Plasmon-Enhanced Optoelectronic Graded Neurons for Dual-Waveband Image Fusion and Motion Perception.

Motion recognition based on vision detectors requires the synchronous encoding and processing of temporal and spatial information in wide wavebands. Here, the dual-waveband sensitive optoelectronic synapses performing as graded neurons are reported for high-accuracy motion recognition and perception. Wedge-shaped nanostructures are designed and fabricated on molybdenum disulfide (MoS) monolayers, leading to plasmon-enhanced wideband absorption across the visible to near-infrared spectral range. Due to the charge trapping and release at shallow trapping centers within the device channel, the optoelectronic graded neurons demonstrate remarkable photo-induced conductance plasticity at both 633 and 980 nm wavelengths. A dynamic vision system consisting of 20 × 20 optoelectronic neurons demonstrates remarkable capabilities in the precise detection and perception of various motions. Moreover, neural network computing systems have been built as visual motion perceptron to identify target object movement. The recognition accuracy of dual-wavelength fused images for various motion trajectories has experienced a remarkable enhancement, transcending the previous level of less than 80% to impressive values exceeding 99%.