Transferring a generic pedestrian detector towards specific scenes

@article{Wang2012TransferringAG,
  title={Transferring a generic pedestrian detector towards specific scenes},
  author={M. Wang and W. Li and Xiaogang Wang},
  journal={2012 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2012},
  pages={3274-3281}
}
The performance of a generic pedestrian detector may drop significantly when it is applied to a specific scene due to mismatch between the source dataset used to train the detector and samples in the target scene. In this paper, we investigate how to automatically train a scene-specific pedestrian detector starting with a generic detector in video surveillance without further manually labeling any samples under a novel transfer learning framework. It tackles the problem from three aspects. (1… Expand
Scene-Specific Pedestrian Detection for Static Video Surveillance
TLDR
This work proposes a new approach of automatically transferring a generic pedestrian detector to a scene-specific detector in static video surveillance without manually labeling samples from the target scene through a single objective function called confidence-encoded SVM. Expand
Specialization of a Generic Pedestrian Detector to a Specific Traffic Scene by the Sequential Monte-Carlo Filter and the Faster R-CNN
TLDR
A new approach to automatically specialize a scene-specific pedestrian detector starting with a generic detector in video surveillance without further manually labeling any samples under a novel transfer learning framework is suggested. Expand
Cognitive pedestrian detector: Adapting detector to specific scene by transferring attributes
TLDR
This paper proposes a novel transfer learning framework for improving the performance of a generic detector by adapting the detector to a scene specific detector and outperforms the state-of-the-art adapting approaches in benchmark datasets. Expand
Deep Learning of Scene-Specific Classifier for Pedestrian Detection
TLDR
A deep model is proposed to automatically learn scene-specific features and visual patterns in static video surveillance without any manual labels from the target scene to bridge the appearance gap. Expand
Scene-specific pedestrian detection based on transfer learning and saliency detection for video surveillance
TLDR
A novel transfer learning framework is proposed, which automatically transfers a generic detector to a scene-specific pedestrian detector without manually labeling training samples from target scenes, and it is comparable with the detector trained by a lot of manually labeled samples from the target scene. Expand
SMC faster R-CNN: Toward a scene-specialized multi-object detector
TLDR
A new formalism of transfer learning based on the theory of a Sequential Monte Carlo (SMC) filter to automatically specialize a scene-specific Faster R-CNN detector towards a target scene is proposed. Expand
A Sparse Coding Based Transfer Learning Framework for Pedestrian Detection
TLDR
A transfer learning framework to automatically train a scene-specific pedestrian detector starting from a pre-trained generic detector is proposed and it is comparable with the detector trained on a large number of training samples manually labeled from the target scene. Expand
Training a Scene-Specific Pedestrian Detector Using Tracklets
TLDR
The proposed approach to automatically train scene-specific pedestrian detectors based on track lets outperforms the state-of-the-art scene- specific detector and shows the effectiveness to adapt to specific scenes without human annotations. Expand
A parallel vision approach to scene-specific pedestrian detection
TLDR
A parallel vision approach to scene-specific pedestrian detection that is incrementally optimized with newly synthesized data as the specific scene evolves over time leads to higher precision than the models trained on generic data. Expand
Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes
TLDR
This paper proposes a novel algorithm to automatically adapt and tune a generic pedestrian detector to specific scenes which may possess different data distributions than the original dataset from which the detector was trained. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 29 REFERENCES
Automatic adaptation of a generic pedestrian detector to a specific traffic scene
TLDR
This paper proposes a new framework of adapting a pre-trained generic pedestrian detector to a specific traffic scene by automatically selecting both confident positive and negative examples from the target scene to re-train the detector iteratively, which significantly improves the accuracy of the generic detector and also outperforms the scene specific detector retrained using background subtraction. Expand
Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness
TLDR
This paper focuses on the disparities caused by viewpoint and scene changes and proposes an efficient solution to these particular cases by adapting generic detectors, assuming boosting style, to improve detection accuracy over state-of-the-art methods. Expand
A discriminative deep model for pedestrian detection with occlusion handling
TLDR
A probabilistic pedestrian detection framework using a deformable part-based model to obtain the scores of part detectors and the visibilities of parts are modeled as hidden variables and a discriminative deep model is used for learning the visibility relationship among overlapping parts at multiple layers. Expand
Pedestrian Detection: An Evaluation of the State of the Art
TLDR
An extensive evaluation of the state of the art in a unified framework of monocular pedestrian detection using sixteen pretrained state-of-the-art detectors across six data sets and proposes a refined per-frame evaluation methodology. Expand
Poselets: Body part detectors trained using 3D human pose annotations
TLDR
A new dataset, H3D, is built of annotations of humans in 2D photographs with 3D joint information, inferred using anthropometric constraints, to address the classic problems of detection, segmentation and pose estimation of people in images with a novel definition of a part, a poselet. Expand
An unsupervised, online learning framework for moving object detection
  • Vinod Nair, James J. Clark
  • Computer Science
  • Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
TLDR
This work presents a framework that learns the classifier online with automatically labeled data for the specific case of detecting moving objects from video with an online learner based on the Winnow algorithm. Expand
Improving Part based Object Detection by Unsupervised, Online Boosting
  • Bo Wu, R. Nevatia
  • Computer Science
  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
TLDR
This work proposes an unsupervised, incremental learning approach based on online boosting to improve the performance on special applications of a set of general part detectors, which are learned from a small amount of labeled data and have moderate accuracy. Expand
Cross-domain learning methods for high-level visual concept classification
TLDR
This work develops a new cross-domain SVM (CDSVM) algorithm for adapting previously learned support vectors from one domain to help classification in another domain, and proposes an intuitive selection criterion to determine which cross- domain learning method to use for each concept. Expand
Semi-Supervised Self-Training of Object Detection Models
TLDR
The key contributions of this empirical study are to demonstrate that a model trained in this manner can achieve results comparable to a modeltrained in the traditional manner using a much larger set of fully labeled data, and that a training data selection metric that is defined independently of the detector greatly outperforms a selection metric based on the detection confidence generated by the detector. Expand
Cross-domain video concept detection using adaptive svms
TLDR
This paper proposes Adaptive Support Vector Machines (A-SVMs) as a general method to adapt one or more existing classifiers of any type to the new dataset and outperforms several baseline and competing methods in terms of classification accuracy and efficiency in cross-domain concept detection in the TRECVID corpus. Expand
...
1
2
3
...