Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks

By Xueyun Chen, Shiming Xiang, Chenglin Liu, Chunhong Pan. IEEE Geoscience and Remote Sensing Letters, 2014

598 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/81df59341d0bbdaed68eee0b1222969303e0f951

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

A deep learning framework for hyperspectral image classification using spatial pyramid pooling (2016, methodology): “However, the traditional DCNNs can only extract features of the same scale and is insu ﬃ cient to deal with large-scale variance of object (Chen, Xiang, et al. 2014).”
Adaptive Convolutional Neural Network and Its Application in Face Recognition (2015, unknown): “[11] presented a hybrid DNN (HDNN), by dividing the maps of the last convolutional layer and the maxpooling layer of DNN into multiple blocks of variable receptive field sizes or max-pooling field sizes, to enable the HDNN to extract variable-scale features.”
An object-based convolutional neural network (OCNN) for urban land use classification (2018, background): “…feature representation and scene understanding, the CNN has demonstrated great potential in 99 many remote sensing tasks such as vehicle detection (Chen et al., 2014; Dong et al., 2015), 100 road network extraction (Cheng et al., 2017), remotely sensed scene classification (Othman et 101 al.,…”
Unsupervised Deep Change Vector Analysis for Multiple-Change Detection in VHR Images (2019, background): “tasks, including semantic labeling [27], hyperspectral image classification [28], and target detection [29].”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, background): “…used for overall interpretation of images such as scene classification (for an image, recognize a theme from a list of possible themes; Marmanis et al., 2016; Nogueira et al., 2017), change detection (P. Zhang, Gong, et al., 2016), and object detection, for example, vehicles (X. Chen et al., 2014).”
Multimodal Classification of Remote Sensing Images: A Review and Future Directions (2015, background): “For this reason, their application to remote sensing data is still at its beginning [122], [123].”
Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification (2019, unknown): “information [40].”
Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks (2017, unknown): “Multi-scale CNN predictions have been investigated by [31] with a pyramid of images used as input to an ensemble of CNN for land cover use classification, while [1] used several convolutional blocks to process multiple scales.”
Deep Learning Based Oil Palm Tree Detection and Counting for High-Resolution Remote Sensing Images (2016, methodology): “[26] proposed a hybrid deep convolutional neural network for vehicle detection in high-resolution satellite images.”
Deep learning for decentralized parking lot occupancy detection (2017, methodology): “In the context of vehicle detection, the only work of which we are aware of using CNN is the one presented in (Chen et al., 2014), which uses a multi-scale CNN to detect vehicles in high-resolution satellite images.”
Capsule Networks for Hyperspectral Image Classification (2019, background): “However, the two-dimensional nature of all these early models typically generates an important spatial information loss, which eventually leads to a limited classiﬁcation performance (especially under the most challenging scenarios) [23].”
Spectral–spatial classification of hyperspectral images using deep convolutional neural networks (2015, methodology): “It has been introduced for image classification and achieved the state-of-the-art performance on the recognition of handwritten characters and traffic signs (Chen, Xiang, et al. 2014).”
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, background): “Among these tasks, object detection and recognition has attracted wide attention in the past few years [20, 18, 62, 55, 66, 5, 63].”
Deep Feature Fusion for VHR Remote Sensing Scene Classification (2017, background): “The research in [12] proposed a hybrid deep convolutional neural network (CNN) for vehicle detection from satellite images.”
Multiview Deep Learning for Land-Use Classification (2015, methodology): “[11] for improved vehicle detection in satellite images where variable-scale features are extracted through the use of multiple blocks of variable receptive field sizes or maxpool field sizes.”