scholarly journals Crop Phenology Classification Using A Representation Learning Network From Sentinel-1 SAR Data

2019 ◽  
Author(s):  
Subhadip Dey ◽  
Dipankar Mandal ◽  
Vineet Kumar ◽  
Biplab Banerjee ◽  
J. M. Lopez-Sanchez ◽  
...  
Keyword(s):  
Representation Learning ◽  
Crop Phenology ◽  
Learning Network ◽  
Sar Data

scholarly journals SRNet: Scale-Aware Representation Learning Network for Dense Crowd Counting

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 136032-136044
Author(s):  
Liangjun Huang ◽  
Luning Zhu ◽  
Shihui Shen ◽  
Qing Zhang ◽  
Jianwei Zhang
Keyword(s):  
Representation Learning ◽  
Crowd Counting ◽  
Learning Network ◽  
Dense Crowd

scholarly journals Learning Network Embedding with Community Structural Information

2019 ◽  
Author(s):  
Yu Li ◽  
Ying Wang ◽  
Tingting Zhang ◽  
Jiawei Zhang ◽  
Yi Chang
Keyword(s):  
Community Structure ◽  
Link Prediction ◽  
Structural Information ◽  
Representation Learning ◽  
Network Embedding ◽  
Learning Network ◽  
Optimization Framework ◽  
Vertex Representation ◽  
Low Dimensional ◽  
Embedding Methods

Network embedding is an effective approach to learn the low-dimensional representations of vertices in networks, aiming to capture and preserve the structure and inherent properties of networks. The vast majority of existing network embedding methods exclusively focus on vertex proximity of networks, while ignoring the network internal community structure. However, the homophily principle indicates that vertices within the same community are more similar to each other than those from different communities, thus vertices within the same community should have similar vertex representations. Motivated by this, we propose a novel network embedding framework NECS to learn the Network Embedding with Community Structural information, which preserves the high-order proximity and incorporates the community structure in vertex representation learning. We formulate the problem into a principled optimization framework and provide an effective alternating algorithm to solve it. Extensive experimental results on several benchmark network datasets demonstrate the effectiveness of the proposed framework in various network analysis tasks including network reconstruction, link prediction and vertex classification.

scholarly journals DRLnet: Deep Difference Representation Learning Network and An Unsupervised Optimization Framework

2017 ◽  
Author(s):  
Puzhao Zhang ◽  
Maoguo Gong ◽  
Hui Zhang ◽  
Jia Liu
Keyword(s):  
Representation Learning ◽  
Learning Network ◽  
Learning Framework ◽  
Optimization Framework ◽  
Training Samples ◽  
Important Research Topic ◽  
Different Types ◽  
Joint Interpretation ◽  
The Difference ◽  
Limited Training Samples

Change detection and analysis (CDA) is an important research topic in the joint interpretation of spatial-temporal remote sensing images. The core of CDA is to effectively represent the difference and measure the difference degree between bi-temporal images. In this paper, we propose a novel difference representation learning network (DRLnet) and an effective optimization framework without any supervision. Difference measurement, difference representation learning and unsupervised clustering are combined as a single model, i.e., DRLnet, which is driven to learn clustering-friendly and discriminative difference representations (DRs) for different types of changes. Further, DRLnet is extended into a recurrent learning framework to update and reuse limited training samples and prevent the semantic gaps caused by the saltation in the number of change types from over-clustering stage to the desired one. Experimental results identify the effectiveness of the proposed framework.

scholarly journals Understanding Crop Growing Pattern in Bardhaman district of West Bengal using Multi-Date RISAT 1 MRS data

2014 ◽  
Vol XL-8 ◽  
pp. 861-864 ◽  
Author(s):  
Neetu ◽  
M. Prashnani ◽  
D. K. Singh ◽  
R. Joshi ◽  
S. S. Ray
Keyword(s):  
West Bengal ◽  
Crop Productivity ◽  
Crop Phenology ◽  
Medium Resolution ◽  
Hierarchical Decision ◽  
Signature Pattern ◽  
Sar Data ◽  
Spatio Temporal ◽  
Cropping Seasons ◽  
Phenological Phases

Information on crop phenology is essential for evaluating crop productivity and crop management. Phenological phases of rice and jute show great inter-annual variability and also large spatial distribution in West Bengal. Hence, it is essential to map the pheonological patterns. In this study spatio-temporal monitoring of the growing pattern of rice and other crops was carried out using multi-date RISAT-1 MRS data in the major rice growing region of Bardhaman district of West Bengal. RISAT-1 provides C band (5.3 Ghz) SAR data. The MRS (Medium Resolution ScanSAR) mode data with HH polarization having spatial resolution of 25 m and swath 115 km was used for this study. Total fifteen sets of MRS SAR data (with repetivity of 25 days) covering a complete year (May, 2013 to April, 2014) was used. Pre-processing of multi-date MRS data included georeferencing, calibration, image-image registration and speckle removal using Lee filter. Groundtruth collected during various cropping seasons (pre-Kharif, Kharif and Rabi) were used to generate crop signature pattern based on which hierarchical decision based models could be formed for classification. The periodic backscatter pattern of different crops and crop sequences were analysed. Accuracy of rice crop classification was higher by using 4-date data, compared to 3-date data. Rice transplanting patterns (Early, Normal and Late), both for Kharif and Rabi, could be identified using multi-date data. Major transplanting period for Kharif Rice was Early August and that of Rabi Rice was Early February.

Sign in / Sign up

Export Citation Format

Share Document