Event-Based Hough Transform in a Spiking Neural Network for Multiple Line Detection and Tracking Using a Dynamic Vision Sensor

Hough Transform has been widely used to detect lines in images captured by conventional cameras. In this paper, we develop an event-based Hough transform and apply it to a new type of camera, namely Dynamic Vision Sensor (DVS). DVS outputs an asynchronous stream of binary events representing illumination change in the scene. We implement the proposed algorithm in a spiking neural network to detect lines on DVS output. Spikes (events) from the DVS sensor are first mapped to Hough transform parameter space and then sent to corresponding spiking neurons for accumulation. A spiking neuron will fire an output spike once it accumulates enough input contributions and then reset itself. The output spikes of the spiking neural network represent the parameters of detected lines. An event-based clustering algorithm is applied on the parameter space spikes to segment multiple lines and track them. In our spiking neural network, a lateral inhibition strategy is applied to suppress noise lines from being detected. This is achieved by resetting a neuron’s neighbors in addition to itself once the neuron fires an output spike. The efficacy of the proposed algorithm is shown by extensive experiments on both artificially generated events and various real DVS outputs.