基于改进YOLOv4的多目标光盘检测算法

Muti-Object dishes detection algorithm based on improved YOLOv4

针对已有两阶段目标检测算法推理速度较慢,轻量化模型在小数据集上效果较差的问题,提出了一种基于单阶段目标检测YOLOv4改进的多目标识别算法。本文以光盘检测为例,利用多目标检测完成对光盘图片的识别与分类。利用餐盘边缘特征相似的特点,对逐个餐盘进行识别,判定是否为光盘。为保留显著特征而加入注意力机制以及池化方式,并采用轻量化网络加快推理速度。通过多尺度融合的方式提高模型准确率,达到快速识别并区分多目标餐盘的光盘情况。在一个具有1000张图片的餐盘数据集上进行实验。结果表明:本文算法与改进前相比准确率提高了4.25%,与Faster RCNN等经典的目标检测器相比,FPS是后者的8~9倍。本文算法改善了轻量化模型的精度下降问题,可更加便捷并快速地部署到移动或嵌入式设备中完成任务。

The two-stage object detection algorithm has a slow inference speed,meanwhile,the lightweighted model has a poor performance on small datasets. In view of reasons mentioned above,an improved multi-object detection algorithm based on the algorithm YOLOv4 is proposed. Taking dishes detection as an example,multi-object detection is used to detect and classify the empty dishes. Similar characteristics of the plates’ edge are key identity to each completed plate. In order to preserve the salient features,the attention mechanism and pooling methods are added. Furthermore,a light-weighted network can speed up the inference speed and a multi-scale fusion method is able to improve the precision of the model. It turns out that the algorithm proposed improved 4.25% than previous work. According to the comparison with the classic detectors such as Faster RCNN,the FPS is 8-9 times of the latter one. The algorithm in this paper improves the reduced accuracy that the light-weighted models caused,and a more convenient and quick deployment of mobile or embedded devices are able to complete tasks.