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

介绍了一种用于超低功耗嵌入式处理器的新型视频目标检测框架Multi-Resolution Rescored Byte-Track（MR2-ByteTrack），其通过交替处理高分辨率图像和多个缩小尺寸的帧来减少现成的深度神经网络（DNN）目标检测器的平均计算负载，同时使用ByteTrack跟踪器在时间上相关联输出的检测结果，并通过一种新颖的概率重新评分算法来纠正潜在的错分问题，通过在不同最新DNN目标检测器的输入中使用两个缩小尺寸的图像交错处理每个高分辨率图像的方法，与基于全分辨率图像独占使用的基准帧级推理方案相比，在GAP9微控制器上展示了平均准确率提高了2.16%，延迟减少了43%的结果。

多分辨率重评分字节跟踪用于超低功耗嵌入式系统的视频目标检测