Scholarlink

Efficient recycling of transparent PET bottles necessitates a multi-model AI system capable of concurrently performing material classification and component detection. However, executing multiple models sequentially on resource-constrained edge devices results in cumulative inference times. In this paper, we address this challenge by implementing and evaluating a GStreamer-based parallel inference pipeline on a Raspberry Pi CM 5 equipped with a Hailo-8 AI accelerator. The implemented parallel architecture replicates input frames into two independent branches, enabling simultaneous execution of a PET/CAN classification model and a cap/ring/label detection model. Experimental results demonstrate that the parallel pipeline reduced the average frame processing time by 11.3% (from 29.50 ms to 26.17 ms) compared to sequential processing, thereby improving overall processing efficiency. This finding suggests that the parallel processing architecture mitigates inefficient idle times during multi-model execution, enabling stable real-time multi-task processing even in resource-constrained embedded environments.

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

Performance Evaluation of Parallel Inference Pipeline for Multi-model Processing on Edge Devices

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • So-Yeon Lee,
  • Tae-Jun Yoon,
  • Dae-Young Kim

摘要

Efficient recycling of transparent PET bottles necessitates a multi-model AI system capable of concurrently performing material classification and component detection. However, executing multiple models sequentially on resource-constrained edge devices results in cumulative inference times. In this paper, we address this challenge by implementing and evaluating a GStreamer-based parallel inference pipeline on a Raspberry Pi CM 5 equipped with a Hailo-8 AI accelerator. The implemented parallel architecture replicates input frames into two independent branches, enabling simultaneous execution of a PET/CAN classification model and a cap/ring/label detection model. Experimental results demonstrate that the parallel pipeline reduced the average frame processing time by 11.3% (from 29.50 ms to 26.17 ms) compared to sequential processing, thereby improving overall processing efficiency. This finding suggests that the parallel processing architecture mitigates inefficient idle times during multi-model execution, enabling stable real-time multi-task processing even in resource-constrained embedded environments.