Scholarlink

<p>Efficient dynamic vision requires capturing instantaneous changes and temporal context, yet existing image and event sensors rely on power-hungry digital processing. Here, we introduce an in-sensor dual-response architecture that concurrently generates analog event spikes and persistent memory tails. A prototype sensor integrates phosphor pairs with silicon photodiodes and transimpedance amplifiers to achieve microsecond- and millisecond-scale dual kinetics. Measurements during light-emitting diode replay reconstruct event frames that match software frame differences, while the slow channel behaves as a linear reservoir of motion history. A single memory frame fed to a convolutional neural network enables accurate classification of human actions (93.1%) and vehicle trajectories (98.0%), as well as speed estimation with errors of 2.15 km/h. Integration with a compressive optical neural network front end mapping 4900 inputs to 16 per frame yields 93.3% action classification accuracy. By eliminating analog-to-digital conversion and digital accumulation, this approach enables ultralow-latency, ultralow-power neuromorphic vision.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

In-sensor analog optoelectronic processing of concurrent event and memory signals for dynamic vision sensing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月26日

查看全文
  • Yelim Kim,
  • Hyeonsu Park,
  • Minjoo Kim,
  • Suhee Jang,
  • Dae Yeop Jeong,
  • Lia Saptini Handriani,
  • Hyuncheol Yun,
  • Namyoung Gwak,
  • Nuri Oh,
  • Sung Ik Yang,
  • Soyeong Kwon,
  • SungWoo Nam,
  • Won Il Park

摘要

Efficient dynamic vision requires capturing instantaneous changes and temporal context, yet existing image and event sensors rely on power-hungry digital processing. Here, we introduce an in-sensor dual-response architecture that concurrently generates analog event spikes and persistent memory tails. A prototype sensor integrates phosphor pairs with silicon photodiodes and transimpedance amplifiers to achieve microsecond- and millisecond-scale dual kinetics. Measurements during light-emitting diode replay reconstruct event frames that match software frame differences, while the slow channel behaves as a linear reservoir of motion history. A single memory frame fed to a convolutional neural network enables accurate classification of human actions (93.1%) and vehicle trajectories (98.0%), as well as speed estimation with errors of 2.15 km/h. Integration with a compressive optical neural network front end mapping 4900 inputs to 16 per frame yields 93.3% action classification accuracy. By eliminating analog-to-digital conversion and digital accumulation, this approach enables ultralow-latency, ultralow-power neuromorphic vision.