DOTA: A Large-Scale Dataset for Object Detection in Aerial Images

Xia, Gui-Song; Bai, Xiang; Ding, Jian; Zhu, Zhen; Belongie, Serge; Luo, Jiebo; Datcu, Mihai; Pelillo, Marcello; Zhang, Liangpei

doi:10.1109/cvpr.2018.00418

Cited by 1,716 publications

(1,156 citation statements)

References 35 publications

Supporting

Mentioning

1,149

Contrasting

Order By: Relevance

“…As depicted in Tab. 1, using the same network on DOTA [25], the proposed method improves [5] by 4.49% and 4.75% mAP with and without FPN, respectively. The proposed method outperforms [5] by 1.2% mAP on HRSC2016 [38].…”

Section: Experiments On Different Network Architecturesmentioning

confidence: 86%

“…For the experiments on DOTA [25], we train the model for 50k steps, and the learning rate decays at {38k, 46k} 1. https://github.com/facebookresearch/maskrcnn-benchmark steps. Random rotation with angle among {0, π/2, π, 3π/2} and class balancing are adopted for data augmentation.…”

Section: Object Detection In Aerial Imagesmentioning

confidence: 99%

“…As illustrated, the proposed method accurately detects both horizontal and oriented objects even under dense distribution and/or being long. The quantitative comparisons with other methods on DOTA [25] and HRSC2016 [38] are depicted in Tab. 1 and Tab.…”

Section: Object Detection In Aerial Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Wang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

497

206

View full text Add to dashboard Cite

Object detection has recently experienced substantial progress. Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts. In this paper, we propose a simple yet effective framework to detect multi-oriented objects. Instead of directly regressing the four vertices, we glide the vertex of the horizontal bounding box on each corresponding side to accurately describe a multi-oriented object. Specifically, We regress four length ratios characterizing the relative gliding offset on each corresponding side. This may facilitate the offset learning and avoid the confusion issue of sequential label points for oriented objects. To further remedy the confusion issue for nearly horizontal objects, we also introduce an obliquity factor based on area ratio between the object and its horizontal bounding box, guiding the selection of horizontal or oriented detection for each object. We add these five extra target variables to the regression head of fast R-CNN, which requires ignorable extra computation time. Extensive experimental results demonstrate that without bells and whistles, the proposed method achieves superior performances on multiple multi-oriented object detection benchmarks including object detection in aerial images, scene text detection, pedestrian detection in fisheye images.

show abstract

Section: Experiments On Different Network Architecturesmentioning

confidence: 86%

Section: Object Detection In Aerial Imagesmentioning

confidence: 99%

See 1 more Smart Citation

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Wang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

497

206

View full text Add to dashboard Cite

show abstract

“…The dataset for counting task is scarce in remote sensing community. Although there are datasets built for detecting or extracting objects from remote sensing images such as SpaceNet 1 , DOTA 2 [23], these datasets are not directly suitable for counting problem, because most of images in these datasets only contain a small number of object instances, which is not enough to support the counting task; 2) Scale variation. Objects (such as buildings) in remote sensing images have diverse scales ranging from only a few pixels to thousands of pixels; 3) Complex cluttered background.…”

Section: Introductionmentioning

confidence: 99%

Counting Dense Objects in Remote Sensing Images

Gao

Liu

Wang

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Estimating accurate number of interested objects from a given image is a challenging yet important task. Significant efforts have been made to address this problem and achieve great progress, yet counting number of ground objects from remote sensing images is barely studied. In this paper, we are interested in counting dense objects from remote sensing images. Compared with object counting in natural scene, this task is challenging in following factors: large scale variation, complex cluttered background and orientation arbitrariness. More importantly, the scarcity of data severely limits the development of research in this field. To address these issues, we first construct a large-scale object counting dataset based on remote sensing images, which contains four kinds of objects: buildings, crowded ships in harbor, large-vehicles and small-vehicles in parking lot. We then benchmark the dataset by designing a novel neural network which can generate density map of an input image. The proposed network consists of three parts namely convolution block attention module (CBAM), scale pyramid module (SPM) and deformable convolution module (DCM). Experiments on the proposed dataset and comparisons with state of the art methods demonstrate the challenging of the proposed dataset, and superiority and effectiveness of our method.

show abstract

“…Object detection is also often approached using deep learning methods. To this effect, [12] introduced an object detection dataset and evaluated classical deep learning approaches. Methods taking into account the specificity of remote sensing data have been developed, such as [13] which proposed to modify the classical approach by generating rotatable region proposal which are particularly relevant for top-view imagery.…”

mentioning

confidence: 99%

Visual Question Answering From Remote Sensing Images

Lobry

Murray

Marcos

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

This paper introduces the task of visual question answering for remote sensing data (RSVQA). Remote sensing images contain a wealth of information which can be useful for a wide range of tasks including land cover classification, object counting or detection. However, most of the available methodologies are task-specific, thus inhibiting generic and easy access to the information contained in remote sensing data. As a consequence, accurate remote sensing product generation still requires expert knowledge. With RSVQA, we propose a system to extract information from remote sensing data that is accessible to every user: we use questions formulated in natural language and use them to interact with the images. With the system, images can be queried to obtain high level information specific to the image content or relational dependencies between objects visible in the images. Using an automatic method introduced in this article, we built two datasets (using low and high resolution data) of image/question/answer triplets. The information required to build the questions and answers is queried from OpenStreetMap (OSM). The datasets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task. We report the results obtained by applying a model based on Convolutional Neural Networks (CNNs) for the visual part and on a Recurrent Neural Network (RNN) for the natural language part to this task. The model is trained on the two datasets, yielding promising results in both cases.

show abstract

DOTA: A Large-Scale Dataset for Object Detection in Aerial Images

Cited by 1,716 publications

References 35 publications

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Counting Dense Objects in Remote Sensing Images

Visual Question Answering From Remote Sensing Images

Contact Info

Product

Resources

About