Automatic human action recognition in a scene from visual inputs

Bouma, Henri; Hanckmann, P.; Marck, Jan Willem; Penning, Leo de; Hollander, Richard den; Hove, Johan-Martijn ten; Broek, Sebastiaan van den; Schutte, Klamer; Burghouts, Gertjan J.

doi:10.1117/12.918582

Cited by 17 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although [13] already showed that the RF TP is a good stand alone verb classifier, here we see it also performs well when applied to a description task. Even though the RF TP classifier is not optimized for the description generator (e.g.…”

Section: Resultsmentioning

confidence: 91%

“…This overall system is described in [12,13] and it is summarized here. It consists of five building blocks (see figure 2): visual processing, fusion engine, event description, action classifier, and the description generator.…”

Section: System Overviewmentioning

confidence: 99%

“…The Random-Forest Tag-Propagation (RF TP) and multihypotheses Rule Based System (RBS) classifiers are considered. The choice is based on performance: the RF TP performs best [21] and the RBS performed second best as actions classifiers in previous research [13] on the DARPA dataset under investigation (see section 3 for details).…”

Section: Action Classifiermentioning

confidence: 99%

See 2 more Smart Citations

Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions

Hanckmann

Schutte

Burghouts

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

Self Cite

View full text Add to dashboard Cite

Abstract. Presented is a hybrid method to generate textual descriptions of video based on actions. The method includes an action classifier and a description generator. The aim for the action classifier is to detect and classify the actions in the video, such that they can be used as verbs for the description generator. The aim of the description generator is (1) to find the actors (objects or persons) in the video and connect these correctly to the verbs, such that these represent the subject, and direct and indirect objects, and (2) to generate a sentence based on the verb, subject, and direct and indirect objects. The novelty of our method is that we exploit the discriminative power of a bag-of-features action detector with the generative power of a rule-based action descriptor. Shown is that this approach outperforms a homogeneous setup with the rulebased action detector and action descriptor.

show abstract

Section: Resultsmentioning

confidence: 91%

Section: System Overviewmentioning

confidence: 99%

See 1 more Smart Citation

Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions

Hanckmann

Schutte

Burghouts

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

Self Cite

View full text Add to dashboard Cite

show abstract

“…Future work may include a large scale experiment, the combination with behavioral profiling [6] or automatic action recognition [5][7] [9], and an evaluation on a public available database for multi-camera surveillance for person reidentification, such as the database of Bialkowski e.a. [2].…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Real-time tracking and fast retrieval of persons in multiple surveillance cameras of a shopping mall

et al. 2013

Self Cite

View full text Add to dashboard Cite

The capability to track individuals in CCTV cameras is important for e.g. surveillance applications at large areas such as train stations, airports and shopping centers. However, it is laborious to track and trace people over multiple cameras. In this paper, we present a system for real-time tracking and fast interactive retrieval of persons in video streams from multiple static surveillance cameras. This system is demonstrated in a shopping mall, where the cameras are positioned without overlapping fields-of-view and have different lighting conditions. The results show that the system allows an operator to find the origin or destination of a person more efficiently. The misses are reduced with 37%, which is a significant improvement.

show abstract

“…A person-tracing system is composed of multiple components such as moving object detection [13] or static person detection [9][15] [26], segmentation, tracking [25] [43][45] [46], human interaction [6] [8] and person re-identification. The scope of our investigation focuses on the person re-identification algorithm which uses still images of the persons' bounding boxes as input and performs two steps: descriptor computation and matching ( Figure 1).…”

Section: Literature Overviewmentioning

confidence: 99%

Re-identification of persons in multi-camera surveillance under varying viewpoints and illumination

et al. 2012

Self Cite

View full text Add to dashboard Cite

The capability to track individuals in CCTV cameras is important for surveillance and forensics alike. However, it is laborious to do over multiple cameras. Therefore, an automated system is desirable. In literature several methods have been proposed, but their robustness against varying viewpoints and illumination is limited. Hence performance in realistic settings is also limited. In this paper, we present a novel method for the automatic re-identification of persons in video from surveillance cameras in a realistic setting. The method is computationally efficient, robust to a wide variety of viewpoints and illumination, simple to implement and it requires no training. We compare the performance of our method to several state-of-the-art methods on a publically available dataset that contains the variety of viewpoints and illumination to allow benchmarking. The results indicate that our method shows good performance and enables a human operator to track persons five times faster.

show abstract

Automatic human action recognition in a scene from visual inputs

Cited by 17 publications

References 19 publications

Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions

Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions

Real-time tracking and fast retrieval of persons in multiple surveillance cameras of a shopping mall

Re-identification of persons in multi-camera surveillance under varying viewpoints and illumination

Contact Info

Product

Resources

About