Di Cao

Di Cao

Auto-generated profile, based on publicly available information

Di Cao

School of Computer Science and Technology, Zhejiang University of Technology, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2013
Verified
Conference Paper
Closed access
DCDi Cao
Di Cao
JYJinfeng Yang
Jinfeng Yang
YSYihua Shi
Yihua Shi
CXChenghua Xu
Chenghua Xu
A new finger-vein image matching method based on structure feature is proposed in this paper. To describe the finger-vein structures conveniently, the vein skeletons are firstly extracted and used as the primitive information. Based on the skeletons, a curve tracing scheme depended on junction points is proposed for curve segment extraction. Next, the curve segments are encoded piecewise using a modified included angle chain, and the structure feature code of a vein network are generated sequentially. Finally, a dynamic scheme is adopted for structure feature matching. Experimental results show that the proposed method perform well in improving finger-vein matching accuracy.

7 April 2022 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
TWTianxiao Wang
Tianxiao Wang
HWHao Wu
Hao Wu
QLQiang Li
Qiang Li
SNShaoquan Ni
Shaoquan Ni
TQTinghui Qin
Tinghui Qin
DCDi Cao
Di Cao
Profound understanding of an interaction mechanism among influencing factors in the perspective of urban road traffic operation is of great significance for scientific and effective urban congestion management. In this paper, 6 indicators are proposed for the road traffic operation in the aspects of average speed of road sections, regional traffic index, and number of traffic incidents. Based on this, 4 major influencing factors and 12 measurable subinfluencing factors are proposed according to urban traffic supply and demand, and the SEM (structural equation model) is established to find out their interaction mechanism. And then, several sets of local traffic data collected in Shenzhen are used for model fitting, validation, and path analysis. The mathematical results show that all 6 indicators affiliated to the road traffic operation have a good explanation when it comes to the change of operation status. Among 4 latent variables in the traffic supply and demand aspect, the service equipment operation level and control equipment operation level can positively influence the road traffic operation status, while the urban traffic demand plays a negative role. Complex interactions among four latent variables are further pointed out. Finally, on the basis of the path coefficient relationship among the influencing factors, scientific suggestions and guidance are provided for urban road management control.

4 November 2022
Verified
Conference Paper
Open access
ZGZhenghao Gu
Zhenghao Gu
YLYanjing Lei
Yanjing Lei
SCSixian Chan
Sixian Chan
DCDi Cao
Di Cao
HZHongkai Zhang
Hongkai Zhang
With the increasing urbanization and the popularity of traffic video surveillance, and the rapid development of object detection algorithms, object detection of traffic events through video analysis has become possible. This paper proposes the design and implementation of a traffic event detection system based on video analysis. Firstly, the video stream is processed, mainly for video access and display, and the compression of neural networks achieves the network acceleration. Secondly, the structured information of vehicles is obtained by nighttime vehicle detection and joint detection and tracking. Finally, the car's driving behavior is analyzed through video calibration and video analysis. The system has been used online in many places in China and has achieved remarkable results.

4 November 2022
Verified
Conference Paper
Open access
ZGZhenghao Gu
Zhenghao Gu
YLYanjing Lei
Yanjing Lei
DCDi Cao
Di Cao
LZLue Zhan
Lue Zhan
Most of the existing trackers have high performance and good effect, but it is difficult to have fast speed and can not meet the real-time requirements. Therefore, the development of target tracking system with high accuracy and good robustness has become an urgent task for researchers. This paper proposes to add an Region Proposal Network (RPN) module based on the structure of the traditional Siamese Network (SiamFC), calculate the template and branch of the Siamese sub network in advance in the reasoning stage, and decompose the tracking task into task nodes that are detected first and then matched for real-time online tracking. The experimental results on VOT2015, VOT2018 and OTB2015 data sets show that compared with other trackers, the model based on SiamRPN proposed in this paper shows better performance in achieving the dual goals of high accuracy and low robustness.