Abstract | ||
---|---|---|
We present an object detection system based on the Fisher vector (FV) image representation computed over SIFT and color descriptors. For computational and storage efficiency, we use a recent segmentation-based method to generate class-independent object detection hypotheses, in combination with data compression techniques. Our main contribution is a method to produce tentative object segmentation masks to suppress background clutter in the features. Re-weighting the local image features based on these masks is shown to improve object detection significantly. We also exploit contextual features in the form of a full-image FV descriptor, and an inter-category rescoring mechanism. Our experiments on the VOC 2007 and 2010 datasets show that our detector improves over the current state-of-the-art detection results. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICCV.2013.369 | Computer Vision |
Keywords | Field | DocType |
image representation,image segmentation,object detection,vectors,FV image representation,Fisher vectors,SIFT,VOC,background clutter suppression,class-independent object detection hypotheses,color descriptors,data compression techniques,intercategory rescoring mechanism,object detection system,segmentation driven object detection,segmentation-based method,tentative object segmentation masks,fisher vectors,object detection | Computer vision,Object detection,Viola–Jones object detection framework,Scale-space segmentation,Pattern recognition,Object-class detection,Feature detection (computer vision),Computer science,Feature (computer vision),Segmentation-based object categorization,Image segmentation,Artificial intelligence | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
51 | 2.02 | 33 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
R. Gokberk Cinbis | 1 | 510 | 25.60 |
J. J. Verbeek | 2 | 3944 | 181.44 |
Cordelia Schmid | 3 | 28581 | 1983.22 |