Learning a Rotation Invariant Detector with Rotatable Bounding Box
Preprint
Abstract
Detection of arbitrarily rotated objects is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects. In this article, a new detection method is proposed which applies the newly defined rotatable bounding box (RBox). The proposed detector (DRBox) can effectively handle the situation where the orientation angles of the objects are arbitrary. The training of DRBox forces the detection networks to learn the correct orientation angle of the objects, so that the rotation invariant property can be achieved. DRBox is tested to detect vehicles, ships and airplanes on satellite images, compared with Faster R-CNN and SSD, which are chosen as the benchmark of the traditional bounding box based methods. The results shows that DRBox performs much better than traditional bounding box based methods do on the given tasks, and is more robust against rotation of input image and target objects. Besides, results show that DRBox correctly outputs the orientation angles of the objects, which is very useful for locating multi-angle objects efficiently. The code and models are available at https://github.com/liulei01/DRBox.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Feature Pyramid Networks for Object Detection2017
- Affine Invariant Description and Large-Margin Dimensionality Reduction for Target Detection in Optical Remote Sensing ImagesIEEE Geoscience and Remote Sensing Letters, 2017
- Building Regional Covariance Descriptors for Vehicle DetectionIEEE Geoscience and Remote Sensing Letters, 2017
- Convolutional Neural Network Based Automatic Object Detection on Aerial ImagesIEEE Geoscience and Remote Sensing Letters, 2016
- Efficient Saliency-Based Object Detection in Remote Sensing Images Using Deep Belief NetworksIEEE Geoscience and Remote Sensing Letters, 2016
- Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature LearningIEEE Transactions on Geoscience and Remote Sensing, 2014
- Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural NetworksIEEE Geoscience and Remote Sensing Letters, 2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Airborne Vehicle Detection in Dense Urban Areas Using HoG Features and Disparity MapsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2013
- Automatic Target Detection in High-Resolution Remote Sensing Images Using Spatial Sparse Coding Bag-of-Words ModelIEEE Geoscience and Remote Sensing Letters, 2011