Real-Time Object Detection System with Multi-Path Neural Networks
Real-Time Object Detection System with Multi-Path Neural Networks
复制标题
具有多路径神经网络的实时物体检测系统
DOI：
10.1109/rtas48715.2020.000-8
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Hanjun Kim
中科院分区：
文献类型：
--
作者：
Seonyeong Heo;Sungjun Cho;Youngsok Kim;Hanjun Kim
由于深度神经网络（DNN）的最新进展，基于DNN的目标检测系统变得高度精确，并广泛应用于自动驾驶车辆、无人机和安保机器人等实时环境中。尽管这些系统应在一定的时限内检测目标，该时限可能因车辆速度等执行环境而异，但现有系统在不考虑时变时限的情况下盲目地执行整个长延迟的DNN，因此无法保证实时性约束。这项工作提出了一种新颖的实时目标检测系统，该系统在GPU上基于一种新的DNN最坏情况执行时间（WCET）模型采用多路径神经网络。这项工作通过分析GPU上的处理器和内存争用情况，为单个DNN层设计了WCET模型，并将该模型扩展到端到端网络。这项工作还设计了具有三个新操作符（跳过、切换和动态生成提议）的多路径网络，这些操作符可动态改变其执行路径和目标对象的数量。最后，这项工作提出了一种路径决策模型，该模型在运行时根据动态变化的环境和时间约束选择最优执行路径。我们使用广泛使用的驾驶数据集进行的详细评估表明，所提出的实时目标检测系统在不违反时变时限的情况下，性能与基准目标检测系统相当。此外，WCET模型预测卷积层和组归一化层的最坏情况执行延迟的平均误差分别仅为27%和81%。
Thanks to the recent advances in Deep Neural Networks (DNNs), DNN-based object detection systems become highly accurate and widely used in real-time environments such as autonomous vehicles, drones and security robots. Although the systems should detect objects within a certain time limit that can vary depending on their execution environments such as vehicle speeds, existing systems blindly execute the entire long-latency DNNs without reflecting the time-varying time limits, and thus they cannot guarantee real-time constraints. This work proposes a novel real-time object detection system that employs multipath neural networks based on a new worst-case execution time (WCET) model for DNNs on a GPU. This work designs the WCET model for a single DNN layer analyzing processor and memory contention on GPUs, and extends the WCET model to the end-to-end networks. This work also designs the multipath networks with three new operators such as skip, switch, and dynamic generate proposals that dynamically change their execution paths and the number of target objects. Finally, this work proposes a path decision model that chooses the optimal execution path at run-time reflecting dynamically changing environments and time constraints. Our detailed evaluation using widely-used driving datasets shows that the proposed real-time object detection system performs as good as a baseline object detection system without violating the time-varying time limits. Moreover, the WCET model predicts the worst-case execution latency of convolutional and group normalization layers with only 27% and 81% errors on average, respectively.
DOI：
10.1145/3316781.3324696
发表时间：
2019-06
期刊：
2019 56th ACM/IEEE Design Automation Conference (DAC)
影响因子：
--
作者：
Zirui Xu;Fuxun Yu;Chenchen Liu;Xiang Chen
通讯作者：
Zirui Xu;Fuxun Yu;Chenchen Liu;Xiang Chen
DOI：
10.1145/3218603.3218652
发表时间：
2018-07
期刊：
Proceedings of the International Symposium on Low Power Electronics and Design
影响因子：
--
作者：
Zirui Xu;Zhuwei Qin;Fuxun Yu;Chenchen Liu;Xiang Chen
通讯作者：
Zirui Xu;Zhuwei Qin;Fuxun Yu;Chenchen Liu;Xiang Chen
使用混合分析估计 GPU 加速应用程序的 WCET
DOI：
10.1109/ecrts.2013.29
发表时间：
2013
期刊：
--
影响因子：
--
作者：
Betts A
通讯作者：
Betts A