A Lightweight Keypoint-Based Oriented Object Detection of Remote Sensing Images
| Autor: | Ronghua Shang, Licheng Jiao, Mao Heting, Yangyang Li, Xuan Pei, Ruijiao Liu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Edge device
Computer science Science 0211 other engineering and technologies Scale (descriptive set theory) 02 engineering and technology Object detection Task (computing) symbols.namesake knowledge distillation Bounding overwatch arbitrary-oriented object detection lightweight network 0202 electrical engineering electronic engineering information engineering Gaussian function symbols General Earth and Planetary Sciences 020201 artificial intelligence & image processing remote sensing image Noise (video) 021101 geological & geomatics engineering Remote sensing Block (data storage) |
| Zdroj: | Remote Sensing Volume 13 Issue 13 Pages: 2459 Remote Sensing, Vol 13, Iss 2459, p 2459 (2021) |
| ISSN: | 2072-4292 |
| DOI: | 10.3390/rs13132459 |
| Popis: | Object detection in remote sensing images has been widely used in military and civilian fields and is a challenging task due to the complex background, large-scale variation, and dense arrangement in arbitrary orientations of objects. In addition, existing object detection methods rely on the increasingly deeper network, which increases a lot of computational overhead and parameters, and is unfavorable to deployment on the edge devices. In this paper, we proposed a lightweight keypoint-based oriented object detector for remote sensing images. First, we propose a semantic transfer block (STB) when merging shallow and deep features, which reduces noise and restores the semantic information. Then, the proposed adaptive Gaussian kernel (AGK) is adapted to objects of different scales, and further improves detection performance. Finally, we propose the distillation loss associated with object detection to obtain a lightweight student network. Experiments on the HRSC2016 and UCAS-AOD datasets show that the proposed method adapts to different scale objects, obtains accurate bounding boxes, and reduces the influence of complex backgrounds. The comparison with mainstream methods proves that our method has comparable performance under lightweight. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |