Context and Subcategories for Sliding Window Object Recognition - Divvala, Santosh Kumar
44,99 €
inkl. MwSt.
Versandkostenfrei*
Versandfertig in 1-2 Wochen
payback
22 °P sammeln
  • Broschiertes Buch

The sliding window approach is the current de facto standard for building high-performance object detectors. The approach involves scanning an image with a fixed-size rectangular window and applying a classifier to the features extracted within the sub-image defined by the window. In this work, we study two important factors influencing its performance. First is the role played by context, where information outside the window is used to rescore the detections output by the local window classifier. Context helps in suppressing detections in regions that are less probable to contain an object…mehr

Andere Kunden interessierten sich auch für
Produktbeschreibung
The sliding window approach is the current de facto standard for building high-performance object detectors. The approach involves scanning an image with a fixed-size rectangular window and applying a classifier to the features extracted within the sub-image defined by the window. In this work, we study two important factors influencing its performance. First is the role played by context, where information outside the window is used to rescore the detections output by the local window classifier. Context helps in suppressing detections in regions that are less probable to contain an object and encourages those that are more plausible. We enumerate different sources and uses of context, and evaluate their role in aiding detection performance. Second is the role played by subcategories, where information within the window is used to split training data into smaller groups, for learning multiple classifiers to model the object appearance. The smaller groups have reduced appearance diversity and thus lead to simpler classification problems. We show that the use of subcategories not only improves detection performance, but also alleviates the need for complex representation and models.
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.
Autorenporträt
Santosh Kumar Divvala is a Postdoctoral Research Associate at the University of Washington. He completed his PhD in Robotics at the Carnegie Mellon University in 2012, advised by Martial Hebert and Alexei A. Efros. His research interests are in Machine Learning and Computer Vision.