基于类人视觉的多任务交通目标实时检测模型

doi:10.19562/j.chinasae.qcgc.2021.01.007

Abstract

Abstract:

In view of that in complex traffic scenes the single model can't carry out unified detection of drivable region and traffic objects concurrently and the poor real?time performance of detection， a single?stage detection model for multi?task traffic object based on humanoid vision is proposed in this paper， achieving the unified detection of drivable region， vehicle and pedestrian concurrently in real time.Firstly， a humanoid vision attention mechanism is established for supervision and lightweight model MobileNetV3 is adopted as a framework. Then the idea of feature pyramid network （FPN） is utilized to detect drivable region. Finally， dynamic attention algorithm and the idea of anchor?free are used to detect traffic object. The experimental results show that the attention mechanism of driver's eyes introduced obviously enhance the accuracy and robustness of the model and the average calculation speed of the model in real vehicle reaches 12 f/s.

Key words: humanoid vision, attention mechanism, anchor?free, traffic scene detection

Jun Liu,Lanlei Li Hanbing Chen. A Real⁃time Detection Model for Multi⁃task Traffic Objects Based on Humanoid Vision[J].Automotive Engineering, 2021, 43(1): 50-58.

Figures/Tables 15

模型	骨架网络	参数量	模型大小/MB	AP₅₀/%	F-值/%	所需时间/ms
YOLOv3^[11]	DarkNet-53	61 587 112	235	91.91	86.89	42.32
SSD^[10]	ResNet-101	27 188 676	103	89.88	84.33	48.87
Mask R-CNN^[9]	ResNeXt-101-FPN	132 257 325	542	92.32	87.12	50.38
FCO $S [12]$	ResNet-101-FPN	112 036 407	427	88.77	85.76	42.89
本文	MobileNetV3-DAN	9 758 992	37.4	91.12	86.94	33.91

References 24

1	LIU J， ZHANG R. Vehicle detection and ranging using two diffe-rent focal length cameras ［EB/OL］. ［2020-03-20］. .
2	WANG Z， REN W， QIU Q. LaneNet： real-time lane detection networks for autonomous driving［EB/OL］. ［2018-07-04］. .
3	LI W， ZHU X， GONG S. Person re-identification by deep joint learning of multi-loss classification［EB/OL］. ［2017-05-12］. .
4	ZHANG J， HUANG M， JIN X， et al. A real-time chinese traffic sign detection algorithm based on modified yolov2［J］. Algorithms，2017， 10（4）：127.
5	王政军. 基于深度学习的智能驾驶目标及可行驶区域检测研究［D］. 长春：吉林大学，2019.
	WANG Z. Research on object and free space detection of intelligent driving based on deep learning［D］. Changchun：Jilin University， 2019.
6	SADEGHIAN A， ALAHI A， SAVARESE S. Tracking the untrackable： learning to track multiple cues with long-term dependencies ［EB/OL］. ［2017-01-08］. .
7	刘军，后士浩，张凯，等. 基于单目视觉车辆姿态角估计和逆透视变换的车距测量［J］. 农业工程学报，2018，34（13）：70-76.
	LIU J， HOU S， ZHANG K， et al. Vehicle distance measurement with implementation of vehicle attitude angle estimation and inverse perspective mapping based on monocular vision［J］. Transactions of the Chinese Society of Agricultural Engineering （Transactions of the CSAE），2018，34（13）：70-76.
8	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（6）：1137.
9	HE K， GKIOXARI G， DOLLAR P， et al. Mask R-CNN ［EB/OL］. ［2017-03-20］. .
10	LIU W， ANGUELOV D， ERHAN D， et al. SSD： single shot multibox detector ［C］. Proc of European Conference on Computer Vision， 2016：21-37.
11	REDMON J， FARHADI A. YOLOv3： an incre-mental improvement ［EB/OL］. ［2018-04-08］. .
12	TIAN Z， SHEN C， CHEN H， et al. FCOS： fully convolutional one-stage object detection［EB/OL］. ［2019-04-02］. .
13	LONG J， SHELHAMER E， DARRELL T. Fully convolutional networks for semantic segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，39（4）：640-651.
14	BADRINARAYANAN V， KENDALL A， CIPOLLA R. SegNet： a deep convolutional encoder-decoder architecture for image segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（12）：2481-2495.
15	RONNEBERGER O， FISCHER P， BROX T. U-Net： convolutio-nal networks for biomedical image segmentation［EB/OL］. ［2015-05-18］. .
16	HOWARD A， SANDLER M， CHU G， et al. Searching for MobileNetV3［EB/OL］. ［2019-11-20］. .
17	王文冠，沈建冰，贾云得. 视觉注意力检测综述［J］. 软件学报，2019，30（2）：416-439.
	WANG W， SHEN J， JIA Y. Review of visual attention detection［J］. Journal of Software，2019，30（2）：416-439.
18	IANDOLA F N， HAN S， MOSKEWICZ M W， et al. SqueezeNet： alexnet-level accuracy with 50x fewer parameters and <0.5MB model size［EB/OL］. ［2016-02-24］. .
19	HOWARD A G， ZHU M， CHEN B， et al. MobileNets： efficient convolutional neural networks for mobile vision applications［EB/OL］. ［2017-04-17］. .
20	SANDLER M， HOWARD A， ZHU M， et al. MobileNetV2： inverted residuals and linear bottlenecks［EB/OL］. ［2018-01-13］. .
21	TAN M， CHEN B， PANG R， et al. MnasNet： platform-aware neural architecture search for mobile［EB/OL］. ［2018-06-31］. .
22	SHI X， CHEN Z， WANG H， et al. Convolutional LSTM network： a machine learning approach for precipitation nowcasting［EB/OL］. ［2015-06-13］. .
23	LIN T Y， DOLLAR P， GIRSHICK R， et al. Feature pyramid networks for object detection［C］. Proc of IEEE Conference on Computer Vision and Pattern Recognition，2017：936-944.
24	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： unified， real-time object detection［C］. Proc of IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.

[1]	XU Cheng-Shan, JIANG Fa-Chao, SONG Sen-Nan, TIAN Guang-Yu. [J]. , 2017, 39(1): 9 -14 .
[2]	ZHANG Yi-Bing, 吕Jian-Jun , YUAN Guang-Hui. [J]. , 2016, 38(12): 1467 -1470 .
[3]	JIA Ji-De, WU Chun-Zhi, JIA Xiang-Yu, REN Gang, HAN Jia-Jia. [J]. , 2017, 39(1): 97 -101 .
[4]	RONG Bing, XIAO Pan, ZHOU Jian-Wen, LIU Yi-Lu. [J]. , 2017, 39(2): 214 -219 .
[5]	WANG Zhen, CUI Ya-Hui-.Liu-Kai, XU Lin. [J]. , 2017, 39(3): 304 -310 .
[6]	GUAN Xin, XU Liang, GUO Rui, WANG Bo, SONG Hai-Yan. [J]. , 2017, 39(3): 311 -316 .
[7]	JIN Geng-Ri, GUAN Xin, ZHAN Jun, GUO Rui. [J]. , 2017, 39(3): 364 -368 .
[8]	XIONG Xing-Wang, GAO Jun-Hua, ZHOU Tao, YU Jin-Tao. [J]. , 2017, 39(4): 381 -385 .
[9]	CAO Li-Feng, ZHOU Shou-Qin, XIE Xiao-Peng. [J]. , 2017, 39(4): 401 -406 .
[10]	Chen Wenqiang, Xiong Hui, Li Keqiang, Li Xiaofei& Zhang Dezhao. Concurrent Pedestrian and Cyclist Detection Based on Deep Neural Networks[J]. , 2018, 40(6): 726 .

数据增强	组归一化	人眼注意力监督	动态注意力算法		距离交并比	中心性	mAP/%
数据增强	组归一化	人眼注意力监督	conv LSTM	FPN	距离交并比	中心性	mAP/%
√				√			48.64
√				√	√		50.17(+1.53)
√				√	√	√	51.44(+1.27)
	√			√	√	√	52.49(+1.05)
	√	√	√	√	√	√	56.09(+3.60)
√	√	√	√	√	√	√	56.88(+0.79)

A Real⁃time Detection Model for Multi⁃task Traffic Objects Based on Humanoid Vision

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 24

Related Articles 7

Metrics

Comments

Recommended 10

[1]	Yongtao Li,Chenxu Sun,Weiguang Zheng,Enyong Xu,Yufang Li,Shanchao Wang. Collision Warning Based on Fusion of Millimeter Wave Radar and Vision [J]. Automotive Engineering, 2023, 45(9): 1666-1676.
[2]	Xia Zhao,Zhao Li,Rui Fu,Zhenzhen Ge,Chang Wang. Real-Time Detection of Distracted Driving Behavior Based on Deep Convolution-Tokens Dimensionality Reduction Optimized Visual Transformer Model [J]. Automotive Engineering, 2023, 45(6): 974-988.
[3]	Linhui Li,Xinliang Zhang,Yifan Fu,Jing Lian,Jiaxu Ma. Research on Visible Light and Infrared Post-Fusion Detection Based on TC-YOLOv7 Algorithm [J]. Automotive Engineering, 2023, 45(12): 2280-2290.
[4]	Long Chen,Chen Yang,Yingfeng Cai,Hai Wang,Yicheng Li. Pedestrian Crossing Intention Prediction Method Based on Multimodal Feature Fusion [J]. Automotive Engineering, 2023, 45(10): 1779-1790.
[5]	Xiaojun Zhang,Jingzhe Xi,Yanlei Shi,Anlu Yuan. Lightweight YOLOv7-R Algorithm for Road-Side View Target Detection [J]. Automotive Engineering, 2023, 45(10): 1833-1844.
[6]	Dafang Wang,Hai Shang,Jiang Cao,Tao Wang,Xiangteng Xia,Yulin Han. Semantic Segmentation Method of Point Cloud in Automatic Driving Scene Based on Self-attention Mechanism [J]. Automotive Engineering, 2022, 44(11): 1656-1664.
[7]	Cai Yingfeng, Tai Kangsheng, Wang Hai, Li Yicheng, Chen Long. Research on Behavior Recognition Algorithm of Surrounding Vehicles for Driverless Car [J]. Automotive Engineering, 2020, 42(11): 1464-1472.