Exploiting the PIR Sensor Analog Behavior as Thermoreceptor: Movement Direction Classification Based on Spiking Neurons

Abstract

Pyroelectric infrared sensors (PIR) are widely used as infrared (IR) detectors due to their basic implementation, low cost, low power, and performance. Combined with a Fresnel lens, they can be used as a binary detector in applications of presence and motion control. Furthermore, due to their features, they can be used in autonomous intelligent devices or included in robotics applications or sensor networks. In this work, two neural processing architectures are presented: (1) an analog processing approach to achieve the behavior of a presynaptic neuron from a PIR sensor. An analog circuit similar to the leaky integrate and fire model is implemented to be able to generate spiking rates proportional to the IR stimuli received at a PIR sensor. (2) An embedded postsynaptic neuron where a spiking neural network matrix together with an algorithm based on digital processing techniques is introduced. This structure allows connecting a set of sensors to the post-synaptic circuit emulating an optic nerve. As a case study, the entire neural processing approach presented in this paper is applied to optical flow detection considering a four-PIR array as input. The results validate both the spiking approach for an analog sensor presented and the ability to retrieve the analog information sent as spike trains in a simulated optic nerve.

Enhancing Infrared Optical Flow Network Computation through RGB-IR Cross-Modal Image Generation

“…Deep learning algorithms can extract richer image features by using a stacked convolutional computation module [ 9 , 10 ], which is beneficial for optical flow solving. In contrast, current experiments [ 11 , 12 , 13 ] involving optical flow computations of IR images still mainly use traditional algorithms or cannot independently use deep learning optical flow algorithms and validation [ 14 ]. The reason for this is that the fitting of network parameters for deep learning algorithms requires an optical flow dataset with the true value of the optical flow, which is often costly to produce.…”