基于SlimYOLOv3的工业场景目标检测算法

基于人工设计特征的检测算法检测速度普遍较慢,检测精度也有待提高,已无法满足现今工业生产中的需求.而基于深度学习的检测技术,因其需要大量的计算和存储空间无法在资源受限的设备上部署使用.针对这些问题,引用一种通道剪枝方法实现YOLOv3检测网络的轻量化,得到剪枝模型SlimYOLOv3,并进一步提出将SlimYOLOv3用于工业场景下的实时检测任务.方法通过对通道缩放因子施加L1正则化来增强卷积层的通道级稀疏性,并对信息量较小的特征通道进行剪枝,最终获得轻量级的网络模型.与原模型相比,SlimYOLOv3剪枝模型减小了60％,计算量减少了50％,检测速度是原模型的1.7倍,更适于智能工业场景中复杂目标的实时检测.

Target detection algorithm in industrial scene based on SlimYOLOv3

The detection speed of detection algorithms based on artificial design features is generally slow, and the detection accuracy needs to be improved, which can no longer meet the needs of today''s industrial production. The detection technology based on deep learning cannot be deployed on resource-constrained devices because it requires a lot of computing and storage space. In response to these problems, this paper cited a channel pruning method to realize the lightweight of the YOLOv3 detection network, and obtained the pruning model SlimYOLOv3, and proposed to use SlimYOLOv3 for real-time detection tasks in industrial scenarios. The method enhanced the channel-level sparsity of the convolutional layer by applying L1 regularization to the channel scaling factor, and pruned the feature channels with less information, and obtained a lightweight network model. Compared with the original model, SlimYOLOv3 gives a 60% reduction in model size and a 50% reduction in computing operations, the detection speed is 1.7 times of the original model. It is more suitable for real-time detection of complex targets in intelligent industrial scenes.