Evaluation of Deep Learning Accelerators for Object Detection at the Edge

Deep learning is moving more and more from the cloud towards the edge. Therefore, embedded devices are needed that are reasonably cheap, energy-efficient and fast enough. In this paper we evaluate the performance and energy consumption of popular, off-the-shelf commercial devices for deep learning inferencing. We compare the Intel Neural Compute Stick 2, the Google Coral Edge TPU and the Nvidia Jetson Nano with the Raspberry Pi 4 for their suitability as a central controller in an autonomous vehicle for the formula student driverless.

[1]  Deok-Jin Lee,et al.  Deep Learning-Based Real-Time Multiple-Object Detection and Tracking from Aerial Imagery via a Flying Robot with GPU-Based Embedded Devices , 2019, Sensors.

[2]  Andrew S. Cassidy,et al.  Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware , 2016, 2016 IEEE International Conference on Rebooting Computing (ICRC).

[3]  Matti Pietikäinen,et al.  Deep Learning for Generic Object Detection: A Survey , 2018, International Journal of Computer Vision.

[4]  Ninghui Sun,et al.  DianNao family , 2016, Commun. ACM.

[5]  Florent Lafarge,et al.  Low-Power Neural Networks for Semantic Segmentation of Satellite Images , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[6]  Jun Ni,et al.  Autonomous Driving System Design for Formula Student Driverless Racecar , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[7]  René Peinl,et al.  Open Source Speech Recognition on Edge Devices , 2020, 2020 10th International Conference on Advanced Computer Information Technologies (ACIT).

[8]  Xukan Ran,et al.  Deep Learning With Edge Computing: A Review , 2019, Proceedings of the IEEE.

[9]  Sungwook Choi,et al.  FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks , 2016, 2016 IEEE International Workshop on Signal Processing Systems (SiPS).

[10]  Nachiket Kapre,et al.  CaffePresso: Accelerating Convolutional Networks on Embedded SoCs , 2017, ACM Trans. Embed. Comput. Syst..

[11]  Chen Xi,et al.  EdgeDRNN: Enabling Low-latency Recurrent Neural Network Edge Inference , 2020 .

[12]  Shanq-Jang Ruan,et al.  Performance Evaluation of Edge Computing-Based Deep Learning Object Detection , 2018, ICNCC 2018.

[13]  Yury Gorbachev,et al.  OpenVINO Deep Learning Workbench: Comprehensive Analysis and Tuning of Neural Networks Inference , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[14]  Siddhartha S. Srinivasa,et al.  MuSHR: A Low-Cost, Open-Source Robotic Racecar for Education and Research , 2019, ArXiv.

[15]  Tao Peng,et al.  An Evaluation of Embedded GPU Systems for Visual SLAM Algorithms , 2020, IRIACV.

[16]  Nicholas D. Lane,et al.  DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices , 2016, 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[17]  Tianshi Chen,et al.  ShiDianNao: Shifting vision processing closer to the sensor , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[18]  Tobi Delbrück,et al.  EdgeDRNN: Enabling Low-latency Recurrent Neural Network Edge Inference , 2019, 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS).

[19]  Renaud Dubé,et al.  AMZ Driverless: The full autonomous racing system , 2019, J. Field Robotics.

[20]  Chao-Tung Yang,et al.  iSEC: An Optimized Deep Learning Model for Image Classification on Edge Computing , 2020, IEEE Access.

[21]  Gu-Yeon Wei,et al.  Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).