arrow
Return

Active Learning-Based Optimized Training Library Generation for Object-Oriented Image Classification

delete2018-01-01
delete5
PRE
AI
R
Rajeswari Balasubramaniam
‪
‪Rama Rao Nidamanuri *
R
Rama Krishna Gorthi
DOI:10.1109/TGRS.2017.2751568delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
In this paper, we introduce an active learning (AL)-based object training library generation for a multiclassifier object-oriented image analysis (OOIA) system. While several AL approaches do exist for pixel-based training library generation and for hyperspectral image classification, there is no standard training library generation strategy for OOIA of very high spatial resolution images. Given a sufficient number of training samples, supervised classification is the method of choice for image classification. However, this strategy becomes computationally expensive with the increase in the number of classes or the number of images to be classified. The above-mentioned issue is solved in this proposed method, where an optimized training library of objects (superpixels) is generated based on a batch mode AL approach. A softmax classifier is used as a detector in this method, which helps in determining the right samples to be chosen for library updation. To this end, we construct a multiclassifier system with max-voting decision to classify an image at pixel level. This algorithm was applied on three different very high-resolution airborne data sets, each with varying complexity in terms of variations in geographical context, sensors, illumination, and view angles. Our method has empirically outperformed the traditional OOIA by producing equivalent accuracy with a training library that is orders of magnitude smaller. In addition, the most distinctive ability of the algorithm is experienced in the most heterogeneous data set, where its performance in terms of accuracy is around twice the performance of the traditional method in the same situation. The generality of this classification strategy is proved through its performance on multispectral images and for cross-domain application. Finally, the robustness of this method is identified by comparing its performance with an alternative AL approach-self-learning-based semisupervised SVM. The capability of the proposed method to handle highly heterogeneous data is identified as the primary reason for its robustness.
Keywords:
Active learning (AL)
multiclassifier systems
object-oriented image analysis (OOIA)
training library

Journal

IEEE Transactions on Geoscience and Remote Sensing cover
IEEE Transactions on Geoscience and Remote Sensing
IF:
8.6
Papers:
2.2W
Citations:
14.1W

Organization

I
indian institute of space science & technology
Scholars:
0
Papers: 6
Citations: 120
D
department of space (dos), government of india
Scholars:
0
Papers: 122
Citations: 1.5K
Cited Papers

Cited Papers

Artificial intelligence system for identification of false-negative interpretations in chest radiographs
err2022-02-23
err0
PREAI
errEui Jin Hwang; Jongsoo Park; Wonju Hong; Hyun-Ju Lee; Hyewon Choi; Hyungjin Kim; Ju Gang Nam; Jin Mo Goo; Soon Ho Yoon; Chang Hyun Lee; Chang Min Park
errShare
errSave
SVM Active Learning Approach for Image Classification Using Spatial Information
err2014-04-01
err130
PREAI
errPasolli, Edoardo; Melgani, Farid; Tuia, Devis; Pacifici, Fabio; Emery, William J.
errShare
errSave
Active Learning Methods for Remote Sensing Image Classification
err2009-07-01
err432
PREAI
errTuia, Devis; Ratle, Frederic; Pacifici, Fabio; Kanevski, Mikhail F.; Emery, William J.
errShare
errSave
Childhood exposures among mothers and Hodgkin’s lymphoma in offspring
err2015-12-01
err0
PREAI
errScott Montgomery; Ole Brus; Ayako Hiyoshi; Yang Cao; Jennifer Rider; Katja Fall
errShare
errSave
Adaptive Batch Mode Active Learning
err2015-08-01
err47
PREAI
errChakraborty, Shayok; Balasubramanian, Vineeth; Panchanathan, Sethuraman
errShare
errSave
Reported self-control is not meaningfully associated with inhibition-related executive function: A Bayesian analysis
err
IF0
err2017-08-17
err0
errOAAI
errBlair Saunders; Marina Milyavskaya; Alexander Etz; Daniel Randles; Michael Inzlicht
errShare
errSave
Hepatozoonosis in a dog with skeletal involvement and meningoencephalomyelitis
err2009-02-26
err0
PREAI
errVeronica Marchetti; George Lubas; Gad Baneth; Mario Modenato; Francesca Mancianti
errShare
errSave
Semisupervised image classification with Laplacian support vector machines
err2008-07-01
err229
PREAI
errGomez-Chova, Luis; Camps-Valls, Gustavo; Munoz-Mari, Jordi; Calpe, Javier
errShare
errSave
researcher View more