Neural Implicit Event Generator for Motion Tracking

We present a novel framework of motion tracking from event data using implicit expression. Our framework uses pre-trained event generation MLP called the implicit event generator (IEG) and carries out motion tracking by updating its state (position and velocity) based on the difference between the observed event and generated event from the current state estimation. The difference is computed implicitly by the IEG. Unlike the conventional explicit approach, which requires dense computation to evaluate the difference, our implicit approach realizes the update of the efficient state directly from sparse event data. Our sparse algorithm is especially suitable for mobile robotics applications in which computational resources and battery life are limited. To verify the effectiveness of our method on real-world data, we applied it to the AR marker tracking application. We have confirmed that our framework works well in real-world environments in the presence of noise and background clutter.

Authors

• Mana Masuda
• Yusuke Sekikawa
• Ryo Fujii
• Hideo Saito 0001

Keywords

• Tracking
• Robot vision systems
• Cameras
• Generators
• Computational efficiency
• Batteries
• State estimation
• Motion Tracking
• Event Data
• Current Estimates
• Multilayer Perceptron
• Sparse Data
• Presence Of Environment
• Neural Network
• Volume Change
• Stochastic Gradient Descent
• Lookup Table
• Tracking Performance
• White Background
• Gaussian Blur
• Inference Time
• Object Motion
• Tracking Algorithm
• Gradient-based Optimization
• Object Tracking
• High Dynamic Range
• Tracking Results
• Dynamic Vision Sensor
• Artificial Data
• White Grains
• Gradient-based Algorithm
• Camera Motion
• Event Stream
• Object Position
• Optimal Threshold