面向超低功耗嵌入式系统视频目标检测的多分辨率重打分ByteTrack
Multi-resolution Rescored ByteTrack for Video Object Detection on Ultra-low-power Embedded Systems
AI总结:
针对超低功耗嵌入式系统视频目标检测的算力与精度平衡问题,提出MR2-ByteTrack框架,通过高低分辨率图像交错处理、ByteTrack时序关联与概率重打分,在GAP9微控制器上实现精度提升与延迟降低。
摘要:
本文提出了多分辨率重打分ByteTrack(MR2-ByteTrack),这是一种面向超低功耗嵌入式处理器的新型视频目标检测框架。该方法通过交替处理高分辨率图像(320×320像素)与多帧降采样帧(192×192像素),将现成的基于深度神经网络(DNN)的目标检测器的平均计算负载降低了最高2.25倍。为解决图像输入尺寸减小导致的精度下降问题,MR2-ByteTrack借助ByteTrack跟踪器将时间维度上的输出检测结果进行关联,并通过一种新型概率重打分算法纠正潜在的误分类。我们将每1帧高分辨率图像与2帧降采样图像交错作为多种前沿DNN目标检测器的输入,结合所提出的MR2-ByteTrack框架,在GAP9微控制器上验证表明:相较于仅使用全分辨率图像的逐帧推理基线方案,该方法平均精度提升2.16%,延迟降低43%。代码可在https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack获取。
英文摘要:
This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors. This method reduces the average compute load of an off-the-shelf Deep Neural Network (DNN) based object detector by up to 2.25$\times$ by alternating the processing of high-resolution images (320$\times$320 pixels) with multiple down-sized frames (192$\times$192 pixels). To tackle the accuracy degradation due to the reduced image input size, MR2-ByteTrack correlates the output detections over time using the ByteTrack tracker and corrects potential misclassification using a novel probabilistic Rescore algorithm. By interleaving two down-sized images for every high-resolution one as the input of different state-of-the-art DNN object detectors with our MR2-ByteTrack, we demonstrate an average accuracy increase of 2.16% and a latency reduction of 43% on the GAP9 microcontroller compared to a baseline frame-by-frame inference scheme using exclusively full-resolution images. Code available at: https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack
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。