| Presentation | 2004/1/22 Trajectory Recognition using State Transition Model with Counters Keiji OTAKA, Tadashi AE, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this report, we propose a method to recognize a trajectory generated by human motion as a realization of human activities. Although the advanced processing of obtained data is a future issue in earlier studies, we will discuss a trajectory recognition using model-based learning to utilize a knowledge acquisition or representation. In recognition based on learning, the performance differs in quality among models. For the 2-dimensional information included in trajectory data, there are several classes of trajectories where HMM(Hidden Markov Model) is not applied, although HMM is an excellent model. In this report, we focus on the recognition capability of model, and propose a model including a higher ability to recognize trajectories, which is called STMC(State Transition Model with Counters). We discuss the learning algorithm of STMC and several experimental results. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Trajectory Recognition / HMM / State Transition Model with Counters / Query Learning |
| Paper # | AI2003-71 |
| Date of Issue |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2004/1/22(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Trajectory Recognition using State Transition Model with Counters |
| Sub Title (in English) | |
| Keyword(1) | Trajectory Recognition |
| Keyword(2) | HMM |
| Keyword(3) | State Transition Model with Counters |
| Keyword(4) | Query Learning |
| 1st Author's Name | Keiji OTAKA |
| 1st Author's Affiliation | Graduate School of Engineering, Hiroshima University() |
| 2nd Author's Name | Tadashi AE |
| 2nd Author's Affiliation | Graduate School of Engineering, Hiroshima University |
| Date | 2004/1/22 |
| Paper # | AI2003-71 |
| Volume (vol) | vol.103 |
| Number (no) | 623 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |