G06V 10/62
Definition
Diese Klassifikationsstelle umfasst:(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)
Techniques involving time-related feature extraction and pattern tracking for image or video recognition or understanding. Such techniques include:
- generative methods, such as kernel-based tracking (KT), Kalman filtering (KF), particle filtering (PF);
- discriminative tracking methods, such as joint probability data association filtering (JPDAF), multiple-hypothesis tracking (MHT), flow network framework (FNF).
Notes – technical background
These notes provide more information about the technical subject matter that is classified in this place:
1. Tracking may be implemented using a single camera or a system with multiple cameras, with possibly overlapping field of views (FOV).
2. In time-related feature extraction and pattern tracking, the features extracted from the video can be low-level (e.g. pixel colours, gradient, motion cues), mid-level (e.g. edges, corners, interest points, regions, etc.) or high-level (e.g. geometrical arrangements of parts of an object). The tracking often involves the foreground-background segmentation or background modelling in order to focus only on the objects of interest and reduce the overall complexity. Target representations are models of the objects of interest which rely on visual cues such as shape, texture, colour. There are rigid models (e.g. regions or volumes of interest), articulated models (e.g. kinematic chains) or deformable models (e.g. fluid models, point-distributions, appearance models).
An inherent problem during tracking is that of localisation, which is usually solved:
- using single-hypothesis localisation in which only one track candidate estimate is evaluated over time, e.g. gradient-based trackers such as Kanade-Lucas-Tomasi (KLT), mean-shift (MS) tracker, Bayes tracker, Kalman filtering; or
- a multiple-hypothesis localisation where multiple tracks are evaluated simultaneously, e.g. grid sampling, particle filter, hybrid methods such as hybrid particle mean shift tracker.
Models employed during tracking include graphical models (e.g. Markov models), graph-matching based tracking, camera-link model (CLM) or statistical models such as maximum a-posteriori estimation (MAP).
Problems frequently occurring are that of context modelling (e.g. changes in background, clutter, duration of the tracking events), or in the case of a multiple camera system, that of re-identification, i.e. detection of the same object in the field of view of these cameras.
Neural networks have been more recently applied to the problem of tracking, examples of architectures include: generic object tracking using regression networks (GOTURN), multi-domain network (MDNet), long short term memory (LSTM) networks, recurrent you only look once (ROLO) networks.
Examples
Tracking, person re-identification in a multiple camera system
Querverweise
Informative Querverweise
| Image preprocessing for image or video recognition or understanding involving the determination of a region or volume of interest [ROI, VOI] | G06V 10/25 |
| Global feature extraction by analysis of the whole pattern | G06V 10/42 |
| Descriptors for shape, contour or point-related descriptors, e.g. SIFT | G06V 10/46 |
| Local feature extraction by performing operations within image blocks or by using histograms | G06V 10/50 |
| Feature extraction related to texture | G06V 10/54 |
| Feature extraction related to colour | G06V 10/56 |
| Pattern recognition or machine learning for image or video recognition or understanding using probabilistic graphical models | G06V 10/84 |
| Analysis of motion in images | G06T 7/20 |
Glossar
| CLM | camera link model |
| FOV | field of view |
| GM | graph matching |
| KF | Kalman filter |
| KT | kernel tracking |
| MAP | maximum a-posteriori estimation |
| MHT | multiple hypothesis tracking |
| PF | particle filtering |
G06V 10/62
Definition Statement
This place covers:Techniques involving time-related feature extraction and pattern tracking for image or video recognition or understanding. Such techniques include:
- generative methods, such as kernel-based tracking (KT), Kalman filtering (KF), particle filtering (PF);
- discriminative tracking methods, such as joint probability data association filtering (JPDAF), multiple-hypothesis tracking (MHT), flow network framework (FNF).
Notes – technical background
These notes provide more information about the technical subject matter that is classified in this place:
1. Tracking may be implemented using a single camera or a system with multiple cameras, with possibly overlapping field of views (FOV).
2. In time-related feature extraction and pattern tracking, the features extracted from the video can be low-level (e.g. pixel colours, gradient, motion cues), mid-level (e.g. edges, corners, interest points, regions, etc.) or high-level (e.g. geometrical arrangements of parts of an object). The tracking often involves the foreground-background segmentation or background modelling in order to focus only on the objects of interest and reduce the overall complexity. Target representations are models of the objects of interest which rely on visual cues such as shape, texture, colour. There are rigid models (e.g. regions or volumes of interest), articulated models (e.g. kinematic chains) or deformable models (e.g. fluid models, point-distributions, appearance models).
An inherent problem during tracking is that of localisation, which is usually solved:
- using single-hypothesis localisation in which only one track candidate estimate is evaluated over time, e.g. gradient-based trackers such as Kanade-Lucas-Tomasi (KLT), mean-shift (MS) tracker, Bayes tracker, Kalman filtering; or
- a multiple-hypothesis localisation where multiple tracks are evaluated simultaneously, e.g. grid sampling, particle filter, hybrid methods such as hybrid particle mean shift tracker.
Models employed during tracking include graphical models (e.g. Markov models), graph-matching based tracking, camera-link model (CLM) or statistical models such as maximum a-posteriori estimation (MAP).
Problems frequently occurring are that of context modelling (e.g. changes in background, clutter, duration of the tracking events), or in the case of a multiple camera system, that of re-identification, i.e. detection of the same object in the field of view of these cameras.
Neural networks have been more recently applied to the problem of tracking, examples of architectures include: generic object tracking using regression networks (GOTURN), multi-domain network (MDNet), long short term memory (LSTM) networks, recurrent you only look once (ROLO) networks.
Examples
Tracking, person re-identification in a multiple camera system
References
Informative references
| Image preprocessing for image or video recognition or understanding involving the determination of a region or volume of interest [ROI, VOI] | G06V 10/25 |
| Global feature extraction by analysis of the whole pattern | G06V 10/42 |
| Descriptors for shape, contour or point-related descriptors, e.g. SIFT | G06V 10/46 |
| Local feature extraction by performing operations within image blocks or by using histograms | G06V 10/50 |
| Feature extraction related to texture | G06V 10/54 |
| Feature extraction related to colour | G06V 10/56 |
| Pattern recognition or machine learning for image or video recognition or understanding using probabilistic graphical models | G06V 10/84 |
| Analysis of motion in images | G06T 7/20 |
Glossary
| CLM | camera link model |
| FOV | field of view |
| GM | graph matching |
| KF | Kalman filter |
| KT | kernel tracking |
| MAP | maximum a-posteriori estimation |
| MHT | multiple hypothesis tracking |
| PF | particle filtering |