Putting Objects in Perspective
Derek Hoiem, Alexei A. Efros, Martial Hebert · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2006
Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. Most object detection methods consider all scales and locations in the image as equally likely. We show that with probabilistic estimates of 3D geometry, both in terms of surfaces and world coordinates, we can put objects into perspective and model the scale and location variance in the image. Our approach reflects the cyclical nature of the problem by allowing probabilistic object hypotheses to refine geometry and vice-versa. Our framework allows painless substitution of almost any object detector and is easily extended to include other aspects of image understanding. Our results confirm the benefits of our integrated approach.
Cited by 258 works. doi:10.1109/cvpr.2006.232
Authors
References
- Histograms of Oriented Gradients for Human Detection
- Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
- Robust Real-Time Face Detection
- LabelMe: A Database and Web-Based Tool for Image Annotation
- Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
- RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES
- Geometric context from a single image
- Logistic Regression, AdaBoost and Bregman Distances
- Image Parsing: Unifying Segmentation, Detection, and Recognition
- Discriminative random fields: a discriminative framework for contextual interaction in classification