Yan Xingyu, Jia Lixin, Cao Hui, Yu Yajie, Wang Tao, Zhang Feng, Guan Qingshu
IEEE Trans Neural Netw Learn Syst. 2024 Feb;35(2):2413-2424. doi: 10.1109/TNNLS.2022.3190139. Epub 2024 Feb 5.
The object detection of the substation is the key to ensuring the safety and reliable operation of the substation. The traditional image detection algorithms use the corresponding texture features of single-class objects and would not handle other different class objects easily. The object detection algorithm based on deep networks has generalization, and its sizeable complex backbone limits the application in the substation monitoring terminals with weak computing power. This article proposes a multitargets joint training lightweight model. The proposed model uses the feature maps of the complex model and the labels of objects in images as training multitargets. The feature maps have deeper feature information, and the feature maps of complex networks have higher information entropy than lightweight networks have. This article proposes the heat pixels method to improve the adequate object information because of the imbalance of the proportion between the foreground and the background. The heat pixels method is designed as a kind of reverse network calculation and reflects the object's position to the pixels of the feature maps. The temperature of the pixels indicates the probability of the existence of the objects in the locations. Three different lightweight networks use the complex model feature maps and the traditional tags as the training multitargets. The public dataset VOC and the substation equipment dataset are adopted in the experiments. The experimental results demonstrate that the proposed model can effectively improve object detection accuracy and reduce the time-consuming and calculation amount.
变电站的目标检测是确保变电站安全可靠运行的关键。传统的图像检测算法使用单类对象的相应纹理特征，不容易处理其他不同类别的对象。基于深度网络的目标检测算法具有通用性，但其庞大复杂的主干限制了在计算能力较弱的变电站监测终端中的应用。本文提出了一种多目标联合训练的轻量级模型。所提出的模型使用复杂模型的特征图和图像中对象的标签作为训练多目标。特征图具有更深的特征信息，并且复杂网络的特征图比轻量级网络具有更高的信息熵。由于前景和背景之间比例的不平衡，本文提出了热像素方法来改善足够的对象信息。热像素方法被设计为一种反向网络计算，并将对象的位置反映到特征图的像素上。像素的温度表示对象在这些位置存在的概率。三种不同的轻量级网络使用复杂模型特征图和传统标签作为训练多目标。实验采用了公共数据集VOC和变电站设备数据集。实验结果表明，所提出的模型可以有效提高目标检测精度，减少耗时和计算量。
