改进RetinaNet的无人机小目标检测

无人机技术的不断成熟，使得搭载高效视觉系统的无人机应用也更加广泛。针对无人机航拍图像中小目标较多、分辨率低等原因导致的检测精度不高的问题，提出了一种改进RetinaNet的无人机航拍目标检测算法。算法针对特征图中小目标信息提取不足的问题，设计了多阶段特征融合方法，并将其与注意力机制串联设计了特征挖掘模块，可以在浅层特征图中融入深层的语义信息，丰富小目标特征；设计了基于中心点检测的无锚框(Anchor-free)方法，网络通过对中心点的回归来定位目标，而不是通过固定大小的锚框去匹配，这样做可以使网络对小目标的回归更加灵活，提高了算法的整体性能；且通过深度可分离卷积方法对网络进行轻量化设计，以压缩模型大小并提高检测速度。实验结果表明，改进算法较原RetinaNet算法平均精度提升了8.5%,检测速度提升了6帧/s,且与其他先进算法相比也具有性能优势，达到了检测精度与检测速度的均衡。

Improved RetinaNet for UAV Small Target Detection

UAV equipped with efficient vision system is widely used with the continuous maturity of UAV technology. In order to solve the problem of low detection precision due to the large number of small targets and low resolution, An improved RetinaNet algorithm for UAV aerial photography target detection was proposed. To solve the problem of insufficient extraction of small target information in feature maps, a multi-stage feature fusion method was proposed, and the feature mining module was designed by connecting the method with attention mechanism, which can integrate deep semantic information into shallow feature map and enrich small target features; the Anchor-free method based on central point detection was designed in the algorithm, In this way, the network can locate the target by the regression of the center point, rather than by the fixed size of the anchor frame to match, which can make the network more flexible in the regression of small targets; the depth separable convolution method was used to design its lightweight network model with characteristics of both reduced size and improved detection speed. The experimental results show that the improved RetinaNet algorithm improves the average accuracy by 8.5% and the detection speed by 6FPS compared with the original RetinaNet algorithm. it also has performance advantages compared with other advanced algorithms, which and achieves the balance of detection accuracy and detection speed.