Discovering Heterogeneous Subsequences for Trajectory Classification
arXiv:1903.07722v14 citations
Originality Synthesis-oriented
AI Analysis
This work addresses trajectory classification, potentially benefiting fields like robotics or surveillance, but appears incremental as it builds on existing methods without claiming major breakthroughs.
The authors tackled trajectory classification by proposing a parameter-free method that identifies optimal trajectory partitions and dimension combinations, with preliminary experiments indicating promising results.
In this paper we propose a new parameter-free method for trajectory classification which finds the best trajectory partition and dimension combination for robust trajectory classification. Preliminary experiments show that our approach is very promising.