Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images

Cheng, Gong; Zhou, Peicheng; Han, Junwei

doi:10.1109/tgrs.2016.2601622

Cited by 1,482 publications

(682 citation statements)

References 48 publications

Supporting

Mentioning

682

Contrasting

Order By: Relevance

“…In our work, we selected an NWPU VHR-10 dataset used in prior studies [5] as benchmarks based on the considerations listed above. The advantages of NWPU VHR-10 dataset can be summarized as:…”

Section: Dataset and Implementation Detailsmentioning

confidence: 99%

“…In the past, researchers have modeled geometric variations with two methods, both based on feature representation. The first method involves adding geometric priors in training samples, which is usually completed by manually rotating or performing transformation the training objects in two-dimensional (2D) or three-dimensional (3D) space [5]. The second method involves extracting transform invariance features.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed deformable ConvNet with arcNMS is evaluated and compared to established VHR object detection methods in the NWPU VHR-10 dataset [5,17] . The experiment results confirm our assumptions and prove that deformable ConvNets outperforms state-of-the-art CNN models in object detection tasks without data augmentation.…”

Section: Introductionmentioning

confidence: 99%

“…With Cheng et al [5] being cited more than 60 times, the NWPU VHR-10 dataset has become the widely applied open source VHR remote sensing image dataset for object detection. Han et al [16] reported that CNNs attained an accuracy of about 70% in object detection.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Deformable ConvNet with Aspect Ratio Constrained NMS for Object Detection in Remote Sensing Imagery

Wang

et al. 2017

Remote Sensing

108

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have demonstrated their ability object detection of very high resolution remote sensing images. However, CNNs have obvious limitations for modeling geometric variations in remote sensing targets. In this paper, we introduced a CNN structure, namely deformable ConvNet, to address geometric modeling in object recognition. By adding offsets to the convolution layers, feature mapping of CNN can be applied to unfixed locations, enhancing CNNs' visual appearance understanding. In our work, a deformable region-based fully convolutional networks (R-FCN) was constructed by substituting the regular convolution layer with a deformable convolution layer. To efficiently use this deformable convolutional neural network (ConvNet), a training mechanism is developed in our work. We first set the pre-trained R-FCN natural image model as the default network parameters in deformable R-FCN. Then, this deformable ConvNet was fine-tuned on very high resolution (VHR) remote sensing images. To remedy the increase in lines like false region proposals, we developed aspect ratio constrained non maximum suppression (arcNMS). The precision of deformable ConvNet for detecting objects was then improved. An end-to-end approach was then developed by combining deformable R-FCN, a smart fine-tuning strategy and aspect ratio constrained NMS. The developed method was better than a state-of-the-art benchmark in object detection without data augmentation.

show abstract

Section: Dataset and Implementation Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Deformable ConvNet with Aspect Ratio Constrained NMS for Object Detection in Remote Sensing Imagery

Wang

et al. 2017

Remote Sensing

108

View full text Add to dashboard Cite

show abstract

“…With the development of deep learning techniques, learning features from data is promising for discriminating objects from the clutter background. For instance, Cheng proposed learning rotation-invariant HOG [3] and rotation-invariant CNN(convolutional neural networks) [4] to describe objects. Cao [5] tried to use the region-based CNN to detect aircrafts under complex environments.…”

Section: Introductionmentioning

confidence: 99%

Learning Deep Relationship for Object Detection

Huo

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYObject detection has been a hot topic of image processing, computer vision and pattern recognition. In recent years, training a model from labeled images using machine learning technique becomes popular. However, the relationship between training samples is usually ignored by existing approaches. To address this problem, a novel approach is proposed, which trains Siamese convolutional neural network on feature pairs and finely tunes the network driven by a small amount of training samples. Since the proposed method considers not only the discriminative information between objects and background, but also the relationship between intraclass features, it outperforms the state-of-arts on real images.

show abstract

Bibliography

2021

Deep Learning for the Earth Sciences

View full text Add to dashboard Cite

Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images

Cited by 1,482 publications

References 48 publications

Deformable ConvNet with Aspect Ratio Constrained NMS for Object Detection in Remote Sensing Imagery

Deformable ConvNet with Aspect Ratio Constrained NMS for Object Detection in Remote Sensing Imagery

Learning Deep Relationship for Object Detection

Bibliography

Contact Info

Product

Resources

About