Detection of dog-robot interactions in video sequences

Al-Raziqi, Ali; Krishna, Mahesh Venkata; Denzler, Joachim

doi:10.1134/s1054661816010028

Cited by 1 publication

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the Cavy dataset does not contain ground truth in terms of interactions among objects, we marked the semantically meaningful interactions in the scene (clip-wise annotations). Then, similar to the procedure in (Kuettel et al, 2010;Krishna and Denzler, 2014;Al-Raziqi et al, 2014), the output of our system is manually mapped to the ground truth labels and the performance measures are calculated. For the performance evaluation, we use the accuracy…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Unsupervised Learning, In the work presented in (Al-Raziqi et al, 2014), the authors have developed an HDP-based interaction extraction approach in which the optical flow is extracted in the whole image without object localization or trajectories motion analysis. Another interesting method which tried to tackle this problem is described in (Zhu et al, 2011).…”

Section: Related Workmentioning

confidence: 99%

“…In our case, we follow Al-Raziqi et al, 2014;Kuettel et al, 2010), where the corpus, documents and words correspond to the video sequence, short equal sized clips, and optical flow respectively. Generally, for a given input video, optical flow features are extracted from each pair of successive frames.…”

Section: Hierarchical Dirichlet Processesmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Framework for Interactions Modeling between Multiple Objects

Al-Raziqi

Denzler

2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Self Cite

View full text Add to dashboard Cite

Extracting compound interactions involving multiple objects is a challenging task in computer vision due to different issues such as the mutual occlusions between objects, the varying group size and issues raised from the tracker. Additionally, the single activities are uncommon compared with the activities that are performed by two or more objects, e.g., gathering, fighting, running, etc. The purpose of this paper is to address the problem of interaction recognition among multiple objects based on dynamic features in an unsupervised manner. Our main contribution is twofold. First, a combined framework using a tracking-by-detection framework for trajectory extraction and HDPs for latent interaction extraction is introduced. Another important contribution is the introduction of a new dataset, the Cavy dataset. The Cavy dataset contains about six dominant interactions performed several times by two or three cavies at different locations. The cavies are interacting in complicated and unexpected ways, which leads to perform many interactions in a short time. This makes working on this dataset more challenging. The experiments in this study are not only performed on the Cavy dataset but we also use the benchmark dataset Behave. The experiments on these datasets demonstrate the effectiveness of the proposed method. Although the our approach is completely unsupervised, we achieved satisfactory results with a clustering accuracy of up to 68.84% on the Behave dataset and up to 45% on the Cavy dataset.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%