Research on Intelligent Target Detection and Coder-decoder Technology Based on Embedded Platform

In order to meet the embedded application requirements of machine learning algorithm, the intelligent target detection and recognition algorithm based on convolutional neural network and corresponding optimal process are studied. Detailed network structure analysis and network performance analysis are carried out. Based on GPU embedded platform, TensorRT technology is used to accelerate the embedded application of intelligent target detection and recognition algorithm, including fp16 and int8 inference modes. Satisfactory verification results are achieved on embedded platform. In addition, an integrated system of real-time machine learning and H.265 encoding and decoding technology is realized. Firstly, the compressed image data sent by the camera is received by embedded platform and decoded in real time in H.265 format. Then the real-time intelligent target detection and recognition algorithm basing on TensorRT technology is done for RGB data obtained by hardware decoding process. Finally, the data is compressed in H.265 format, and subsequently storage and data transmission are carried out. The experimental results show that TensorRT technology can improve the inference speed of neural network in embedded platform. The network structure optimized by TensorRT technology can achieve three times the speed increase, with limited accuracy loss. Hardware coding and decoding of H.265 can also cause corresponding delay to program inevitably.

[1]  Nouri Masmoudi,et al.  JEM-post HEVC vs. HM-H265/HEVC performance and subjective quality comparison based on QVA metric , 2018, 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[2]  Bocheng Liu,et al.  Implementation and optimization of intra prediction in H264 video parallel decoder on CUDA , 2012, 2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI).

[3]  Krzysztof Nowicki,et al.  Comparison Study of H.264/AVC, H.265/HEVC and VP9-Coded Video Streams for the Service IPTV , 2018, 2018 26th International Conference on Software, Telecommunications and Computer Networks (SoftCOM).

[4]  Paolo Bestagini,et al.  Video Codec Forensics Based on Convolutional Neural Networks , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[5]  Bo Chen,et al.  Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[7]  Rengan Xu,et al.  Deep Learning at Scale on NVIDIA V100 Accelerators , 2018, 2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS).

[8]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Bin Dong,et al.  Efficient Implementation of Convolutional Neural Networks with End to End Integer-Only Dataflow , 2019, 2019 IEEE International Conference on Multimedia and Expo (ICME).

[10]  Nan Zhang,et al.  Image parallel processing based on GPU , 2010, 2010 2nd International Conference on Advanced Computer Control.

[11]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[12]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[13]  Abhinav Gupta,et al.  Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Runqing Zhang,et al.  Object Detection and Tracking based on Recurrent Neural Networks , 2018, 2018 14th IEEE International Conference on Signal Processing (ICSP).

[15]  Yong Dou,et al.  Efficient parallel implementation of morphological operation on GPU and FPGA , 2014, Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC).

[16]  Anastasios Kourtis,et al.  Performance evaluation of H264/SVC streaming system featuring real-time in-network adaptation , 2011, 2011 IEEE Nineteenth IEEE International Workshop on Quality of Service.

[17]  Jian Sun,et al.  Deep Learning with Low Precision by Half-Wave Gaussian Quantization , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[20]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[21]  Qi Zhang,et al.  Real-time CPU based H.265/HEVC encoding solution with x86 platform technology , 2015, 2015 International Conference on Computing, Networking and Communications (ICNC).

[22]  Tanupriya Choudhury,et al.  Study on H.265/HEVC against VP9 and H.264 : On Space and Time Complexity for Codecs , 2018, 2018 International Conference on Communication, Computing and Internet of Things (IC3IoT).

[23]  Cong Hu,et al.  Deep learning application based on embedded GPU , 2017, 2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS).

[24]  Wei Liu,et al.  DSSD : Deconvolutional Single Shot Detector , 2017, ArXiv.

[25]  Jian Cheng,et al.  Quantized Convolutional Neural Networks for Mobile Devices , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Nouri Masmoudi,et al.  Statistical analysis on coding unit partition of HEVC encoded HD videos , 2016, 2016 International Image Processing, Applications and Systems (IPAS).

[28]  Shenghuo Zhu,et al.  Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM , 2017, AAAI.

[29]  Dongxiao Li,et al.  Feature Aligned Recurrent Network for Causal Video Object Detection , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[30]  Ayoub Al-Hamadi,et al.  Effects of Video Encoding on Camera-Based Heart Rate Estimation , 2019, IEEE Transactions on Biomedical Engineering.

[31]  2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, PMBS@SC 2018, Dallas, TX, USA, November 12, 2018 , 2018, PMBS@SC.