Rotation-Invariant Feature Learning for Object Detection in VHR Optical Remote Sensing Images by Double-Net

Zhang, Zhi; Jiang, Ruoqiao; Mei, Shaohui; Zhang, Shun; Zhang, Yifan

doi:10.1109/access.2019.2960931

Cited by 18 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6. CNNs have proved to give extraordinary results not only in case of image classification [28], [29] and object detection tasks [42]- [44] but also for quality assessment [45]- [48]. The motivation for using CNNs is the reported performance of CNN based IQA models [21]- [23] for natural images.…”

Section: Fundus Iqa Modelmentioning

confidence: 99%

Multivariate Regression-Based Convolutional Neural Network Model for Fundus Image Quality Assessment

et al. 2020

View full text Add to dashboard Cite

Objectively assessing the perceptual quality of an ocular fundus image is essential for the reliable diagnosis of various ocular diseases. A fair amount of work has been done in this field to date. However, the generalizability of the current work is limited, as the existing quality models were developed and evaluated with data-sets built with limited subjective inputs. This paper aims at addressing this limitation with the following two contributions. First, a new fundus image quality assessment (FIQuA) data-set is presented, containing 1500 fundus images with three classes of quality: Good, Fair, and Poor. Also, for each image, subjective scores (in the range [0-10]) were collected for six quality parameters, including structural and generic properties of the fundus images. Second, a new multivariate regression based convolutional neural network (CNN) model is proposed to predict the fundus image quality. The proposed model consists of two individually trained blocks. The first block consists of four pre-trained models, trained against the subjective scores for the six quality parameters, and aims at deriving the optimized features for classification. Next, the optimized features from each of the four models are ensembled together and transferred to the second block for final classification. The proposed model achieves a strong correlation with the subjective scores, with the values 0.941, 0.954, 0.853, and 0.401 obtained for SROCC, LCC, KCC, and RMSE respectively. Its classification accuracy is 95.66% over the FIQuA data-set, and 98.96% and 88.43% respectively over the two publicly available data-sets DRIMDB and EyeQ. INDEX TERMS Fundus image quality assessment, diabetic retinopathy, multivariate regression, convolutional neural network.

show abstract

Section: Fundus Iqa Modelmentioning

confidence: 99%

Multivariate Regression-Based Convolutional Neural Network Model for Fundus Image Quality Assessment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The learning-rate method proposed by Smith [9] sets cyclical learning rates for the model instead of a fixed value and uses this to train the model. Results show that this can improve the accuracy of the classification and reduce the need for trivial adjustments.…”

Section: Cyclical Learning Ratementioning

confidence: 99%

“…In the past, when using image data for classification research, the primary focus was on how to effectively perform the task of feature extraction [9,10]. The deep-learning methods used today make use of different convolutional neural network models to automatically perform feature recognition, extract the required image details, and then train the classification model to recognize the scene.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Scene Classification and Explanation Using RSSCNet and LIME

Hung

Tseng

2020

Applied Sciences

View full text Add to dashboard Cite

Classification is needed in disaster investigation, traffic control, and land-use resource management. How to quickly and accurately classify such remote sensing imagery has become a popular research topic. However, the application of large, deep neural network models for the training of classifiers in the hope of obtaining good classification results is often very time-consuming. In this study, a new CNN (convolutional neutral networks) architecture, i.e., RSSCNet (remote sensing scene classification network), with high generalization capability was designed. Moreover, a two-stage cyclical learning rate policy and the no-freezing transfer learning method were developed to speed up model training and enhance accuracy. In addition, the manifold learning t-SNE (t-distributed stochastic neighbor embedding) algorithm was used to verify the effectiveness of the proposed model, and the LIME (local interpretable model, agnostic explanation) algorithm was applied to improve the results in cases where the model made wrong predictions. Comparing the results of three publicly available datasets in this study with those obtained in previous studies, the experimental results show that the model and method proposed in this paper can achieve better scene classification more quickly and more efficiently.

show abstract

“…Wang et al [8] achieved object detection using a unified framework that can gather contextual information at multiple scales along with feature maps at the same scale. Zhang et al [9] proposed a Double-Net model with multiple CNN channels, where each channel corresponds to a certain direction of rotation, and all CNNs share the same weights. Cheng et al [10] developed a rotation-invariant framework based on the Collection of Part Detectors (COPD) for multiclass object detection.…”

Section: Introductionmentioning

confidence: 99%

Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

Körez

Barışçı

Çetin

et al. 2020

IJGI

View full text Add to dashboard Cite

The detection of objects in very high-resolution (VHR) remote sensing images has become increasingly popular with the enhancement of remote sensing technologies. High-resolution images from aircrafts or satellites contain highly detailed and mixed backgrounds that decrease the success of object detection in remote sensing images. In this study, a model that performs weighted ensemble object detection using optimized coefficients is proposed. This model uses the outputs of three different object detection models trained on the same dataset. The model’s structure takes two or more object detection methods as its input and provides an output with an optimized coefficient-weighted ensemble. The Northwestern Polytechnical University Very High Resolution 10 (NWPU-VHR10) and Remote Sensing Object Detection (RSOD) datasets were used to measure the object detection success of the proposed model. Our experiments reveal that the proposed model improved the Mean Average Precision (mAP) performance by 0.78%–16.5% compared to stand-alone models and presents better mean average precision than other state-of-the-art methods (3.55% higher on the NWPU-VHR-10 dataset and 1.49% higher when using the RSOD dataset).

show abstract

Rotation-Invariant Feature Learning for Object Detection in VHR Optical Remote Sensing Images by Double-Net

Cited by 18 publications

References 26 publications

Multivariate Regression-Based Convolutional Neural Network Model for Fundus Image Quality Assessment

Multivariate Regression-Based Convolutional Neural Network Model for Fundus Image Quality Assessment

Remote Sensing Scene Classification and Explanation Using RSSCNet and LIME

Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

Contact Info

Product

Resources

About