MadEye：通过自适应相机配置提升实时视频分析精度
MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations
AI总结：
本文提出MadEye相机-服务器系统，通过自适应调整PTZ相机朝向并结合快速搜索算法与知识蒸馏策略，在同等资源下提升实时视频分析准确性2.9-25.7%，或以2-3.7倍更低的资源成本达到相同准确性。
摘要：
相机朝向（即旋转和缩放）决定了相机在给定场景中捕获的内容，进而严重影响实时视频分析管线的准确性。然而，现有的分析方法未触及这一关键的自适应调节手段，而是选择仅改变固定朝向捕获图像的编码、流式传输和分析方式。我们提出了MadEye，这是一个相机-服务器系统，能够自动且持续地调整朝向，以在当前工作负载和资源约束下最大化准确性。为了使用商用云台变焦（PTZ）相机实现这一点，MadEye嵌入了（1）一种搜索算法，能够快速探索庞大的朝向空间，以在每个时刻识别出有效的子集；以及（2）一种新颖的知识蒸馏策略，以高效地（仅使用相机资源）选择能最大化工作负载准确性的朝向。在多样化工作负载上的实验表明，MadEye在相同资源使用下将准确性提升了2.9-25.7%，或在相同准确性下实现了2-3.7倍更低的资源成本。
英文摘要：
Camera orientations (i.e., rotation and zoom) govern the content that a camera captures in a given scene, which in turn heavily influences the accuracy of live video analytics pipelines. However, existing analytics approaches leave this crucial adaptation knob untouched, instead opting to only alter the way that captured images from fixed orientations are encoded, streamed, and analyzed. We present MadEye, a camera-server system that automatically and continually adapts orientations to maximize accuracy for the workload and resource constraints at hand. To realize this using commodity pan-tilt-zoom (PTZ) cameras, MadEye embeds (1) a search algorithm that rapidly explores the massive space of orientations to identify a fruitful subset at each time, and (2) a novel knowledge distillation strategy to efficiently (with only camera resources) select the ones that maximize workload accuracy. Experiments on diverse workloads show that MadEye boosts accuracy by 2.9-25.7% for the same resource usage, or achieves the same accuracy with 2-3.7x lower resource costs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
