Towards autonomous detection and tracking of electric towers for aerial power line inspection

This paper presents an approach towards autonomous aerial power line inspection. In particular, the presented work focuses on real-time autonomous detection, localization and tracking of electric towers. A strategy which combines classic computer vision and machine learning techniques, is proposed. A generalized detection and localization approach is presented, where a two-class multilayer perceptron (MLP) neural network was trained for Tower-Background classification. This MLP is applied over sliding windows for each camera frame until a tower is detected. The detection of a tower triggers the tracker. A hierarchical tracking methodology, especially designed for tracking towers in real-time, is presented. This methodology is based on the Hierarchical Multi-Parametric and Multi-Resolution Inverse Compositional Algorithm [1], and is proposed to be used for tracking and maintaining the tower in the field of view (FOV). The proposed strategy, which is the combination of the tower detector and the tracker, is evaluated on videos from several real manned helicopter inspections. Overall, the results show that the proposed strategy performs very well at detecting and tracking various types of electric towers in diverse environmental settings.