Adaptive Period Embedding for Representing Oriented Objects in Aerial Images

Abstract

We propose a novel method for representing oriented objects in aerial images named Adaptive Period Embedding (APE). While traditional object detection methods represent object with horizontal bounding boxes, the objects in aerial images are oritented. Calculating the angle of object is an yet challenging task. While almost all previous object detectors for aerial images directly regress the angle of objects, they use complex rules to calculate the angle, and their performance is limited by the rule design. In contrast, our method is based on the angular periodicity of oriented objects. The angle is represented by two two-dimensional periodic vectors whose periods are different, the vector is continuous as shape changes. The label generation rule is more simple and reasonable compared with previous methods. The proposed method is general and can be applied to other oriented detector. Besides, we propose a novel IoU calculation method for long objects named length independent IoU (LIIoU). We intercept part of the long side of the target box to get the maximum IoU between the proposed box and the intercepted target box. Thereby, some long boxes will have corresponding positive samples. Our method reaches the 1 st place of DOAI2019 competition task1 (oriented object) held in workshop on Detecting Objects in Aerial Images in conjunction with IEEE CVPR 2019.

Learning Point-Guided Localization for Detection in Remote Sensing Images

“…Some works have also borrowed ideas from semantic segmentation [35]. APE [36] generates candidate bounding boxes from the shrunk segmentation map of the OBB, which is the same as EAST [37]. Segmentation maps with 8 channels are predicted in the RPN stage to represent rotated proposals for regression.…”

Single-Stage Rotation-Decoupled Detector for Oriented Object

“…DHN [17] presents a dynamic refinement network which alleviates the misalignment between receptive fields and objects by a feature selection module (FSM) and refines the prediction in an object-wise manner by using a dynamic refinement head (DRH). Regarding the angular periodicity problem in rotating object detection, APE [18] represents the angle as continuously changing periodic vectors to avoid ambiguity. In addition, APE [18] designs a length-independent IoU (LIIoU) for long objects to make the detector more robust.…”

“…Regarding the angular periodicity problem in rotating object detection, APE [18] represents the angle as continuously changing periodic vectors to avoid ambiguity. In addition, APE [18] designs a length-independent IoU (LIIoU) for long objects to make the detector more robust.…”

“…As a result of these problems, the IoU between the matched oriented anchor and the ground truth box fluctuates dramatically with the change of the angle between the principal axes, especially when the aspect ratio of the bounding box is large. Recent studies [12][13][14][15][16][17][18] have proposed a series of optimization schemes for oriented object detection, but there is still much room for improvement in this area of research. In this paper, we propose a novel single-stage detector for effective and accurate oriented object detection.…”

ℱ3-Net: Feature Fusion and Filtration Network for Object Detection in Optical Remote Sensing Images

“…Ding et al [20] took the geometry transformation between horizontal and rotational RoIs into account and developed a lightweight Region of Interest (RoI) Transformer for rotation-invariant region feature extraction. Following the rotational regional proposal network (RRPN) [21], many researchers incorporate rotation-aware factors into a regional proposal network (RPN) to handle object rotation variations [22][23][24]. Specifically, Li et al [25] embedded additional multi-angle anchors into RPN for the generation of multi-scale and translation-invariant candidate regions.…”