[论文解读] Fast vehicle detection algorithm based on lightweight YOLO7-tiny

Bo Li, YiHua Chen+2 more|arXiv (Cornell University)|Apr 12, 2023

Advanced Neural Network Applications被引用 4

一句话总结

该论文提出Ghost-YOLOv7，一种基于YOLOv7-tiny的轻量化车辆检测模型，采用Ghost卷积、自定义的Ghost BiFPN、Ghost解耦头以及坐标注意力机制，以降低计算成本并提升推理速度与精度。在PASCAL VOC数据集上，其FLOPs降低29.8%，参数量减少37.3%，模型大小缩小35.1%，mAP提升1.1%，推理速度提升27 FPS，优于YOLOv7-tiny。

ABSTRACT

The swift and precise detection of vehicles plays a significant role in intelligent transportation systems. Current vehicle detection algorithms encounter challenges of high computational complexity, low detection rate, and limited feasibility on mobile devices. To address these issues, this paper proposes a lightweight vehicle detection algorithm based on YOLOv7-tiny (You Only Look Once version seven) called Ghost-YOLOv7. The width of model is scaled to 0.5 and the standard convolution of the backbone network is replaced with Ghost convolution to achieve a lighter network and improve the detection speed; then a self-designed Ghost bi-directional feature pyramid network (Ghost-BiFPN) is embedded into the neck network to enhance feature extraction capability of the algorithm and enriches semantic information; and a Ghost Decouoled Head (GDH) is employed for accurate prediction of vehicle location and species; finally, a coordinate attention mechanism is introduced into the output layer to suppress environmental interference. The WIoU loss function is employed to further enhance the detection accuracy. Ablation experiments results on the PASCAL VOC dataset demonstrate that Ghost-YOLOv7 outperforms the original YOLOv7-tiny model. It achieving a 29.8% reduction in computation, 37.3% reduction in the number of parameters, 35.1% reduction in model weights, 1.1% higher mean average precision (mAP), the detection speed is higher 27FPS compared with the original algorithm. Ghost-YOLOv7 was also compared on KITTI and BIT-vehicle datasets as well, and the results show that this algorithm has the overall best performance.

研究动机与目标

• 解决现有车辆检测模型在移动设备上计算复杂度过高、可行性低的问题。
• 提升智能交通系统中实时车辆检测的精度与速度。
• 在保持或提升mAP性能的同时，减小模型大小与参数数量。
• 增强复杂场景下特征表示能力与对环境干扰的鲁棒性。
• 优化模型以在资源受限的边缘设备上部署，同时不牺牲检测质量。

提出的方法

• 将YOLOv7-tiny的宽度乘数降低至0.5，以减少模型复杂度并提升推理速度。
• 用Ghost卷积替换主干网络中的标准卷积，以在保持特征表示能力的同时降低FLOPs与参数量。
• 设计了Ghost双向特征金字塔网络（Ghost-BiFPN），以增强多尺度特征融合并丰富语义信息。
• 提出了Ghost解耦头（GDH），通过解耦预测头实现更精确的车辆定位与分类。
• 在输出层集成坐标注意力机制，以抑制背景噪声并提升对相关车辆特征的关注度。
• 采用WIoU损失函数，以提高边界框回归精度并增强mAP表现。

实验结果

研究问题

• RQ1 基于YOLO的轻量化模型是否能在移动设备与边缘设备上实现更快的推理速度与更高的检测精度？
• RQ2 Ghost卷积在不降低检测性能的前提下，能在多大程度上减少模型大小与FLOPs？
• RQ3 所提出的Ghost-BiFPN在提升特征表示与多尺度检测方面效果如何？
• RQ4 Ghost解耦头是否在车辆定位与分类精度上优于标准头？
• RQ5 坐标注意力与WIoU损失是否能协同提升对环境干扰的鲁棒性与回归精度？

主要发现

• 在PASCAL VOC数据集上，Ghost-YOLOv7相比YOLOv7-tiny实现了29.8%的FLOPs降低。
• 模型参数数量减少了37.3%，模型大小缩小了35.1%。
• mAP较原始YOLOv7-tiny模型提高了1.1%。
• 推理速度提升了27 FPS，达到总提速27 FPS。
• 在KITTI与BIT-vehicle数据集上，Ghost-YOLOv7相比基线模型展现出更优的整体性能。
• 消融实验验证了各组件（包括Ghost-BiFPN、GDH与坐标注意力）在提升精度与效率方面的有效性。