基于双分支特征融合的无锚框目标检测算法

针对无锚框目标检测算法CenterNet中，目标特征利用程度不高、检测结果不够准确的问题，该文提出一种双分支特征融合的改进算法。在算法中，一个分支包含了特征金字塔增强模块和特征融合模块，以对主干网络输出的多层特征进行融合处理。同时，为利用更多的高级语义信息，在另一个分支中仅对主干网络的最后一层特征进行上采样。其次，对主干网络添加了基于频率的通道注意力机制，以增强特征提取能力。最后，采用拼接和卷积操作对两个分支的特征进行融合。实验结果表明，在公开数据集PASCAL VOC上的检测精度为82.3%，比CenterNet算法提高了3.6%，在KITTI数据集上精度领先其6%，检测速度均满足实时性要求。该文提出的双分支特征融合方法将不同层的特征进行处理，更好地利用浅层特征中的空间信息和深层特征中的语义信息，提升了算法的检测性能。

Anchor-free Object Detection Algorithm Based on Double Branch Feature Fusion

Focusing on the problem of low utilization of object features and inaccurate detection results in CenterNet, an improved algorithm of double branch feature fusion is proposed in the paper. One branch of the algorithm includes feature pyramid enhancement module and feature fusion module to fuse the multi-layer features output from the backbone network. At the same time, in order to use more high-level semantic information, only the last layer of the backbone network is upsampled in the other branch. Secondly, a frequency-based channel attention mechanism is added to the backbone network to enhance feature extraction capability. Finally, the features of the two branches are concatenated and convoluted. The experimental results show that the detection accuracy on PASCAL VOC dataset is 82.3%, which is 3.6% higher than CenterNet, and the detection accuracy on KITTI dataset is 6% higher than CenterNet. The detection speed meets the real-time requirements. The double branch feature fusion method is proposed to process the features of different layers, which makes better use of the spatial information of shallow features and the semantic information of deep features, and improves the detection performance of the algorithm.