CMAX-CAMEL: A Coarse-to-Fine Adaptive, Memory-Efficient, and Low-Power Edge Processor for Contrast Maximization

  • Min, Kyeongpil; 
  • Choi, Jongin; 
  • Lee, Kyeongwon; 
  • Lee, Woojoo
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

Contrast maximization (CMAX) is a direct geometric framework for event-based motion estimation, but its iterative warp-and-accumulate pipeline incurs input-dependent computation and frequent memory accesses, limiting real-time, low-power edge deployment. We present CMAX-CAMEL, a coarse-to-fine adaptive, memory-efficient, low-power edge processor that combines runtime-adaptive execution with a memory-centric architecture. CMAX-CAMEL adapts coarse-to-fine execution to the observed event distribution, prioritizing accuracy-improving stages while suppressing low-value iterations and unnecessary transitions. Its banked parallel memory organization sustains real-time throughput, while subsampling-coupled accumulation reduces memory-access activity along the warp-and-accumulate dataflow. On a 200 MHz Virtex FPGA prototype, CMAX-CAMEL improves estimation accuracy by up to 19%, reduces latency by 53.3%, lowers effective memory accesses by 42%, and cuts total system energy by 52.2%, demonstrating an HW–SW co-designed edge processor for real-time, low-power event-based motion estimation.

키워드

Contrast maximization; FPGA prototyping; Low-power system design; Motion estimation; SW-HW Co-design
제목
CMAX-CAMEL: A Coarse-to-Fine Adaptive, Memory-Efficient, and Low-Power Edge Processor for Contrast Maximization
저자
Min, Kyeongpil; Choi, Jongin; Lee, Kyeongwon; Lee, Woojoo
DOI
10.1145/3816440.3818592
발행일
2026
유형
Proceedings Paper
저널명
Proceedings of the International Symposium on Low Power Electronics and Design