Robust dual-modal image quality assessment aware deep learning network for traffic targets detection of autonomous vehicles

Geng, Keke; Huang, Wenhan

doi:10.1007/s11042-022-11924-1

Cited by 16 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These systems coordinate the different power components [104][105][106][107][108]. System processing is quick and network administration is easy under these conditions [109][110][111][112][113].…”

Section:  mentioning

confidence: 99%

Resiliency-Constrained Placement and Sizing of Virtual Power Plants in the Distribution Network Considering Extreme Weather Events

Zadehbagheri,

Pirouzi,

Dehghan

et al. 2024

Preprint

View full text Add to dashboard Cite

The placement and scale of virtual power plants (VPPs) in distribution networks are the only topics covered in this article that pertain to the resilience of the grid to severe weather. This problem is framed as a two-objective optimization, where the predicted energy that the network would not deliver in the case of an earthquake or flood, and the annual planning cost of the VPP, are the two objective functions to be reduced. The constraints include the formula for VPP planning, limitations on network operation and resilience, and equations for AC power flow. Uncertainties about demand, renewable power, energy prices, and the supply of network hardware and VPP components are all taken into account in stochastic programming. The proposed technique achieves a single-objective formulation in the subsequent stage by the use of a Pareto optimization strategy based on the ε-constraint method. This article uses a solver based on a hybrid of Crow search algorithm (CSA) and sine cosine algorithm (SCA) to achieve the trustworthy optimal solution with lowest dispersion in the final response. In order to tackle the problem, the proposed system looks at how the VPP affects network resilience, scales it, and combines it with the hybrid evolutionary algorithm. In the end, the numerical findings verify that the optimal placement and dimensions of VPPs help to improve the operational, financial, and resilience status of the distribution network by applying the proposed problem to a 69-bus distribution network.

show abstract

Section:  mentioning

confidence: 99%

Resiliency-Constrained Placement and Sizing of Virtual Power Plants in the Distribution Network Considering Extreme Weather Events

Zadehbagheri,

Pirouzi,

Dehghan

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Objective function includes min (max) term to calculate minimum (maximum) value of this function [65][66][67][68][69][70]. It expresses as single or multi-objective function [71][72][73][74][75][76]. Optimization problem includes the different constraints [77][78][79][80][81].…”

Section: Formulation Of the Ibvpp Operationmentioning

confidence: 99%

Energy management of distribution network with inverter‐based renewable virtual power plant considering voltage security index

Azarhooshang,

Rezazadeh

2023

IET Renewable Power Gen

View full text Add to dashboard Cite

Virtual power plants (VPP) with resources and storages are able to control the active power of the network. They are also connected to the network through an inverter, which is capable of controlling reactive power. Therefore, it is expected that the optimal use of inverter‐based VPP can play an effective role in improving the economic and technical status of the distribution network. So, the operation of a smart distribution system is presented in this paper by considering inverter‐based VPPs constrained to the operator's measures. The weighted sum of expected energy loss (EEL) and voltage security index (VSI) is minimized while considering AC optimal power flow equations, restrictions of network's security, and operating model of the inverter‐based VPPs. Uncertainties with an origin of the amount of demand, renewable energy, and parameters of mobile energy storage are also discussed. The uncertainties are modelled using a stochastic optimization approach relying on the unscented transformation (UT). Evaluating inverter‐based VPP performance, providing models of flexible resources such as responsive loads and mobile storages, checking network voltage security status, and modelling uncertainties using the UT method are among the innovations of this study. According to the results, it is demonstrated that the technical situation of the distribution system is improved with the help of optimal management of the VPP. With energy management of the inverter‐based VPP, the suggested design has succeeded to enhance the operating status (voltage security) of the system by approximately 33–73% (12%) in comparison to power flow studies.

show abstract

“…w T X T Xw (10) The maximum amount in brackets in the formula is Rayleigh entropy. The corresponding w is the maximum feature vector of X T X.…”

Section: Model Constructionmentioning

confidence: 99%

“…Target recognition in the traffic environment is achieved by dual-mode image quality aware deep neural network based on image RGB and laser radar sensing data [9]. Target recognition in the road traffic environment is based on video target detection technology YOLOv4 and improved recognition accuracy by cutting-edge network model [10]. In our study, YOLOv5 is selected for target detection of the road traffic environment, and the target object data are extracted through the target object feature RGB.…”

Section: Introduction 1backgroundmentioning

confidence: 99%

Quantitative Study on Road Traffic Environment Complexity under Car-Following Condition

Liu

Chen

et al. 2022

Sustainability

View full text Add to dashboard Cite

With the development of the drive of electronic communication technology, the driving assistance system that perceives the external traffic environment has developed rapidly. However, when quantifying the complexity of the road traffic environment without fully considering the driving characteristics and subjective feelings, the false alarm rate of the driving warning system increases and affects the early warning effect. In order to more accurately quantify the complexity of the road traffic environment, we analyzed the impact of road traffic environment changes on drivers under the condition of car-following. Firstly, we selected the influencing factors of the traffic environment complexity, such as the driving operation indicators, the vehicle driving status indicators and the road environmental indicators. The weight calculation model of each influence factor is established based on the principal component analysis method. Secondly, the driver’s reaction time during car-following is used as the quantitative index of road traffic environment complexity. The quantitative model of road traffic environment complexity is constructed combined with the weight of road traffic environment complexity. Finally, the driving simulation experiment is designed to verify the complexity quantification model of the road traffic environment. The road traffic environment complexity value calculated in our study is better than the TTC, and the early-warning threshold is raised by 2–5%. The research conclusion can provide a basis for the design of the car alarm system.

show abstract

Robust dual-modal image quality assessment aware deep learning network for traffic targets detection of autonomous vehicles

Cited by 16 publications

References 33 publications

Resiliency-Constrained Placement and Sizing of Virtual Power Plants in the Distribution Network Considering Extreme Weather Events

Resiliency-Constrained Placement and Sizing of Virtual Power Plants in the Distribution Network Considering Extreme Weather Events

Energy management of distribution network with inverter‐based renewable virtual power plant considering voltage security index

Quantitative Study on Road Traffic Environment Complexity under Car-Following Condition

Contact Info

Product

Resources

About