Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images
Rotated object detection in aerial images is a meaningful yet challenging task as objects are densely arranged and have arbitrary orientations. The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions. As ln-norm losses are mainly based on non-scale-invariant Minkowski distance, using ln-norm losses will lead to inconsistency with the detection metric rotational Intersection-over-Union (IoU) and training instability. To address the problems, we use Mahalanobis distance to calculate loss between the predicted and the target box vertices' vectors, proposing a new loss function called Mahalanobis Distance Loss (MDL) for eight-parameter rotated object detection. As Mahalanobis distance is scale-invariant, MDL is more consistent with detection metric and more stable during training than ln-norm losses. To alleviate the problem of boundary discontinuity like all other eight-parameter methods, we further take the minimum loss value to make MDL continuous at boundary cases. We achieve state-of-art performance on DOTA-v1.0 with the proposed method MDL. Furthermore, compared to the experiment that uses smooth L1 loss, we find that MDL performs better in rotated object detection.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionObject Detection In Aerial ImagesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance
Detecting rotated objects accurately and efficiently is a significant challenge in computer vision, particularly in applications such as aerial imagery, remote sensing, and autonomous driving. Although traditional object…
Object LocalizationAutonomous DrivingObject DetectionOriented Bounding Boxes for Small and Freely Rotated Objects
A novel object detection method is presented that handles freely rotated objects of arbitrary sizes, including tiny objects as small as $2\times 2$ pixels. Such tiny objects appear frequently in remotely sensed images, a…
Novel Object Detectionobject-detectionObject DetectionRotated Feature Network for multi-orientation object detection
General detectors follow the pipeline that feature maps extracted from ConvNets are shared between classification and regression tasks. However, there exists obvious conflicting requirements in multi-orientation object d…
ClassificationDecoderGeneral ClassificationObject+4Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-p…
object-detectionObject DetectionObject Detection In Aerial ImagesregressionRotation-robust Intersection over Union for 3D Object Detection
In this paper, we propose a Rotation-robust Intersection over Union ($ extit{RIoU}$) for 3D object detection, which aims to jointly learn the overlap of rotated bounding boxes. In most existing 3D object detection method…
2D Object Detection3D Object DetectionObjectobject-detection+1