Abstract | ||
---|---|---|
In this paper, we evaluate the notion of scene analysis with regard to physical risks and potential hazards in an environment and providing a quantified risk score. A definition of risk is given incorporating different elements but mainly focusing on intrinsic risk related properties of an object (e.g sharpness). A novel 3D Voxel-HOG descriptor is introduced that aims to classify and recognise the presence of sharp characteristics and features of objects present in a given scene. Additionally we present a new dataset (3DRS) designed for risk evaluation in scene analysis. The effectiveness of our method is demonstrated by conducting experiments on all the objects in the 3DRS dataset, comparing the proposed features with state-of-the-art descriptors. |
Year | Venue | Keywords |
---|---|---|
2015 | 2015 IEEE INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP) | Scene Analysis, Content Analysis, Automated Risk Assessment |
Field | DocType | Citations |
Voxel,Computer vision,Histogram,Risk evaluation,Scene analysis,Pattern recognition,Computer science,Feature extraction,Artificial intelligence,Estimation theory | Conference | 3 |
PageRank | References | Authors |
0.36 | 26 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rob Dupre | 1 | 5 | 2.77 |
Vasileios Argyriou | 2 | 279 | 30.51 |