Create Machine Vision Inspired by Eagle Eye

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 (MoS2) 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%.

Parallel Driving with Big Models and Foundation Intelligence in Cyber-Physical-Social Spaces

Recent years have witnessed numerous technical breakthroughs in connected and autonomous vehicles (CAVs). On the one hand, these breakthroughs have significantly advanced the development of intelligent transportation systems (ITSs); on the other hand, these new traffic participants introduce more complex and uncertain elements to ITSs from the social space. Digital twins (DTs) provide real-time, data-driven, precise modeling for constructing the digital mapping of physical-world ITSs. Meanwhile, the metaverse integrates emerging technologies such as virtual reality/mixed reality, artificial intelligence, and DTs to model and explore how to realize improved sustainability, increased efficiency, and enhanced safety. More recently, as a leading effort toward general artificial intelligence, the concept of foundation model was proposed and has achieved significant success, showing great potential to lay the cornerstone for diverse artificial intelligence applications across different domains. In this article, we explore the big models embodied foundation intelligence for parallel driving in cyber-physical-social spaces, which integrate metaverse and DTs to construct a parallel training space for CAVs, and present a comprehensive elucidation of the crucial characteristics and operational mechanisms. Beyond providing the infrastructure and foundation intelligence of big models for parallel driving, this article also discusses future trends and potential research directions, and the "6S" goals of parallel driving.