![]() ![]() Please cite our work if you are using it in your project. ![]() ![]() Experimental results are found to be promising for the proposed scheme to handle the DA problem under a cross-sensor environment. Finally, the labeled source and “most-informative” target samples are merged to train a classifier which is then used to predict the land cover classes under a multi-sensor framework. Thereafter, a standard deviation (SD)-based active learning (AL) technique is investigated by exploiting the labeled source images to get the “most-informative” target samples. An Open, Multi-Sensor, Dataset of Water Pollution of Ganga Basin and its Application to Understand Impact of Large Religious Gathering Biplav Srivastava1,3, Sandeep Sandha1, Vaskar Raychoudhury2,4, Sukanya Randhawa1, Viral Kapoor2 and Anmol Agrawal2 1IBM Research India 3IBM T J Watson Research Center, USA. At the onset, a feature extraction (FE) along with a “stacking of sample” (whenever required) strategy is proposed to balance the cross-sensor data in terms of feature dimensions and the available number of samples. To resolve this, a cross-sensor domain adaptation (DA) strategy is investigated by considering two source → target scenarios using hyperspectral and aerial image datasets. This occurs due to different probability distributions of the collected data from different satellites (having diverse image resolutions and different geographical locations). IEEE Geoscience and Remote Sensing Letters, 19, 1-5.Ĭross-sensor remote-sensing data have a significant impact on degrading the performance of traditional land cover classification (LCC) models. Deep Learning-Based Cross-Sensor Domain Adaptation Under Active Learning for Land Cover Classification. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |