Suchergebnisse - DeeplabV3+ and PSPNet algorithm*

A lightweight multiscale smoke segmentation algorithm based on improved DeepLabV3+.

Autoren: Chen, Xin Hou, Qingshan Fu, Yan et al.

Quelle: IET Image Processing (Wiley-Blackwell); 8/21/2024, Vol. 18 Issue 10, p2665-2678, 14p

Schlagwörter: EVIDENCE gaps, IMAGE processing, FEATURE extraction, IMAGE segmentation, SOIL erosion, TUNNEL ventilation

基于航拍图像与改进 U-net 语义分割的复杂果园路径规划.

Alternate Title: Complex path planning in orchard using aerial images and improved U-net semantic segmentation.

Autoren: 蒲应俊 任安华 方智恒 et al.

Quelle: Transactions of the Chinese Society of Agricultural Engineering. Jul2025, Vol. 41 Issue 13, p243-253. 11p.

Schlagwörter: *DITCHES, *FRUIT trees, *ORCHARDS, *DATA augmentation, *ROBOTIC path planning

CFP-PSPNet: a lightweight unmanned vessel water segmentation algorithm.

Autoren: Yang, Xuecun Song, Yijing He, Lintao et al.

Quelle: Journal of Real-Time Image Processing; Jan2025, Vol. 22 Issue 1, p1-12, 12p

Image reconstruction of electromagnetic tomography based on generative adversarial network with spectral normalization and improved dung beetle optimization algorithm.

Autoren: Jia, Shuqing Zhang, Ronghua Fu, Wenying et al.

Quelle: Review of Scientific Instruments. Feb2025, Vol. 96 Issue 2, p1-20. 20p.

Schlagwörter: *GENERATIVE adversarial networks, *OPTIMIZATION algorithms, *MAGNETIC induction tomography, *IMAGE reconstruction, *DUNG beetles, *DEEP learning, *IMAGE reconstruction algorithms

Crack Unet: Crack Recognition Algorithm Based on Three-Dimensional Ground Penetrating Radar Images.

Autoren: Tang, Jiaming Chen, Chunhua Huang, Zhiyong et al.

Quelle: Sensors (14248220); Dec2022, Vol. 22 Issue 23, p9366, 21p

Schlagwörter: GROUND penetrating radar, IMAGE segmentation, IMAGE processing, CRACKING of pavements, IMAGE analysis, ALGORITHMS

Phenology-Guided Wheat and Corn Identification in Xinjiang: An Improved U-Net Semantic Segmentation Model Using PCA and CBAM-ASPP.

Autoren: Wei, Yang Guo, Xian Lu, Yiling et al.

Quelle: Remote Sensing; Nov2025, Vol. 17 Issue 21, p3563, 22p

Schlagwörter: WHEAT, CORN, IMAGE segmentation, DEEP learning, PHENOLOGY, FEATURE extraction

Geografische Kategorien: XINJIANG Uygur Zizhiqu (China)

A Deep Learning-Based Three-Stage Method for Spillway Blockage Detection in Reservoirs.

Autoren: Xu, Xiaohua Bao, Xuecai Wang, Yining et al.

Quelle: Water (20734441); Dec2024, Vol. 16 Issue 23, p3396, 18p

Schlagwörter: OBJECT recognition (Computer vision), DETECTION algorithms, EMERGENCY management, FLOOD control, FOREIGN bodies, IMAGE segmentation, DEEP learning

基于深度学习方法的烟草种植面积分割. (Chinese)

Alternate Title: Tobacco Planting Area Segmentation Based on Deep Learning. (English)

Autoren: 张少搏 杨 振 陈晓恒 et al.

Quelle: Mechanical & Electrical Engineering Technology; Aug2025, Vol. 54 Issue 16, p79-84, 6p

A New Clustering Algorithm Toward Building Segmentation From Aerial Images by Utilizing RGB‐Component Differences.

Autoren: Liu, Yang Liu, Shuang Xu, Jingwen et al.

Quelle: Earth & Space Science; Aug2021, Vol. 8 Issue 8, p1-15, 15p

Schlagwörter: DEEP learning, FUZZY algorithms, ALGORITHMS, K-means clustering, DRONE aircraft, MACHINE learning, REMOTE sensing

An improved tongue image segmentation algorithm based on Deeplabv3+ framework.

Autoren: Zhang, Xinfeng Bian, Haonan Cai, Yiheng et al.

Quelle: IET Image Processing (Wiley-Blackwell); Apr2022, Vol. 16 Issue 5, p1473-1485, 13p

Schlagwörter: IMAGE segmentation, CHINESE medicine, IMAGE quality analysis, TONGUE, SEMANTICS

大田作物行识别图像的快速标注与试验. (Chinese)

Alternate Title: A rapid image annotation method for row detection in field crops and experimental evaluation. (English)

Autoren: 翟志强 张硕 田永浩 et al.

Quelle: Transactions of the Chinese Society of Agricultural Engineering; Sep2025, Vol. 14 Issue 18, p193-199, 7p

Schlagwörter: LEAST squares, FIELD crops, CROP canopies, CORN seedlings, STANDARD deviations

基于弱监督语义分割的砀山梨表面缺陷识别方法. (Chinese)

Alternate Title: Recognizing the surface defects of Dangshan pears using weakly supervised semantic segmentation network. (English)

Autoren: 侯文慧 郭丹丹 周传起 et al.

Quelle: Transactions of the Chinese Society of Agricultural Engineering; Apr2025, Vol. 41 Issue 7, p173-181, 9p

Schlagwörter: COLOR space, SURFACE defects, SEED technology, NONDESTRUCTIVE testing, FRUIT quality, DEEP learning

RSA-TransUNet: a robust structure-adaptive TransUNet for enhanced road crack segmentation.

Autoren: Hou, Liling Yu, Fei Hu, Yaowen et al.

Quelle: Frontiers in Neurorobotics; 2025, p1-17, 17p

Schlagwörter: IMAGE segmentation, CRACKING of pavements, OPTIMIZATION algorithms, DETECTION algorithms, DEEP learning

An Improved HRNetV2-Based Semantic Segmentation Algorithm for Pipe Corrosion Detection in Smart City Drainage Networks.

Autoren: Gao, Liang Huang, Xinxin Si, Wanling et al.

Quelle: Journal of Imaging; Oct2025, Vol. 11 Issue 10, p325, 19p

A 2 DSC-Net: A Network Based on Multi-Branch Dilated and Dynamic Snake Convolutions for Water Body Extraction.

Autoren: Zhang, Shuai Zhang, Chao Zhao, Qichao et al.

Quelle: Water (20734441); Sep2025, Vol. 17 Issue 18, p2760, 20p

Schlagwörter: REMOTE sensing, IMAGE segmentation, HIGH resolution imaging, DEEP learning, WATER management, CONVOLUTIONAL neural networks, SPATIOTEMPORAL processes

Deep reinforcement learning and robust SLAM based robotic control algorithm for self-driving path optimization.

Autoren: Khan, Samiullah Niaz, Ashfaq Yinke, Dou et al.

Quelle: Frontiers in Neurorobotics; 2025, p1-12, 12p

Schlagwörter: REINFORCEMENT learning, DEEP reinforcement learning, TRACKING algorithms, SLAM (Robotics), DYNAMICAL systems

基于改进 ENet 的复杂背景下山药叶片图像分割方法. (Chinese)

Alternate Title: Image Segmentation Method of Chinese Yam Leaves in Complex Background Based on Improved ENet. (English)

Autoren: 芦碧波 梁 迪 杨 洁 et al.

Quelle: Smart Agriculture; Dec2024, Vol. 6 Issue 6, p109-120, 12p

Automatic Detection System for Rainfall-Induced Shallow Landslides in Southeastern China Using Deep Learning and Unmanned Aerial Vehicle Imagery.

Autoren: Zhu, Yunfu Xia, Bing Huang, Jianying et al.

Quelle: Water (20734441); Aug2025, Vol. 17 Issue 15, p2349, 22p

Schlagwörter: DEEP learning, LANDSLIDES, HIGH resolution imaging, REAL-time control, DRONE aircraft, DETECTION algorithms, ENVIRONMENTAL risk assessment

Geografische Kategorien: NANCHANG (China), CHINA

Identification of NAPL Contamination Occurrence States in Low-Permeability Sites Using UNet Segmentation and Electrical Resistivity Tomography.

Autoren: Gao, Mengwen Xiao, Yu Zhang, Xiaolei

Quelle: Applied Sciences (2076-3417); Jul2025, Vol. 15 Issue 13, p7109, 21p

Schlagwörter: ELECTRICAL resistance tomography, DEEP learning, HAZARDOUS waste sites, ENVIRONMENTAL monitoring, INDUSTRIAL contamination, POLLUTION remediation, GEOPHYSICAL observations

Geografische Kategorien: SHANGHAI (China)

Study on visual localization and evaluation of automatic freshwater fish cutting system based on deep learning framework.

Autoren: Peng, Xianhui Chen, Yan Fu, Dandan et al.

Quelle: International Journal of Food Properties; 2024, Vol. 27 Issue 1, p516-531, 16p

Schlagwörter: ARTIFICIAL neural networks, COMPUTER vision, CASCADE connections, FRESHWATER fishes, SIZE of fishes