Automatic-Detection Method for Mining Subsidence Basins Based on InSAR and CNN-AFSA-SVM

Article Construction & Building Technology

Rapid data annotation for sand-like granular instance segmentation using mask-RCNN

Zhiyong Zhang et al.

Summary: Image processing, utilizing deep learning algorithm, demonstrates a high degree of autonomy in instance segmentation of granular materials. Lack of training data is a common challenge, but a mask labelling methodology proposed in this study can establish a large training set without manual labour. By combining data labelling method and deep-learning algorithms, fully automated image processing for granular materials can be achieved without massive manual labelling workload.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Energy & Fuels

Automatic fracture detection and characterization from unwrapped drill-core images using mask R-CNN

Fatimah Alzubaidi et al.

Summary: This paper introduces a machine learning-based approach for automatic fracture recognition from unwrapped drill-core images. The method applies a state-of-the-art convolutional neural network for object identification and segmentation, and investigates the feasibility of using synthetic fracture images for training the learning model.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Robotics

The effect of data augmentation and network simplification on the image-based detection of broccoli heads with Mask R-CNN

Pieter M. Blok et al.

Summary: The study aims to develop a robot capable of detecting broccoli heads using a deep learning algorithm to reduce labor costs. Data augmentation was found to improve the algorithm's generalization performance, with geometric transformations proving more effective than photometric transformations. The algorithm achieved successful generalization after including 5% of images from a specific cultivar in the training dataset.

JOURNAL OF FIELD ROBOTICS (2021)

添加到收藏夹

Article Remote Sensing

A New Model for three-dimensional Deformation Extraction with Single-track InSAR Based on Mining Subsidence Characteristics

Hongdong Fan et al.

Summary: The proposed model utilizes LOS displacement of symmetric points to calculate three-dimensional surface deformation in mining areas, showing good accuracy in extraction.

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Attributes based skin lesion detection and recognition: A mask RCNN and transfer learning-based deep learning framework

Muhammad Attique Khan et al.

Summary: Malignant melanoma is a deadly type of skin cancer, and a fully automated computer-aided diagnosis system based on deep learning achieves an accuracy of 96.3% in detecting it.

PATTERN RECOGNITION LETTERS (2021)

添加到收藏夹

Article Crystallography

Protein Crystal Instance Segmentation Based on Mask R-CNN

Jiangping Qin et al.

Summary: This paper introduces an algorithm that combines Mask R-CNN, CLAHE, and transfer learning to improve the accuracy of protein crystal detection. The experimental results demonstrate that this improved algorithm effectively enhances the accuracy of segmentation.

CRYSTALS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Adaptive threshold cascade faster RCNN for domain adaptive object detection

Xinhong Shi et al.

Summary: Object detection often faces the challenge of domain shift, where training and test data come from different distributions, leading to decreased detection accuracy. Domain adaptive methods, such as adaptive threshold cascade Faster RCNN (ATCFR), are developed to address this issue by introducing cascade and adaptive threshold strategies to improve detection accuracy. Experimental results show that ATCFR outperforms state-of-the-art methods in handling various domain shift problems.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

添加到收藏夹

Article

A Hybrid Two-Stage CNN-SVM Model for Bone X-Rays Classification and Abnormality Detection

Hadeer El-Saadawy et al.

International Journal of Sociotechnology and Knowledge Development (2021)

添加到收藏夹

Article Remote Sensing

A DPIM-InSAR method for monitoring mining subsidence based on deformation information of the working face after mining has ended

Jiang Chuang et al.

Summary: This study investigated a 3D surface deformation prediction method based on D-InSAR and DPIM model constraints, which effectively processed satellite image data using differential interferometry to achieve good prediction results, verifying the feasibility of the method.

INTERNATIONAL JOURNAL OF REMOTE SENSING (2021)

添加到收藏夹

Article Environmental Sciences

Subsidence Monitoring Base on SBAS-InSAR and Slope Stability Analysis Method for Damage Analysis in Mountainous Mining Subsidence Regions

Mingze Yuan et al.

Summary: This study utilized SBAS technology to analyze the surface subsidence in Zhangjiamao mining area in Shaanxi province, revealing the subsidence boundaries of three mining faces and effectively identifying landslide regions at the edge of subsidence boundaries through slope stability analysis. Field surveys confirmed the effectiveness of this method, providing a practical approach to predict subsidence boundaries and assess landslide risks in mountainous mining areas.

REMOTE SENSING (2021)

添加到收藏夹

Article Construction & Building Technology