A5048398929- Advanced Vision and Imaging
- Autonomous Vehicle Technology and Safety
- Evacuation and Crowd Dynamics
- Robotics and Sensor-Based Localization
- Image Enhancement Techniques
- Robotic Path Planning Algorithms
- Optical measurement and interference techniques
- Smart Agriculture and AI
- Human-Automation Interaction and Safety
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- 3D Surveying and Cultural Heritage
- Reinforcement Learning in Robotics
Skolkovo Institute of Science and Technology
2022-2023
Deep convolutional neural networks are highly efficient for computer vision tasks using plenty of training data. However, there remains a problem small datasets. For addressing this the pipeline which handles rare object types and an overall lack data to build well-performing models that provide stable predictions is required. This article reports on comprehensive framework <i>XtremeAugment</i> provides easy, reliable, scalable way collect image datasets efficiently label augment collected...
We present a dataset of 1000 video sequences human portraits recorded in real and uncontrolled conditions by using handheld smartphone accompanied an external high-quality depth camera. The collected contains 200 people captured different poses locations its main purpose is to bridge the gap between raw measurements obtained from downstream applications, such as state estimation, 3D reconstruction, view synthesis, etc. sensors employed data collection are smartphone's camera Inertial...
This work is dedicated to the study of how uncertainty estimation human motion prediction can be embedded into constrained optimization techniques, such as Model Predictive Control (MPC) for social robot navigation. We propose several cost objectives and constraint functions obtained from predicting pedestrian positions related probability collision that applied MPC, all different variants are compared in challenging scenes with multiple agents. The main question this paper tries answer is:...
This work is dedicated to the study of how uncertainty estimation human motion prediction can be embedded into constrained optimization techniques, such as Model Predictive Control (MPC) for social robot navigation. We propose several cost objectives and constraint functions obtained from predicting pedestrian positions related probability collision that applied MPC, all different variants are compared in challenging scenes with multiple agents. The main question this paper tries answer is:...
We present a dataset of 1000 video sequences human portraits recorded in real and uncontrolled conditions by using handheld smartphone accompanied an external high-quality depth camera. The collected contains 200 people captured different poses locations its main purpose is to bridge the gap between raw measurements obtained from downstream applications, such as state estimation, 3D reconstruction, view synthesis, etc. sensors employed data collection are smartphone's camera Inertial...