A5015473075- Autonomous Vehicle Technology and Safety
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Traffic and Road Safety
- Electric and Hybrid Vehicle Technologies
- Traffic Prediction and Management Techniques
- Electric Vehicles and Infrastructure
- Robotics and Sensor-Based Localization
- Automated Road and Building Extraction
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Vehicle License Plate Recognition
- Vehicle emissions and performance
- Advanced Battery Technologies Research
- Web visibility and informetrics
- EEG and Brain-Computer Interfaces
- 3D Surveying and Cultural Heritage
- Industrial Vision Systems and Defect Detection
- Smart Grid Energy Management
- Advanced Text Analysis Techniques
- Neurobiology of Language and Bilingualism
- Remote Sensing in Agriculture
- Reading and Literacy Development
- Advanced Computational Techniques and Applications
- Currency Recognition and Detection
Beijing Institute of Technology
2022-2025
Beijing Language and Culture University
2023
Tsinghua University
2023
North China University of Technology
2016
Utilizing infrastructure and vehicle-side information to track forecast the behaviors of surrounding traffic participants can significantly improve decision-making safety in autonomous driving. However, lack real-world sequential datasets limits research this area. To address issue, we introduce V2X-Seq, first large-scale V2X dataset, which includes data frames, trajectories, vector maps, lights captured from natural scenery. V2X-Seq comprises two parts: perception more than 15,000 frames 95...
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, temporal asynchrony limited wireless communication in traffic environments lead to fusion misalignment impact detection performance. This paper proposes Feature Flow Net (FFNet), a novel cooperative framework that uses feature flow prediction module address these issues vehicle-infrastructure 3D object detection. Rather than transmitting maps...
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, the uncertain temporal asynchrony limited communication conditions lead to fusion misalignment constrain exploitation of data. To address these issues in vehicle-infrastructure cooperative 3D (VIC3D) object detection, we propose Feature Flow Net (FFNet), a novel detection framework. FFNet is flow-based feature framework that uses flow prediction...
Change detection is an important task in remote sensing imagery which has seen tremendous advances recent years with the progress of deep neural networks. Although Convolutional Neural Network (CNN) and Transformer-based methods work sufficiently well, building specificity usually less considered to contribute performance improvement. In this letter, we propose a global specific high-frequency cues guidance network for change detection, called GSHF-Net. More specifically, extraction module...
In recent years, the pervasive deployment and progression of autonomous driving technology have engendered heightened demands, particularly within intricate campus surrounding environments frequently traversed by delivery vehicles, such as automated food courier services. Accurately predicting pedestrian trajectories is paramount in realm driving. face complex scenarios environments, traditional trajectory prediction methods failed to achieve satisfactory results. To address this challenge...
Abstract Studies on sentence processing in inflectional languages support that syntactic structure building functionally precedes semantic processing. Conversely, most EEG studies of Chinese do not the priority syntax. One possible explanation is language lacks morphological inflections. Another may be presentation separate components individual screens disrupts framework construction during reading. The present study investigated this using a self-paced reading experiment mimicking rapid...
Motion forecasting is an essential task for autonomous driving, and the effective information utilization from infrastructure other vehicles can enhance motion capabilities. Existing research have primarily focused on leveraging single-frame cooperative to limited perception capability of ego vehicle, while underutilizing interaction traffic participants observed devices. In this paper, we first propose trajectory representations learning paradigm. Specifically, present V2X-Graph,...
This paper uses scientometrics method of knowledge mapping domains, on the basis CAJD database, summarizes and analyses discipline structure "Teaching Chinese as a Second Language (TCSL)". It introduces analysis to research area Teaching .It shows how present overview hot spots subject intuitively visually by analyzing keywords frequency co-words.
Utilizing infrastructure and vehicle-side information to track forecast the behaviors of surrounding traffic participants can significantly improve decision-making safety in autonomous driving. However, lack real-world sequential datasets limits research this area. To address issue, we introduce V2X-Seq, first large-scale V2X dataset, which includes data frames, trajectories, vector maps, lights captured from natural scenery. V2X-Seq comprises two parts: perception more than 15,000 frames 95...
Recent advances in 3D object detection rely heavily on the representation of data. Several high-performance detectors a point-based structure as it preserves precise point positions. However, point-level features incur high computation overheads due to unordered storage. Conversely, voxel-based is better suited for feature extraction but often results slow inference times interaction between points and voxels can be time-consuming. In this work, we propose new cloud framework that...
Battery state estimation is always a crucial issue on electric vehicles (EVs), where the state-of-health (SOH) and state-of-charge (SOC) are especially important. Given that, strategy proposed for vehicular power batteries in this paper. The cloud platform connected with vehicle terminal under Cyber-Physical System (CPS) architecture. On platform, SOH implemented long short-term memory (LSTM) algorithm, extracting three features from discharging processes as inputs of LSTM model. terminal,...