Insulator string position estimation method under complex background. (Image by SIACAS)

Unmanned aerial vehicles (UAVs) have become a popular tool in monitoring equipment condition in industrial Internet of Things (IIoT), with insulator string defect detection as an important application scenario. 

However, the limitation of energy is still a main challenge for better utilization of UAVs in such field. The endurance time is mainly affected by such factors as UAVs weight, flight time, data transmission energy consumption, and tasks computing energy consumption.

Recently, the edge computing research group in Shenyang Institute of Automation, the Chinese Academy of Sciences (SIACAS) proposed a cloud edge collaborative intelligent method for object detection, in order to reduce the computational load for intelligence computing of UAVs. The study is published in IEEE Internet of Things Journal titled A Cloud Edge Collaborative Intelligence Method of Insulator String Detection for Power IIoT.

In the process of transmission line inspection based on UAV, some targets such as insulator strings have large aspect ratio. At present, the classical methods of target location and recognition based on deep learning obtain recognition results by classifying the annotation boxes with specific aspect ratio and scale. For the recognition of rotating targets with large aspect ratios, it is necessary to rotate the annotation boxes along the specific reference direction to complete the target recognition. In order to improve the detection accuracy, it needs to increase the number of reference directions, which will greatly increase the calculation of the model, making it unsuitable for UAV patrol and other resource constrained front-end devices. Therefore, how to determine the number of reference directions and how to reduce the high amount of computation caused by multi-directional detection become the core issue.

To overcome this issue, the researchers from SIACAS analyzed the impact of the extremely large aspect ratio of object on the detection accuracy and the computational load, and established the quantitative relationship between the number of reference directions and the aspect ratio of the target.

Then, they presented a novel cloud edge collaborative intelligent method for defect recognition of insulator strings. First, an ultra-lightweight direction estimation method is proposed, which is based on the observation that the shape of targets with extremely large aspect ratios can be approximated by ellipse. Second, a lightweight and reliable insulator string defect recognition method is proposed, in which pixel level high-precision segmentation method is used to obtain the boundary of insulator string, and the defect is identified by the distribution of peak and valley points of the boundary. As the avoidance of target detection along all possible directions, the proposed algorithm can reduce the amount of computation by more than 90% without losing the recognition accuracy.

Experimental results show that the proposed method can detect defect of insulator strings with high accuracy, meanwhile has good generalization ability.

It is the first work to analyze the impact of the extremely large aspect ratio of insulator string on the detection accuracy and the computational load, noted the authors in the paper.

The edge computing research group has been focusing on data analysis of power, oil fields, mines and other systems. The relevant research results have been published in international famous academic journals [applied energy (2017, 2018), IEEE Transactions on industrial information (2018), IEEE sensors Journal (2019), complexity (2020), IEEE Internet of things Journal (2020)].

Contact:

Chunhe SONG

Email: songchunhe@sia.cn