|
Igor Lashkov I'm a Postdoctoral Scholar at the University of Hawaiʻi at Mānoa. I did my PhD at St. Petersburg Federal Research Center of the RAS. |
|
ResearchMy research interests include computer vision, deep learning, advanced driver assistance systems, intelligent transportation systems, and connected vehicle applications. Some papers are highlighted. |
|
Context-Aware Prompt-Guided Learning-Free VLM-based Framework for Short Video Understanding in Traffic Accident Detection
Igor Lashkov, Shanglian Zhou, Nathan Li, Guohui Zhang ICCV Workshop SVU, 2025 (Poster Presentation) workshop page A context-based prompt-guided training-free VLM framework for efficient video inference in a fast-motion traffic scene environment. |
|
Optimized long short-term memory network for LiDAR-based vehicle trajectory prediction through bayesian optimization
Shanglian Zhou, Igor Lashkov, Hao Xu, Guohui Zhang, Yin Yang IEEE Transactions on Intelligent Transportation Systems, 2024 IEEExplore A systematic approach for LiDAR-based vehicle trajectory prediction, leveraging LSTM networks to predict vehicle trajectories and employing Bayesian optimization to automatically search for optimal hyperparameter values related to both the training scheme and LSTM architectures. |
|
Edge-computing-empowered vehicle tracking and speed estimation against strong image vibrations using surveillance monocular camera
Igor Lashkov, Runze Yuan, Guohui Zhang IEEE Transactions on Intelligent Transportation Systems, 2023 IEEExplore An effective approach to traffic flow monitoring under daytime conditions by applying machine learning and computer vision techniques to extract motion traffic data parameters from the videos captured by the static surveillance camera installed and fixed at the intersection. |
Miscellanea |
Recorded Talks |
Image Matching Challenge, 2024, 1st place |
|
Source code from Jon Barron template. |