关键词: 遥感图像, 小目标检测, 实时检测, 卷积神经网络, 特征融合

Abstract: Benefiting from deep learning methods, the performance of object detection methods has greatly improved in recent years. However, significant challenges still exist in detecting targets from Unmanned Aerial Vehicle (UAV) remote sensing images. These challenges include: the small resolution and complex background of targets in UAV remote sensing imag-es, and the existing algorithms are difficult to meet the real-time requirements. Confronting these challenges, this paper proposes a Real-Time Small Target Detection (RTSTD) method based on a Multi-scalar & Multi-depth Feature Extraction (MMFE) network, which efficiently detects small targets from UAV remote sensing images. The proposed RTSTD crops an input image into multiple small-size images and feeds a portion of these small-size images into the lightweight MMFE network. Therefore, RTSTD has the capability to handle remote sensing images of arbitrary resolutions without losing image feature. A more effective output was proposed for the MMFE network: an overlap vector that represents the posi-tion and confidence of the target in the input image. To enhance the MMFE network's ability to distinguish targets from complex backgrounds, the definition of positive and negative samples is redefined. In order to test the performance of RTSTD, this paper selects and reconstructs seven datasets from UAV123, DTB70 and AU-AIR, comprising a total of 8369 UAV remote sensing images involving small target detection in ground and sea scenarios. The experimental results demonstrate that, compared to existing detection methods, the RTSTD method achieves improvements in both accuracy and speed. It achieves an F-Score of 0.90 or above, with a running speed of over 66 frames per second (FPS) using GPU acceleration and over 35 FPS using only CPU.

Key words: Remote Sensing Images, Small Target Detection, Real-time Detection, Convolutional Neural Network, Feature Fusion