Open Access

ARTICLE

Probability-Enhanced Anchor-Free Detector for Remote-Sensing Object Detection

Chengcheng Fan^1,2,*, Zhiruo Fang³

1 Innovation Academy for Microsatellites of CAS, Shanghai, 201210, China
2 Shanghai Engineering Center for Microsatellites, Shanghai, 201210, China
3 College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, 210095, China

* Corresponding Author: Chengcheng Fan. Email:

Computers, Materials & Continua 2024, 79(3), 4925-4943. https://doi.org/10.32604/cmc.2024.049710

Received 16 January 2024; Accepted 29 April 2024; Issue published 20 June 2024

Abstract

Anchor-free object-detection methods achieve a significant advancement in field of computer vision, particularly in the realm of real-time inferences. However, in remote sensing object detection, anchor-free methods often lack of capability in separating the foreground and background. This paper proposes an anchor-free method named probability-enhanced anchor-free detector (ProEnDet) for remote sensing object detection. First, a weighted bidirectional feature pyramid is used for feature extraction. Second, we introduce probability enhancement to strengthen the classification of the object’s foreground and background. The detector uses the logarithm likelihood as the final score to improve the classification of the foreground and background of the object. ProEnDet is verified using the DIOR and NWPU-VHR-10 datasets. The experiment achieved mean average precisions of 61.4 and 69.0 on the DIOR dataset and NWPU-VHR-10 dataset, respectively. ProEnDet achieves a speed of 32.4 FPS on the DIOR dataset, which satisfies the real-time requirements for remote-sensing object detection.

---

Keywords

---