Recognition of Bird's Nest in High Voltage Power Line using SSD

To use this electrical energy wisely all over the world, it is carried out using a medium called high voltage power lines. To transfer the electrical energy safely without any interruption, Regular maintenance and monitoring of the powerlines is needed. The main reason for the faults and damage in the overhead powerlines are due to the presence of external hindrances so-called birds' nest. Our proposed work explores the use of deep learning (DL) to detect birds' nests in high voltage power lines automatically. Two effective approaches are used (i)Visual Geometry Group (VGG16) and (ii)EfficientNetB7 and they act as the backbone architectures to extract features and the extracted features maps with relevant data are transformed into Single Shot Multibox Detector (SSD) which locates the target object - bird's nest, which significantly increases accuracy, precision, recall, and F1-score.