Albireo：面向边缘视频目标检测的自适应、能效推理框架
Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge
- Northeastern University（东北大学）
- University of Glasgow（格拉斯哥大学）
- William & Mary（威廉与玛丽学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出Albireo，一种与检测器无关的自适应推理框架，通过卡尔曼滤波预测不确定性决定跳帧，在保持检测精度的同时降低边缘视频目标检测的能耗和GPU占用。
AI中文摘要：
边缘设备上的视频目标检测需要对长帧流运行计算成本高昂的检测器，导致高能耗和持续的GPU占用。尽管连续帧高度冗余，但朴素的跳帧是内容盲目的：它会在目标进入、遮挡恢复和突然运动等关键时刻跳帧，从而降低检测质量。我们提出了Albireo，一个与检测器无关、无需编解码器的自适应推理框架，它封装现成的检测器，并根据场景内容和每个目标的时态状态决定何时可以安全地跳过检测器调用，无需修改检测器或重新训练。Albireo为每个活动目标维护一个10维卡尔曼滤波器（KF），并且仅在预测不确定性超过阈值时才调用检测器；在跳过的帧上，从KF状态预测边界框，GPU成本接近于零。一种基于KF的救援机制可在短暂的检测器漏检期间保留已确认的目标，以防止输出碎片化，而轻量级的空场景筛查可避免在无目标帧上调用检测器。我们在BDD100K MOT验证集上，使用三种架构不同的检测器（YOLO11x、YOLO26x、RF-DETR-Large）在两个NVIDIA Jetson平台（AGX Thor、AGX Orin）上评估了Albireo。在所有配置中，Albireo将AP@50保持在逐帧推理的±1.2个百分点以内，同时将总能耗降低12.1-17.6%。在YOLO26x上，它将AP@50提高0.8个百分点，同时将能耗降低17.6%（Thor）和14.4%（Orin），并将每帧能量延迟乘积分别降低24.9%和26.1%。因此，默认工作点同时提高了准确性、能量效率和延迟。相比之下，FixedSkip-2（一种固定间隔基线，跳过率为50%）损失了8.6个百分点的AP@50。源代码、评估流程和每片段结果可在https URL获取。
英文摘要：
Video object detection on edge devices runs computationally expensive detectors over long frame streams, causing high energy consumption and sustained GPU utilization. Although consecutive frames are highly redundant, naive frame skipping is content-blind: it skips during critical moments such as object entry, occlusion recovery, and abrupt motion, degrading detection quality. We present Albireo, a detector-agnostic, codec-free adaptive inference framework that wraps off-the-shelf detectors and decides when detector invocation can be safely skipped based on scene content and per-object temporal state, requiring no detector modification or retraining. Albireo maintains a 10-dimensional Kalman filter (KF) per active object and invokes the detector only when prediction uncertainty exceeds a threshold; on skipped frames, boxes are predicted from the KF state at near-zero GPU cost. A KF-based rescue mechanism preserves confirmed objects through brief detector misses to prevent output fragmentation, while a lightweight empty-scene screen avoids detector calls on objectless frames. We evaluate Albireo on the BDD100K MOT validation split with three architecturally distinct detectors (YOLO11x, YOLO26x, RF-DETR-Large) on two NVIDIA Jetson platforms (AGX Thor, AGX Orin). Across all configurations, Albireo keeps AP@50 within +/-1.2 pp of per-frame inference while reducing total energy by 12.1-17.6%. On YOLO26x, it improves AP@50 by +0.8 pp while reducing energy by 17.6% (Thor) and 14.4% (Orin) and per-frame energy-delay product by 24.9% and 26.1%, respectively. Thus, the default operating point improves accuracy, energy, and latency together. In contrast, FixedSkip-2, a fixed-interval baseline with a 50% skip rate, loses 8.6 pp AP@50. Source code, evaluation pipeline, and per-clip results are available at https://github.com/amirtaherin/albireo
