Design and Implementation of Driverless Perceptual System Based on CPU + FPGA

Nowadays, autonomous driving is one of the most popular technologies and is in a stage of rapid development. In the process of working, autonomous vehicles need to locate, perceive, predict and plan. The enormous amount of calculation results high energy consumption. In response to the characteristics of unmanned driving, a high performance, low power consumption and high flexibility unmanned visual perception system was developed using a heterogeneous platform of CPU+FPGA. The heterogeneous platform has the advantages of parallel processing and field programmable, etc. The system can improve the YOLOv3(You Only Look Once) algorithm of the deep neural network for target detection recognition, the Soft-NMS (Non maximum suppression) algorithm is added to the original YOLOv3 algorithm framework, and then the target detection false detection rate and missed detection rate are minimized through the frame regression operation, and finally we train data and test the network. the experimental results show that the system can quickly and accurately identify the target in different complex scenes, and the power consumption is low.

[1]  Hao Chen,et al.  Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss , 2018, IJCAI.

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

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Eduardo Mario Nebot,et al.  Track-based self-supervised classification of dynamic obstacles , 2010, Auton. Robots.

[6]  Yuning Jiang,et al.  Acquisition of Localization Confidence for Accurate Object Detection , 2018, ECCV.

[7]  Monson H. Hayes,et al.  A Novel Lane Detection System With Efficient Ground Truth Generation , 2012, IEEE Transactions on Intelligent Transportation Systems.

[8]  Peter Kontschieder,et al.  The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[9]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  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.

[11]  Ruigang Yang,et al.  The ApolloScape Dataset for Autonomous Driving , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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