Name
Abstract | ||
|---|---|---|
This paper focuses on the problem of scene classification for mobile robots in an outdoor environment. We present a novel model that combines biologically inspired features and cortex-like memory patterns. The biologically inspired gist feature is used to characterize the content of a scene image. The Incremental Hierarchical Discriminant Regression tree is used to simulate the generation and recall process of human memory. The association between the gist feature and the scene label is established in an incremental way. A cognitive model of the world is constructed using real-time online learning, and a new scene differentiated by reasoning. Using the biologically motivated model, we solved the outdoor scene classification problem on the University of Southern California data set. Experimental results indicate the incremental model improves the classification accuracy rates to nearly 100 % and significantly reduces training costs compared with other biologically inspired feature-based approaches. The new scene classification system achieves state-of-the-art performance. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1007/s12559-013-9227-y | Cognitive Computation |
Keywords | Field | DocType |
Mobile robot location,Scene classification,Visual gist feature,Visual memory,Incremental Hierarchical Discriminant Regression,Incremental learning | Online learning,Human memory,Decision tree,Pattern recognition,Computer science,Incremental build model,Visual memory,Artificial intelligence,Cognitive model,Recall,Mobile robot,Machine learning | Journal |
Volume | Issue | ISSN |
7 | 1 | 1866-9956 |
Citations | PageRank | References |
12 | 0.55 | 29 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jingjing Zhao | 1 | 25 | 4.94 |
| Chun Du | 2 | 13 | 0.90 |
| Hao Sun | 3 | 56 | 7.07 |
| Xingtong Liu | 4 | 27 | 2.97 |
| Jixiang Sun | 5 | 70 | 5.70 |