Research on multi-task convolutional neural network facing to AR-HUD

被引：0

作者：

Feng M. ^{[1
]}

Bu C. ^{[1
]}

Xiao H. ^{[1
]}

机构：

[1] College of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing

来源：

Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2021年 / 42卷 / 03期

关键词：

Augmented reality-head up display(AR-HUD); Multi-task convolutional neural network; Semantic segmentation; Target detection;

D O I：

10.19650/j.cnki.cjsi.J2107395

中图分类号：

学科分类号：

摘要：

AR-HUD has been widely used in automobile. Its environment perception module needs to complete target detection, lane segmentation and other tasks, but multiple deep neural networks running at the same time will consume too much computing resources. In order to solve this problem, a lightweight multi-task convolutional neural network (DYPNet) applied in AR-HUD environment perception is proposed in this paper. DYPNet is based on YOLOv3-tiny framework, and fuses the pyramid pooling model, DenseNet dense connection structure and CSPNet network model, which greatly reduces the computing resources consumption without reducing the accuracy. Aiming at the problem that the neural network is difficult to train, a linear weighted sum loss function based on dynamic loss weight is proposed, which makes the loss of the sub-networks tend to decline and converge synchronously. After training and testing on the open data set BDD100K, the results show that the detection mAP and segmentation mIOU of the neural network are 30% and 77.14%, respectively, and after accelerating with TensorRt, it can reach about 15 FPS on Jetson TX2, which has met the application requirements of AR-HUD. It has been successfully applied to the vehicle AR-HUD. © 2021, Science Press. All right reserved.

引用

页码：241 / 250

页数：9

共 29 条

[21]

RUDER S., An overview of multi-task learning in deep neural networks, (2017)

[22]

DUONG L, COHN T, BIRD S, Et al., Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser, Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL) and the 7th International Joint Conference on Natural Language Processing (IJCNLP), pp. 845-850, (2015)

[23]

HUANG G, LIU Z, VAN DER MAATEN L, Et al., Densely connected convolutional networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700-4708, (2017)

[24]

ZHAO H, SHI J, QI X, Et al., Pyramid scene parsing network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881-2890, (2017)

[25]

LIN T Y, DOLLAR P, GIRSHICK R, Et al., Feature pyramid networks for object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117-2125, (2017)

[26]

REDMON J, FARHADI A., Yolov3: An incremental improvement, (2018)

[27]

GIRSHICK R., Fast R-CNN, Proceedings of the IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)

[28]

REN S Q, HE K M, GIRSHICK R, Et al., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions on Pattem Analysis & Machine Intelligence, 39, 6, pp. 1137-1149, (2017)

[29]

CHEN P, TANG Y P, HE X, Et al., Detection method of vehicle fake license plate based on multi-task Faster R-CNN, Chinese Journal of Scientific Instrument, 38, 12, pp. 3079-3089, (2017)

← 1 2 3 →