3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems

Lin, Chunmian; Duan, Xuting; Zhou, Jianshan

doi:10.23919/csms.2021.0004

Cited by 8 publications

(5 citation statements)

References 28 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the studies of environmental factors, Zhu et al [34] applied computational experiments to evaluate the impact of traffic signal control systems. In another paper, Zhu [35] also analyzed the impact of accident and weather with the same technique. Lin et al [36] studied 3D-environment perception for automatic driving test through simulation system.…”

Section: Relevant Studies Of Computational Experimentsmentioning

confidence: 99%

An Evolutionary Adaptive System for Prediction of Strategy Influence: A Case Study of Government Regulation Guided Brand Innovation

Lin

et al. 2022

Complex Syst. Model. Simul.

View full text Add to dashboard Cite

Decision making is one of the common human activities. But in complex, interactive, and dynamic systems, it is extremely important to make decisions scientifically because the influence of the behavior after decision making is generally irreversible. The predictability of behavior influence is an effective way to improve the scientific decision making. As a new branch of computing, computational experiment is an emerging management method for research on complex systems. In this paper, based on particle swarm intelligence, an evolutionary adaptive system model of brand innovation in the toy industry cluster is constructed. By imitating the evolution process of the complex adaptive system, this method is helpful to analyze the impact of the management behavior brought to simulation system, predict the management behavior in real world, and finally choose the best management strategy. This simulation tried to figure out the affection of government regulation strategies and provide corresponding assessments and recommendations, which gives a new solution to assist the government to effectively judge the influence of the macro policy, as well as provides a new way of thinking of the related intelligent decision making.

show abstract

Section: Relevant Studies Of Computational Experimentsmentioning

confidence: 99%

An Evolutionary Adaptive System for Prediction of Strategy Influence: A Case Study of Government Regulation Guided Brand Innovation

Lin

et al. 2022

Complex Syst. Model. Simul.

View full text Add to dashboard Cite

show abstract

“…Several research results have been achieved and significant breakthroughs have been made in the field of 2D image compression and perception, and it has been investigated that compression and perception techniques are also applicable to the case where the transmitted data is high‐dimensional. On this basis, the CS of 3D and even higher dimensional data has received extensive attention, the most famous of which are video CS and hyperspectral image CS (HSICS) 39 . This part will introduce the relevant literature from the basic theory and the challenge of 3D data reconstruction algorithm of CS.…”

Section: Background and Basic Theorymentioning

confidence: 99%

“…On this basis, the CS of 3D and even higher dimensional data has received extensive attention, the most famous of which are video CS and hyperspectral image CS (HSICS). 39 This part will introduce the relevant literature from the basic theory and the challenge of 3D data reconstruction algorithm of CS.…”

Section: Background and Basic Theorymentioning

confidence: 99%

Survey on compressed sensing reconstruction method for 3D data

Zhang

Xie

2022

Concurrency and Computation

View full text Add to dashboard Cite

The information society has higher and higher requirements for the collection, transmission and storage of digital signals, and signal utilization efficiency has become an increasingly important part of the digital signal processing process. The traditional digital signal processing needs to satisfy the Nyquist sampling theorem to ensure the restoration of the signal, while the digital signal processing method based on compressed sensing can sample and reconstruct the signal under the conditions that much lower than the Nyquist sampling theorem. Undoubtedly, the utilization efficiency of digital signals has been greatly accelerated. In this article, taking hyperspectral images and videos as examples, we review the basic theory, reconstruction model, and reconstruction algorithm of 3D data compressed sensing. We analyze, summarize, and discuss the existing literature. Finally, the research status of compressive sensing reconstruction methods for hyperspectral images and videos is compared, and several important research directions for compressive sensing reconstruction of 3D data in the future are proposed.

show abstract

“…There is a spectrum of benchmarks publicly-available for single-vehicle perception, e.g., KITTI [15], nuScenes [16], Waymo [17], etc., with synchronous calibration and finegrained annotation. In the context of multi-agent perception, it is of particular interest for data simulation due to costly acquisition and labeling [18]. For instance, V2V-Sim [14] builds a group of new scenarios from the real-world collections based on a self-driving LiDAR simulation [19], and however, both of them are not released.…”

Section: Introductionmentioning

confidence: 99%

V2VFormer: Vehicle-to-Vehicle Cooperative Perception With Spatial-Channel Transformer

Lin,

Tian,

Duan

et al. 2024

IEEE Trans. Intell. Veh.

Self Cite

View full text Add to dashboard Cite

Collaborative perception aims for a holistic perceptive construction by leveraging complementary information from nearby connected automated vehicle (CAV), thereby endowing the broader probing scope. Nonetheless, how to aggregate individual observation reasonably remains an open problem. In this paper, we propose a novel vehicle-to-vehicle perception framework dubbed V2VFormer with Transformer-based Collaboration (CoTr). Specifically. it re-calibrates feature importance according to position correlation via Spatial-Aware Transformer (SAT), and then performs dynamic semantic interaction with Channel-Wise Transformer (CWT). Of note, CoTr is a light-weight and plugin-play module that can be adapted seamlessly to the off-theshelf 3D detectors with an acceptable computational overhead. Additionally, a large-scale cooperative perception dataset V2V-Set is further augmented with a variety of driving conditions, thereby providing extensive knowledge for model pretraining. Qualitative and quantitative experiments demonstrate our proposed V2VFormer achieves the state-of-the-art (SOTA) collaboration performance in both simulated and real-world scenarios, outperforming all counterparts by a substantial margin. We expect this would propel the progress of networked autonomousdriving research in the future.

show abstract

3D Environmental Perception Modeling in the Simulated Autonomous-Driving Systems

Cited by 8 publications

References 28 publications

An Evolutionary Adaptive System for Prediction of Strategy Influence: A Case Study of Government Regulation Guided Brand Innovation

An Evolutionary Adaptive System for Prediction of Strategy Influence: A Case Study of Government Regulation Guided Brand Innovation

Survey on compressed sensing reconstruction method for 3D data

V2VFormer: Vehicle-to-Vehicle Cooperative Perception With Spatial-Channel Transformer

Contact Info

Product

Resources

About