Neural Computation
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Large Margin Methods for Structured and Interdependent Output Variables
The Journal of Machine Learning Research
A stochastic grammar of images
Foundations and Trends® in Computer Graphics and Vision
Learning structural SVMs with latent variables
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Vehicle Surveillance with a Generic, Adaptive, 3D Vehicle Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-Time On-Road Vehicle Detection Combining Specific Shadow Segmentation and SVM Classification
ICDMA '11 Proceedings of the 2011 Second International Conference on Digital Manufacturing & Automation
Shared parts for deformable part-based models
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Detection and classification of vehicles
IEEE Transactions on Intelligent Transportation Systems
| Hi-index | 0.00 |
Handling occlusions in object detection is a long-standing problem. This paper addresses the problem of X-to-X-occlusion-free object detection (e.g. car-to-car occlusions in our experiment) by utilizing an intuitive coupling-and-decoupling strategy. In the "coupling" stage, we model the pair of occluding X's (e.g. car pairs) directly to account for the statistically strong co-occurrence (i.e. coupling). Then, we learn a hierarchical And-Or directed acyclic graph (AOG) model under the latent structural SVM (LSSVM) framework. The learned AOG consists of, from the top to bottom, (i) a root Or-node representing different compositions of occluding X pairs, (ii) a set of And-nodes each of which represents a specific composition of occluding X pairs, (iii) another set of And-nodes representing single X's decomposed from occluding X pairs, and (iv) a set of terminal-nodes which represent the appearance templates for the X pairs, single X's and latent parts of the single X's, respectively. The part appearance templates can also be shared among different single X's. In detection, a dynamic programming (DP) algorithm is used and as a natural consequence we decouple the two single X's from the X-to-X occluding pairs. In experiments, we test our method on roadside cars which are collected from real traffic video surveillance environment by ourselves. We compare our model with the state-of-the-art deformable part-based model (DPM) and obtain better detection performance.