Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise Object Detector (TOD) which maximises the real-time object detection accuracy on an edge device by selecting an appropriate Deep Neural Network (DNN) on the fly with negligible computational overhead. TOD makes two key contributions over the state of the art: (1) TOD leverages characteristics of the video stream such as object size and speed of movement to identify networks with high prediction accuracy for the current frames; (2) it selects the best-performing network based on projected accuracy and computational demand using an effective and low-overhead decision mechanism. Experimental evaluation on a Jetson Nano demonstrates that TOD improves the average object detection precision by 34.7 % over the YOLOv4-tiny-288 model on average over the MOT17Det dataset. In the MOT17-05 test dataset, TOD utilises only 45.1 % of GPU resource and 62.7 % of the GPU board power without losing accuracy, compared to YOLOv4-416 model. We expect that TOD will maximise the application of edge devices to real-time object detection, since TOD maximises real-time object detection accuracy given edge devices according to dynamic input features without increasing inference latency in practice.
翻译:边缘的实时视频分析具有挑战性,因为计算限制的资源通常无法以完全忠于和框架率分析视频流,从而导致准确性丧失。本文件建议使用一个快速的天体探测器(TOD),在边端设备上最大限度地实现实时天体检测准确性,在飞上选择一个适当的深神经网络(DNN),而计算间接费用微不足道。TOD在最新水平上做出两项重要贡献:(1)TOD利用视频流的特性,如天体大小和移动速度等,以确定当前框架预测精确度高的网络;(2)根据预测准确性和计算需求选择最佳的网络特征,使用一个有效和低超高端的决定机制。杰特森纳诺诺的实验性评估表明,在MOT17D 定位模型中平均将平均天体探测精确度提高34.7%。在MOT17D 数据元中测试数据集,TOD仅使用45.1%的GPU资源精确度和计算需求。