Security systems place great emphasis on the safety of stored cargo, as any loss or tampering can result in significant economic damage. The cargo identification module within the security system faces the challenge of achieving a 99.99% recognition accuracy. However, current identification methods are limited in accuracy due to the lack of cargo data, insufficient utilization of image features and minimal differences between actual cargo classes. First, we collected and created a cargo identification dataset named "Cargo" using industrial cameras. Subsequently, an Attention-guided Multi-granularity feature fusion model (AGMG-Net) was proposed for cargo identification. This model extracts both coarse-grained and fine-grained features of the cargo using two branch networks and fuses them to fully utilize the information contained in these features. Furthermore, the Attention-guided Multi-stage Attention Accumulation (AMAA) module is introduced for target localization, and the Multi-region Optimal Selection method Based on Confidence (MOSBC) module is used for target cropping. The features from the two branches are fused using a fusion branch in a Concat manner for multi-granularity feature fusion. The experimental results show that the proposed model achieves an average recognition rate of 99.58, 92.73 and 88.57% on the self-built dataset Cargo, and the publicly available datasets Flower and Butterfly20, respectively. This is better than the state-of-the-art model. Therefore, this research method accurately identifies cargo categories and provides valuable assistance to security systems.

中文翻译：

---

AGMG-Net：利用多尺度和细粒度特征来改进货物识别。

安全系统非常重视存储货物的安全，因为任何丢失或篡改都可能导致重大经济损失。安防系统内的货物识别模块面临着实现99.99%识别准确率的挑战。然而，由于货物数据的缺乏、图像特征的利用不足以及实际货物类别之间的差异很小，当前的识别方法在准确性上受到限制。首先，我们使用工业相机收集并创建了一个名为“Cargo”的货物识别数据集。随后，提出了一种注意力引导的多粒度特征融合模型（AGMG-Net）用于货物识别。该模型使用两个分支网络提取货物的粗粒度和细粒度特征，并将它们融合以充分利用这些特征中包含的信息。此外，引入注意力引导的多阶段注意力累积（AMAA）模块进行目标定位，并使用基于置信度的多区域最优选择方法（MOSBC）模块进行目标裁剪。使用融合分支以 Concat 方式融合两个分支的特征，以实现多粒度特征融合。实验结果表明，该模型在自建数据集Cargo、公开数据集Flower和Butterfly20上的平均识别率分别为99.58%、92.73%和88.57%。这比最先进的模型更好。因此，该研究方法可以准确识别货物类别，为安全系统提供有价值的帮助。