Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning
Top Cited Papers
- 18 December 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 53 (6), 3325-3337
- https://doi.org/10.1109/tgrs.2014.2374218
Abstract
The abundant spatial and contextual information provided by the advanced remote sensing technology has facilitated subsequent automatic interpretation of the optical remote sensing images (RSIs). In this paper, a novel and effective geospatial object detection framework is proposed by combining the weakly supervised learning (WSL) and high-level feature learning. First, deep Boltzmann machine is adopted to infer the spatial and structural information encoded in the low-level and middle-level features to effectively describe objects in optical RSIs. Then, a novel WSL approach is presented to object detection where the training sets require only binary labels indicating whether an image contains the target object or not. Based on the learnt high-level features, it jointly integrates saliency, intraclass compactness, and interclass separability in a Bayesian framework to initialize a set of training examples from weakly labeled images and start iterative learning of the object detector. A novel evaluation criterion is also developed to detect model drift and cease the iterative learning. Comprehensive experiments on three optical RSI data sets have demonstrated the efficacy of the proposed approach in benchmarking with several state-of-the-art supervised-learning-based object detection approaches.Keywords
Funding Information
- National Science Foundation of China (91120005, 61473231, 61401357)
This publication has 36 references indexed in Scilit:
- Transfer Learning for Visual Categorization: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2014
- Unsupervised Feature Learning for Aerial Scene ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2013
- Low-Level Visual Saliency With Application on Aerial ImageryIEEE Geoscience and Remote Sensing Letters, 2013
- An Object-Oriented Visual Saliency Detection Framework Based on Sparse Coding RepresentationsIEEE Transactions on Circuits and Systems for Video Technology, 2013
- Bayesian Saliency via Low and Mid Level CuesIEEE Transactions on Image Processing, 2012
- Saliency and Gist Features for Target Detection in Satellite ImagesIEEE Transactions on Image Processing, 2010
- The DGPF-Test on Digital Airborne Camera Evaluation Overview and Test DesignPhotogrammetrie - Fernerkundung - Geoinformation, 2010
- SUN: A Bayesian framework for saliency using natural statisticsJournal of Vision, 2008
- Representing shape with a spatial pyramid kernelPublished by Association for Computing Machinery (ACM) ,2007
- Use of Neural Networks for Automatic Classification From High-Resolution ImagesIEEE Transactions on Geoscience and Remote Sensing, 2007