Scholarlink

<p>Time and space constitute fundamental dimensions of physical reality, making their integrated processing crucial for advanced vision perception systems. Current visual information processing faces dual limitations: von Neumann architecture-induced data-transfer bottlenecks and spatial-feature processing often disregard temporal dynamics, while temporal analyzers oversimplify spatial complexity. Here we propose an artificial vision hardware enabling intrinsic temporal-spatial fusion through voltage-tunable temporal differentiation with microsecond-scale resolution and photoresponse-weighted spatial compression via pixel binning. The architecture achieves millisecond-level latency from sensing to decision in autonomous driving scenarios through in-sensor spatiotemporal fusion, eliminating external computing dependencies. Experimental validation demonstrates 95 % recognition accuracy in human actions database while the operation counts required is only 1/10 of conventional convolutional processing. This work facilitates physical-level spatiotemporal fusion through the co-optimization of photodetector arrays and weighted control circuits, which could fundamentally reshape machine vision architectures with potential extensions to real-time decision systems.</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

Temporal-Spatial Fusion Vision Hardware Enables Streamlined In-Sensor Computing for Dynamic Scenes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月15日

查看全文
  • Yi Wu,
  • Wenjie Deng,
  • Ruihao Liu,
  • Chutian Xiao,
  • Jianmiao Guo,
  • Chaoyi Zhu,
  • Qinqi Ren,
  • Zehao Li,
  • Yushan Wu,
  • Kexin Li,
  • Xueliang Ma,
  • Xiaoting Wang,
  • Zhangyang Xu,
  • Zikang Zhao,
  • Zhijie Chen,
  • Yang Chai,
  • Yongzhe Zhang

摘要

Time and space constitute fundamental dimensions of physical reality, making their integrated processing crucial for advanced vision perception systems. Current visual information processing faces dual limitations: von Neumann architecture-induced data-transfer bottlenecks and spatial-feature processing often disregard temporal dynamics, while temporal analyzers oversimplify spatial complexity. Here we propose an artificial vision hardware enabling intrinsic temporal-spatial fusion through voltage-tunable temporal differentiation with microsecond-scale resolution and photoresponse-weighted spatial compression via pixel binning. The architecture achieves millisecond-level latency from sensing to decision in autonomous driving scenarios through in-sensor spatiotemporal fusion, eliminating external computing dependencies. Experimental validation demonstrates 95 % recognition accuracy in human actions database while the operation counts required is only 1/10 of conventional convolutional processing. This work facilitates physical-level spatiotemporal fusion through the co-optimization of photodetector arrays and weighted control circuits, which could fundamentally reshape machine vision architectures with potential extensions to real-time decision systems.