Multi-Scale DenseNets-Based Aircraft Detection from Remote Sensing Images

Wang, Yantian; Li, Haifeng; Jia, Peng; Zhang, Guo; Wang, Taoyang; Hao, Xiaoyan

doi:10.3390/s19235270

Cited by 25 publications

(17 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional architecture of CenterNet [ 30 ] employed ResNet to compute image key points and conduct image medical analysis. However, the ResNet framework utilizes skip-connections and employs identity methods to avoid non-linear transformations, which cause the direct flow of gradient from the back layers to the front ones by using the identity function.…”

Section: Proposed Methodologymentioning

confidence: 99%

Detection of Diabetic Eye Disease from Retinal Images Using a Deep Learning Based CenterNet Model

Nazir

Nawaz

Rashid

et al. 2021

Sensors

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is an eye disease that alters the blood vessels of a person suffering from diabetes. Diabetic macular edema (DME) occurs when DR affects the macula, which causes fluid accumulation in the macula. Efficient screening systems require experts to manually analyze images to recognize diseases. However, due to the challenging nature of the screening method and lack of trained human resources, devising effective screening-oriented treatment is an expensive task. Automated systems are trying to cope with these challenges; however, these methods do not generalize well to multiple diseases and real-world scenarios. To solve the aforementioned issues, we propose a new method comprising two main steps. The first involves dataset preparation and feature extraction and the other relates to improving a custom deep learning based CenterNet model trained for eye disease classification. Initially, we generate annotations for suspected samples to locate the precise region of interest, while the other part of the proposed solution trains the Center Net model over annotated images. Specifically, we use DenseNet-100 as a feature extraction method on which the one-stage detector, CenterNet, is employed to localize and classify the disease lesions. We evaluated our method over challenging datasets, namely, APTOS-2019 and IDRiD, and attained average accuracy of 97.93% and 98.10%, respectively. We also performed cross-dataset validation with benchmark EYEPACS and Diaretdb1 datasets. Both qualitative and quantitative results demonstrate that our proposed approach outperforms state-of-the-art methods due to more effective localization power of CenterNet, as it can easily recognize small lesions and deal with over-fitted training data. Our proposed framework is proficient in correctly locating and classifying disease lesions. In comparison to existing DR and DME classification approaches, our method can extract representative key points from low-intensity and noisy images and accurately classify them. Hence our approach can play an important role in automated detection and recognition of DR and DME lesions.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Detection of Diabetic Eye Disease from Retinal Images Using a Deep Learning Based CenterNet Model

Nazir

Nawaz

Rashid

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Therefore, in our attack method, the optimization goal consists of two parts: L con f and L tv , which are combined to form the total loss function. The total loss function is as shown in Equation (5), where β is a hyperparameter.…”

Section: Detectormentioning

confidence: 99%

“…It has a wide range of types and scale variations and has an important role in transportation, air surveillance, etc. In recent years, object detection algorithms based on CNNs have achieved remarkable success in tasks, such as aircraft detection [1][2][3][4][5]. Adversarial attacks on object detectors have also received extensive attention [6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Scale-Adaptive Adversarial Patch Attack for Remote Sensing Image Aircraft Detection

Chen

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

With the adversarial attack of convolutional neural networks (CNNs), we are able to generate adversarial patches to make an aircraft undetectable by object detectors instead of covering the aircraft with large camouflage nets. However, aircraft in remote sensing images (RSIs) have the problem of large variations in scale, which can easily cause size mismatches between an adversarial patch and an aircraft. A small adversarial patch has no attack effect on large aircraft, and a large adversarial patch will completely cover small aircraft so that it is impossible to judge whether the adversarial patch has an attack effect. Therefore, we propose the adversarial attack method Patch-Noobj for the problem of large-scale variation in aircraft in RSIs. Patch-Noobj adaptively scales the width and height of the adversarial patch according to the size of the attacked aircraft and generates a universal adversarial patch that can attack aircraft of different sizes. In the experiment, we use the YOLOv3 detector to verify the effectiveness of Patch-Noobj on multiple datasets. The experimental results demonstrate that our universal adversarial patches are well adapted to aircraft of different sizes on multiple datasets and effectively reduce the Average Precision (AP) of the YOLOv3 detector on the DOTA, NWPU VHR-10, and RSOD datasets by 48.2%, 23.9%, and 20.2%, respectively. Moreover, the universal adversarial patch generated on one dataset is also effective in attacking aircraft on the remaining two datasets, while the adversarial patch generated on YOLOv3 is also effective in attacking YOLOv5 and Faster R-CNN, which demonstrates the attack transferability of the adversarial patch.

show abstract

“…DenseNet [25] model is the advanced or improved form of Resnet, where the current layer belongs to all other layers. DenseNet contains the set of dense blocks, which remain consecutively linked with each other by using the extra convolutional and pooling layers among consecutive dense blocks.…”

Section: Features Extractionmentioning

confidence: 99%

“…We have selected standard datasets like ORIGA and HRF databases which contain light variations and noise effects but lack the presence of blurriness. So, in this work, we have added blurriness in samples of mentioned datasets and proposed a novel technique, namely, Densenet-77 based [25]…”

Section: Introductionmentioning

confidence: 99%

Optic Disc and Optic Cup Segmentation for Glaucoma Detection from Blur Retinal Images Using Improved Mask-RCNN

Nazir

Irtaza

Старовойтов

2021

International Journal of Optics

View full text Add to dashboard Cite

Glaucoma is a fatal eye disease that harms the optic disc (OD) and optic cup (OC) and results into blindness in progressed phases. Because of slow progress, the disease exhibits a small number of symptoms in the initial stages, therefore causing the disease identification to be a complicated task. So, a fully automatic framework is mandatory, which can support the screening process and increase the chances of disease detection in the early stages. In this paper, we deal with the localization and segmentation of the OD and OC for glaucoma detection from blur retinal images. We have presented a novel method that is Densenet-77-based Mask-RCNN to overcome the challenges of the glaucoma detection. Initially, we have performed the data augmentation step together with adding blurriness in samples to increase the diversity of data. Then, we have generated the annotations from ground-truth (GT) images. After that, the Densenet-77 framework is employed at the feature extraction level of Mask-RCNN to compute the deep key points. Finally, the calculated features are used to localize and segment the OD and OC by the custom Mask-RCNN model. For performance evaluation, we have used the ORIGA dataset that is publicly available. Furthermore, we have performed cross-dataset validation on the HRF database to show the robustness of the presented framework. The presented framework has achieved an average precision, recall, F-measure, and IOU as 0.965, 0.963, 0.97, and 0.972, respectively. The proposed method achieved remarkable performance in terms of both efficiency and effectiveness as compared to the latest techniques under the presence of blurring, noise, and light variations.

show abstract

Multi-Scale DenseNets-Based Aircraft Detection from Remote Sensing Images

Cited by 25 publications

References 39 publications

Detection of Diabetic Eye Disease from Retinal Images Using a Deep Learning Based CenterNet Model

Detection of Diabetic Eye Disease from Retinal Images Using a Deep Learning Based CenterNet Model

Scale-Adaptive Adversarial Patch Attack for Remote Sensing Image Aircraft Detection

Optic Disc and Optic Cup Segmentation for Glaucoma Detection from Blur Retinal Images Using Improved Mask-RCNN

Contact Info

Product

Resources

About