Object recognition from range data prior to segmentation
Image and Vision Computing
Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised learning by probabilistic latent semantic analysis
Machine Learning
Edge-Region-Based Segmentation of Range Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Edge Detection in Range Images of Piled Box-like Objects
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Curvature Scale Space Corner Detector with Adaptive Threshold and Dynamic Region of Support
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Contour-Based Learning for Object Detection
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
3D free-form object recognition in range images using local surface patches
Pattern Recognition Letters
Representing shape with a spatial pyramid kernel
Proceedings of the 6th ACM international conference on Image and video retrieval
Groups of Adjacent Contour Segments for Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Integrated Method for Multiple Object Detection and Localization
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
A boundary-fragment-model for object detection
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
| Hi-index | 0.00 |
We present an object detection technique that uses local edgels and their geometry to locate multiple objects in a range image in the presence of partial occlusion, background clutter, and depth changes. The fragmented local edgels (key-edgels) are efficiently extracted from a 3D edge map by separating them at their corner points. Each key-edgel is described using our scale invariant descriptor that encodes local geometric configuration by joining the edgel at their start and end points adjacent edgels. Using key-edgels and their descriptors, our model generates promising hypothetical locations in the image. These hypotheses are then verified using more discriminative features. The approach is evaluated on ten diverse object categories in a real-world environment.