Context-based abnormal object detection using the fully-connected conditional random fields

@article{Oh2017ContextbasedAO,
  title={Context-based abnormal object detection using the fully-connected conditional random fields},
  author={Jongsuk Oh and Hong-In Kim and Rae-Hong Park},
  journal={Pattern Recognit. Lett.},
  year={2017},
  volume={98},
  pages={16-25}
}
Abstract The contextual information plays an important role in computer vision, particularly in object detection and scene understanding. The existing contextual models use only the relationship between normal objects and natural scenes, and thus there still remains a difficult problem in detection of abnormal objects. This paper proposes an abnormal object detection model using the fully-connected conditional random fields to integrate the contextual information such as the co-occurrence and… Expand
5 Citations
Research on abnormal object detection in specific region based on Mask R-CNN
  • 1
Scene-Aware Context Reasoning for Unsupervised Abnormal Event Detection in Videos
  • 4
Adaptive GMM and BP Neural Network Hybrid Method for Moving Objects Detection in Complex Scenes
  • 5
A comprehensive review of conditional random fields: variants, hybrids and applications
  • 2

References

SHOWING 1-10 OF 22 REFERENCES
A Tree-Based Context Model for Object Recognition
  • 138
  • PDF
An Object-Level High-Order Contextual Descriptor Based on Semantic, Spatial, and Scale Cues
  • 14
Efficient inference for fully-connected CRFs with stationarity
  • Y. Zhang, T. Chen
  • Mathematics, Computer Science
  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
  • 74
  • PDF
The Role of Context for Object Detection and Semantic Segmentation in the Wild
  • 718
  • PDF
A new robust context-based dense CRF model for image labeling
  • 5
  • PDF
Structural Kernel Learning for Large Scale Multiclass Object Co-detection
  • 8
Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation
  • 373
  • PDF
Object Detection with Discriminatively Trained Part Based Models
  • 8,767
  • PDF
...
1
2
3
...