Hierarchical and Robust Convolutional Neural Network for Very High-Resolution Remote Sensing Object Detection

By Yuan Yuan, Yachuang Feng, Xiaoqiang Lu. IEEE Transactions on Geoscience and Remote Sensing, 2019

338 citations recorded by the source corpus.

Object detection is a basic issue of very high-resolution remote sensing images (RSIs) for automatically labeling objects. At present, deep learning has gradually gained the competitive advantage for remote sensing object detection, especially based on convolutional neural networks (CNNs). Most of the existing methods use the global information in the fully connected feature vector and ignore the local information in the convolutional feature cubes. However, the local information can provide spatial information, which is helpful for accurate localization. In addition, there are variable factors, such as rotation and scaling, which affect the object detection accuracy in RSIs. In order to solve these problems, this paper presents a hierarchical robust CNN. First, multiscale convolutional features are extracted to represent the hierarchical spatial semantic information. Second, multiple fully connected layer features are stacked together so as to improve the rotation and scaling robustness. Experiments on two data sets have shown the effectiveness of our method. In addition, a large-scale high-resolution remote sensing object detection data set is established to make up for the current situation that the existing data set is insufficient or too small. The data set is available at https://github.com/CrazyStoneonRoad/TGRS-HRRSD-Dataset.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/68fa1005ae63ee2ce6a57d03cd6057f7ad3a8187

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 Media Technology

In Ocean Engineering

Citations in the corpus

Transformers in Remote Sensing: A Survey (2022, background): “SAIEC [37] Detection, Segmentation DIOR [83], HRRSD [84], NWPU VHR-10 [85] mAP Introduces a local perception Swin transformer backbone that aims to combine the merits of transformers and CNNs for improving the local perception capabilities.”
A Survey of Deep Learning-Based Object Detection (2019, background): “NWPU VHR-10 [166], HRRSD [146], DOTA [167], DLR 3KMunich [168] andVEDAI [169] are remote sensing object detection benchmarks.”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “some public datasets [17], [42], [43], [44], [45] have multiple categories, they have only limited number of samples, which are hardly efficient for training robust deep models.”
Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast (2020, background): “applications [1], [2], such as scene classification [3]–[7], object localization [8]–[12], and change detection [13]–[15], due to their prominent capabilities to uncover highly representative features from RS scenes [16].”
Poly Kernel Inception Network for Remote Sensing Detection (2024, methodology): “…variations in RSIs, certain methods emphasize the extraction of multi-scale features through approaches like data augmentation [2, 54, 82], multi-scale feature integration [39, 61, 81, 83], feature pyramid network (FPN) enhancement [16, 25, 35, 80], or multi-scale anchor generation [19, 24, 52].”
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, methodology): “Among these tasks, object detection and recognition has attracted wide attention in the past few years [20, 18, 62, 55, 66, 5, 63].”
EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain (2024, methodology): “Specifically, we utilize ViT [12] to capture the spatial contextual information at different levels for images and employ CNN [13] to extract the local information present across multiple scales.”
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing (2023, methodology): “We combined six remote sensing datasets with object detection annotation, including DOTA [75], DIOR [76], HRRSD [77], RSOD [78], LEVIR [79], and HRSC [80].”