Ling Song, Hong Xianggong, Liu Yongchao
School of Information Engineering, Nanchang University, Nanchang 330019, China.
Sensors (Basel). 2024 Nov 10;24(22):7197. doi: 10.3390/s24227197.
A new algorithm called YOLO-APDM is proposed to address low quality and multi-scale target detection issues in infrared road scenes. The method reconstructs the neck section of the algorithm using the multi-scale attentional feature fusion idea. Based on this reconstruction, the P2 detection layer is established, which optimizes network structure, enhances multi-scale feature fusion performance, and expands the detection network's capacity for multi-scale complicated targets. Replacing YOLOv8's C2f module with C2f-DCNv3 increases the network's ability to focus on the target region while lowering the amount of model parameters. The MSCA mechanism is added after the backbone's SPPF module to improve the model's detection performance by directing the network's detection resources to the major road target detection zone. Experimental results show that on the FLIR_ADAS_v2 dataset retaining eight main categories, using YOLO-APDM compared to YOLOv8n, mAP and mAP increased by 6.6% and 5.0%, respectively. On the M3FD dataset, mAP and mAP increased by 8.1% and 5.9%, respectively. The number of model parameters and model size were reduced by 8.6% and 4.8%, respectively. The design requirements of the high-precision detection of infrared road targets were achieved while considering the requirements of model complexity control.
提出了一种名为YOLO-APDM的新算法，以解决红外道路场景中的低质量和多尺度目标检测问题。该方法利用多尺度注意力特征融合思想对算法的颈部进行了重构。基于此重构，建立了P2检测层，优化了网络结构，增强了多尺度特征融合性能，并扩展了检测网络对多尺度复杂目标的检测能力。用C2f-DCNv3替换YOLOv8的C2f模块，在降低模型参数量的同时提高了网络聚焦目标区域的能力。在主干的SPPF模块之后添加MSCA机制，通过将网络的检测资源导向主要道路目标检测区域来提高模型的检测性能。实验结果表明，在保留八个主要类别的FLIR_ADAS_v2数据集上，与YOLOv8n相比，使用YOLO-APDM时，mAP和mAP分别提高了6.6%和5.0%。在M3FD数据集上，mAP和mAP分别提高了8.1%和5.9%。模型参数量和模型大小分别减少了8.6%和4.8%。在考虑模型复杂度控制要求的同时，实现了红外道路目标高精度检测的设计要求。
