Contour coding based rotating adaptive model for human detection and tracking in thermal catadioptric omnidirectional vision.

@article{Tang2012ContourCB,
  title={Contour coding based rotating adaptive model for human detection and tracking in thermal catadioptric omnidirectional vision.},
  author={Yazhe Tang and Youfu Li},
  journal={Applied optics},
  year={2012},
  volume={51 27},
  pages={
          6641-52
        }
}
In this paper, we introduce a novel surveillance system based on thermal catadioptric omnidirectional (TCO) vision. The conventional contour-based methods are difficult to be applied to the TCO sensor for detection or tracking purposes due to the distortion of TCO vision. To solve this problem, we propose a contour coding based rotating adaptive model (RAM) that can extract the contour feature from the TCO vision directly as it takes advantage of the relative angle based on the characteristics… 
View on PubMed
personal.cityu.edu.hk
14 Citations
Background Citations
2
Methods Citations
1

14 Citations

Citation Type

Citation Type

Rotational Kinematics Model Based Adaptive Particle Filter for Robust Human Tracking in Thermal Omnidirectional Vision
TLDR
A rotational kinematic modeled adaptive particle filter is proposed based on the characteristic of omnidirectional vision, which can handle multiple movements effectively, including the rapid motions, in a novel surveillance system which can work in total darkness with a wild field of view.
Distortion invariant joint-feature for visual tracking in catadioptric omnidirectional vision
TLDR
A parameterized neighborhood model to efficiently calculate the adaptive neighborhood of an object based on the measurable radial distance in image plane is presented and a distortion invariant joint-feature framework implemented with contour-color fragment mixture model of Gaussian is proposed for visual tracking in catadioptric omnidirectional camera system.
Equivalent projection based distortion invariant visual tracking for omnidirectional vision
TLDR
A distortion invariant multi-feature fusion method for robust feature representation in omnidirectional image and the fragment-based tracking framework can robustly handle the partial occlusion relying on an adaptive weight metric mechanism is presented.
Parameterized Distortion-Invariant Feature for Robust Tracking in Omnidirectional Vision
TLDR
To robustly handle challenging occlusion in the distorted image, a flexible fragment-based joint-feature framework is presented for robust non-rigid human target tracking and the proposed tracking approaches leads to much better performance from the perspective of efficiency and robustness.
Parametric distortion-adaptive neighborhood for omnidirectional camera.
TLDR
This study constructs a catadioptric geometry system to analyze the variation of the neighborhood of an object in terms of the elevation and azimuth directions in a spherical coordinate system and presents a distortion-invariant Haar wavelet transform to perform the robust human detection and tracking in catadiOptric omnidirectional vision.
Structural keypoints voting for global visual tracking
TLDR
A patch-based keypoints clustering method for long term robust visual tracking that could robustly reduce the error due to the misclassified outliers and a two-step voting from global to local scope is proposed.
Patch-based keypoints consensus voting for robust visual tracking
TLDR
A patch-based keypoints clustering method for long term robust visual tracking using a parallel framework with keypoints matching and estimation for tracking purpose and a two-step voting from global to local scope to eliminate the error.
Entropy distribution and coverage rate-based birth intensity estimation in GM-PHD filter for multi-target visual tracking
A hybrid shape descriptor for object recognition
TLDR
A hybrid shape descriptor which contains salient shape features in different aspects to derive a "rich" descriptor is proposed which is invariant to rotation, scale variation, and occlusion and robust to noise.
Penalized Gaussian mixture probability hypothesis density tracker with multi-feature fusion
TLDR
A penalized Gaussian mixture probability hypothesis density tracker with multi-feature fusion to track close moving targets in video and the experimental results validate the effectiveness of the proposed tracker.
...
1
2
...

References

SHOWING 1-10 OF 30 REFERENCES
Human tracking in thermal catadioptric omnidirectional vision
TLDR
The proposed tracking method adopts the classification posterior probability of Support Vector Machine (SVM) to relate the observation likelihood of particle filter for efficient tracking and shows that it has a stable and good performance in TCO vision tracking system.
Infrared human tracking with improved mean shift algorithm based on multicue fusion.
TLDR
Compared with the traditional mean shift algorithm, the presented method greatly improves the accuracy and effectiveness of infrared human tracking under complex scenes, and the tracking results are satisfactory.
Face tracking using a hyperbolic catadioptric omnidirectional system
TLDR
The results show that, when using a careful combination of the two projections, good frame rates can be achieved in the task of tracking faces reliably in the omnidirectional images using Viola-Jones method.
Pedestrian Recognition from a Moving Catadioptric Camera
TLDR
This paper proposes a novel hybrid combination of a boosted cascade of wavelet-based classifiers with a subsequent texture-based neural network involving adaptive local features as final cascade stage within a real-time system for vision-based pedestrian recognition from a moving vehicle-mounted catadioptric camera.
Probabilistic color matching and tracking of human subjects.
TLDR
This work applies the CM approach toward the tracking of human subjects in real time by matching and tracking the underlying color pattern as observed from a fixed camera, and shows that there is an optimum alphabet size and segmentation of the RGB color cube for efficient tracking.
Pedestrian detection and tracking with night vision
TLDR
A two-step detection/tracking method using a support vector machine with size-normalized pedestrian candidates and a combination of Kalman filter prediction and mean shift tracking for nonrigid nature of human appearance on the road is proposed.
Tracking unknown moving targets on omnidirectional vision
Layered Representation for Pedestrian Detection and Tracking in Infrared Imagery
  • Congxia Dai, Yunfei Zheng, Xin Li
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops
  • 2005
TLDR
A hybrid (shape+appearance) algorithm for pedestrian detection, in which shape cue is first used to eliminate non-pedestrian moving objects and appearance cue is then used to pin down the location of pedestrians, is proposed.
Pedestrian detection and tracking in infrared imagery using shape and appearance
Lightweight biometric detection system for human classification using pyroelectric infrared detectors.
TLDR
Two classification methods are demonstrated by using data gathered from sensor clusters of dual-element pyroelectric detectors with coded Fresnel lens arrays for person identification and a more rigorous example that uses principal component regression to perform a blind classification is proposed.
...
1
2
3
...