Dynamic Powerlines Detection for UAVs by Attention Fused Looming Detector

In low altitude flights, powerlines are one of the most dangerous threats for Unmanned Aerial Vehicles (UAVs), as they are widely spread in human society but too thin to be perceived effectively. With the thriving of UAV technology, powerline detection has become a hot issue in numerous researches. Most of the literature, however, extracted powerlines in static images while didn't from the perspective of dynamic scenes. In nature, the motion-sensitive neurons of various insects provide us with ideal examples of perceiving environmental information through the dynamic features of image motion. An outstanding one is the locusts' looming-sensitive neuron, namely the Lobula Giant Movement Detector (LGMD). The locusts being able to fly in a dense swarm without chaos collisions is believed largely owing to the LGMD neuron. Its specialized preference for looming threats and compact morphology inspired a series of robotic researches including the modeling of UAVs' collision detecting systems. However, existing LGMD models are more reactive to large size object movements while not that effective for small ones, making them incompetent for powerline detection. To address the above-mentioned challenges, we propose a neural computational model which fuses a line-attention module with the LGMD model in three different manners, i.e. (a) the preprocessing of input images, (b) processing motion information, and (c) inter-neuron synaptic mappings. Systematic experiments demonstrated that the attention mechanism, especially when discriminating features of image motion in the third manner, excellently extracts visual cues about powerlines and helps to improve collision avoidance performance even in complex backgrounds.