Ship Rotated Bounding Box Space for Ship Extraction From High-Resolution Optical Satellite Images With Complex Backgrounds

Liu, Zikun; Wang, Hongzhen; Weng, Lubin; Yang, Yiping

doi:10.1109/lgrs.2016.2565705

Cited by 342 publications

(226 citation statements)

References 14 publications

Supporting

Mentioning

226

Contrasting

Order By: Relevance

“…There are 14235 vehicles that are manually labeled by using oriented bounding boxes in the images. 7) HRSC2016: The HRSC2016 dataset (Liu et al, 2016b) contains 1070 images and a total of 2976 ships collected from Google Earth used for ship detection. The image sizes change from 300×300 to 1500×900, and most of them are about 1000×600.…”

Section: Object Detection Datasets Of Optical Remote Sensing Imagesmentioning

confidence: 99%

Object detection in optical remote sensing images: A survey and a new benchmark

Wan

Cheng

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

1,232

425

View full text Add to dashboard Cite

Substantial efforts have been devoted more recently to presenting various methods for object detection in optical remote sensing images. However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate. Moreover, most of the existing datasets have some shortcomings, for example, the numbers of images and object categories are small scale, and the image diversity and variations are insufficient. These limitations greatly affect the development of deep learning based object detection methods. In the paper, we provide a comprehensive review of the recent deep learning based object detection progress in both the computer vision and earth observation communities. Then, we propose a large-scale, publicly available benchmark for object DetectIon in Optical Remote sensing images, which we name as DIOR. The dataset contains 23463 images and 192472 instances, covering 20 object classes. The proposed DIOR dataset 1) is large-scale on the object categories, on the object instance number, and on the total image number; 2) has a large range of object size variations, not only in terms of spatial resolutions, but also in the aspect of inter-and intra-class size variability across objects; 3) holds big variations as the images are obtained with different imaging conditions, weathers, seasons, and image quality; and 4) has high inter-class similarity and intra-class diversity. The proposed benchmark can help the researchers to develop and validate their data-driven methods. Finally, we evaluate several state-of-theart approaches on our DIOR dataset to establish a baseline for future research.

show abstract

Section: Object Detection Datasets Of Optical Remote Sensing Imagesmentioning

confidence: 99%

Object detection in optical remote sensing images: A survey and a new benchmark

Wan

Cheng

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

1,232

425

View full text Add to dashboard Cite

show abstract

“…5. Some detection results of the proposed method on HRSC2016 [38] in (a), MSRA-TD500 [39] in (b-c), and RCTW-17 [40] in (d-e).…”

Section: Mw-18marmentioning

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%

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

Wang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

628

274

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

“…Liu et al2016Landsat-8IR, TIR1530n/aTransform domain method: Discrete wavelet transformDiscrimination: morphological filteringyesVessel detectionY. Liu et al2016Google EarthGoogle Earth−−n/aStatistical method: rotated bounding box spaceDiscrimination: binary linear modellingyesVessel detectionZ. Liu et al2016Google Earthn/a−−n/an/aDiscrimination: attribute-based modelyesVessel category recognitionOliveau and Sahbi2016Google Earth, Gaofen-1n/a−1 (GE), (GF-1)n/aThreshold-based method: Otsu segmentation, morphological operationsDiscrimination: based on geometric characteristicsyesVessel detectionShuai, Sun, Shi, Chen2016Google Earthn/a−−n/aComputer vision method: scale invariant feature algorithmDiscrimination: maximum match number with libraryyesVessel detectionShuai, Sun, Wu et al2016WorldView-2, QuickBird-2, GeoEye-1, RapidEye, Formosat-2, Sentinel-2PAN, B, G, R, NIR0.5 (WV), 0.6 (QB), 0.4 (GE), 6.5 (RE), 2 (FS)2 (WV), 2.4 (QB), 1.6 (GE), 5 (RE), 8 (FS), 10 (S2)0–15Shape and texture: Minimum Noise Fraction algorithm, object-based image analysisClassification: threshold-rule set classificationyesVessel detection for immigrant search and rescueTopputo et al2016Google Earthn/a−−n/aComputer vision method: scale invariant feature transform descriptor with improved bag-of-words modelDiscrimination: phase spectrum of quaternion Fourier transformyesTarget detectionX.…”

Section: Inventory Of Evaluated Studiesmentioning

confidence: 99%