6 imageries. The study shows that the segmentation of crown closure with the red band of Pleiades-1B image would be well segmented by using the parameter combination of (hs: 6, hr: 5, M: 33) having overall accuracy of 88.93% and Kappa accuracy of 73.76%, while the red, green, blue (RGB) composite of SPOT-6 image, the optimal parameter combination was (hs:2, hr: 8, M: 11), having overall accuracy of 85.72% and kappa accuracy of 68.33%. The Pleiades-1B image with a spatial resolution of (0.5 m) provides better accuracy than SPOT-5 of (1.5 m) spatial resolution. The differences between single spectral, synthetic, and RGB does not significantly affect the accuracy of segmentation. The study concluded that the segmentation of high and very high-resolution images gives promising results on forest inventory.

Nanoscopic resolution within a single imaging frame

Mean-Shift Super Resolution (MSSR) is a principle based on the Mean Shift theory that improves the spatial resolution in fluorescence images beyond the diffraction limit. MSSR works on low- and high-density fluorophore images, is not limited by the architecture of the detector (EM-CCD, sCMOS, or photomultiplier-based laser scanning systems) and is applicable to single images as well as temporal series. The theoretical limit of spatial resolution, based on optimized real-world imaging conditions and analysis of temporal image series, has been measured to be 40 nm. Furthermore, MSSR has denoising capabilities that outperform other analytical super resolution image approaches. Altogether, MSSR is a powerful, flexible, and generic tool for multidimensional and live cell imaging applications.

Segmentation of Gastric Computerized Tomography Images under Intelligent Algorithms in Evaluation of Efficacy of Decitabine Combined with Paclitaxel in Treatment of Gastric Cancer

To analyze the evaluation of artificial intelligence algorithm combined with gastric computed tomography (CT) image in clinical chemotherapy for advanced gastric cancer, 112 patients with advanced gastric cancer were selected as the research object. Among which, 56 patients in the experimental group received paclitaxel (PTX) combined with decitabine sequential decitabine maintenance therapy. Fifty-six patients in the control group received first-line treatment with decitabine combined with cisplatin. The image segmentation algorithm based on fast interactive dictionary selection was used to process gastric CT images. Complete response (CR), partial response (PR), stable disease (SD), progressive disease (PD), response rate (RR), disease control rate (DCR), and overall survival (OS) after treatment were recorded. The true-positive rate (TPR) and coincidence ratio (CR) of the proposed algorithm for image segmentation were significantly higher than those of the mean shift algorithm and the iCoseg algorithm. The mean edge distance (MED) and edge distance variance (EDV) were significantly lower than the mean shift algorithm and the iCoseg algorithm, and the differences were considerable ( P < 0.05 ). The number of CR (5 cases), PR (13 cases), RR (18 cases), and DCR (44 cases) in the experimental group was significantly higher than that in the control group, while the number of PD (12 cases) was significantly lower than that in the control group ( P < 0.05 ). The number of patients complicated with hematological toxicity, leucopenia, thrombocytopenia, and digestive tract reaction in the experimental group was less than that in the control group ( P < 0.05 ). From the comparison of long-term efficacy, the survival rate of patients in both groups showed a decreasing trend within 24 months, but the decreasing trend of survival rate of patients in the experimental group was better than that in the control group. In short, the proposed algorithm had better segmentation performance than traditional algorithms. Compared with first-line treatment with decitabine and cisplatin, PTX in combination with decitabine sequential citabine maintenance regimens had better disease control rates, lower toxicity, and more effective improvements in patient quality of life and longer survival in patients with advanced gastric cancer.

Nanoscopic resolution within a single imaging frame

Mean-Shift Super Resolution (MSSR) is a principle based on the Mean Shift theory that improves the spatial resolution in fluorescence images beyond the diffraction limit. MSSR works on low- and high-density fluorophore images, is not limited by the architecture of the detector (EM-CCD, sCMOS, or photomultiplier-based laser scanning systems) and is applicable to single images as well as temporal series. The theoretical limit of spatial resolution, based on optimized real-world imaging conditions and analysis of temporal image series, has been measured to be 40 nm. Furthermore, MSSR has denoising capabilities that outperform other analytical super resolution image approaches. Altogether, MSSR is a powerful, flexible, and generic tool for multidimensional and live cell imaging applications.