TOD: Transprecise Object Detection to Maximise Real-Time Accuracy on the Edge
arxiv(2021)
摘要
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
the MOT17Det dataset. In the MOT17-05 test dataset, TOD utilises only 45.1
GPU resource and 62.7
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要