ADT-Det: Adaptive Dynamic Refined Single-Stage Transformer Detector for Arbitrary-Oriented Object Detection in Satellite Optical Imagery
Autor: | Wanying Xu, Peng Sun, Zongtan Zhou, Qiang Ren, Yongbin Zheng |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Computer science
Science Feature extraction 0211 other engineering and technologies 02 engineering and technology feature pyramid transformer adaptive dynamic refined single-stage transformer detector 0202 electrical engineering electronic engineering information engineering Computer vision Pyramid (image processing) 021101 geological & geomatics engineering arbitrary-oriented object detection in satellite optical imagery dynamic feature refinement Orientation (computer vision) business.industry Detector Visual appearance Object detection Feature (computer vision) General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence business Focus (optics) |
Zdroj: | Remote Sensing, Vol 13, Iss 2623, p 2623 (2021) Remote Sensing; Volume 13; Issue 13; Pages: 2623 |
ISSN: | 2072-4292 |
Popis: | The detection of arbitrary-oriented and multi-scale objects in satellite optical imagery is an important task in remote sensing and computer vision. Despite significant research efforts, such detection remains largely unsolved due to the diversity of patterns in orientation, scale, aspect ratio, and visual appearance; the dense distribution of objects; and extreme imbalances in categories. In this paper, we propose an adaptive dynamic refined single-stage transformer detector to address the aforementioned challenges, aiming to achieve high recall and speed. Our detector realizes rotated object detection with RetinaNet as the baseline. Firstly, we propose a feature pyramid transformer (FPT) to enhance feature extraction of the rotated object detection framework through a feature interaction mechanism. This is beneficial for the detection of objects with diverse patterns in terms of scale, aspect ratio, visual appearance, and dense distributions. Secondly, we design two special post-processing steps for rotated objects with arbitrary orientations, large aspect ratios and dense distributions. The output features of FPT are fed into post-processing steps. In the first step, it performs the preliminary regression of locations and angle anchors for the refinement step. In the refinement step, it performs adaptive feature refinement first and then gives the final object detection result precisely. The main architecture of the refinement step is dynamic feature refinement (DFR), which is proposed to adaptively adjust the feature map and reconstruct a new feature map for arbitrary-oriented object detection to alleviate the mismatches between rotated bounding boxes and axis-aligned receptive fields. Thirdly, the focus loss is adopted to deal with the category imbalance problem. Experiments on two challenging satellite optical imagery public datasets, DOTA and HRSC2016, demonstrate that the proposed ADT-Det detector achieves a state-of-the-art detection accuracy (79.95% mAP for DOTA and 93.47% mAP for HRSC2016) while running very fast (14.6 fps with a 600 × 600 input image size). |
Databáze: | OpenAIRE |
Externí odkaz: |