Learning and Inferring 'Dark Matter' and Predicting Human Intents and Trajectories in Videos
| Autor: | Dan, Xie, Tianmin, Shu, Sinisa, Todorovic, Song-Chun, Zhu, Dan Xie, Tianmin Shu, Song-Chun Zhu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Databases
Factual Computer science Video Recording Analogy 02 engineering and technology Intention Machine learning computer.software_genre Motion (physics) Cosmology Electronic mail Pattern Recognition Automated Intelligent agent Public space Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Image Processing Computer-Assisted Cluster Analysis Humans Human Activities business.industry Applied Mathematics 020207 software engineering Cognition Computational Theory and Mathematics Trajectory Table (database) 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business computer Software |
| Zdroj: | IEEE transactions on pattern analysis and machine intelligence. 40(7) |
| ISSN: | 1939-3539 |
| Popis: | This paper presents a method for localizing functional objects and predicting human intents and trajectories in surveillance videos of public spaces, under no supervision in training. People in public spaces are expected to intentionally take shortest paths (subject to obstacles) toward certain objects (e.g., vending machine, picnic table, dumpster etc.) where they can satisfy certain needs (e.g., quench thirst). Since these objects are typically very small or heavily occluded, they cannot be inferred by their visual appearance but indirectly by their influence on people's trajectories. Therefore, we call them “dark matter”, by analogy to cosmology, since their presence can only be observed as attractive or repulsive “fields” in the public space. A person in the scene is modeled as an intelligent agent engaged in one of the “fields” selected depending his/her intent. An agent's trajectory is derived from an Agent-based Lagrangian Mechanics. The agents can change their intents in the middle of motion and thus alter the trajectory. For evaluation, we compiled and annotated a new dataset. The results demonstrate our effectiveness in predicting human intent behaviors and trajectories, and localizing and discovering distinct types of “dark matter” in wide public spaces. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|