Directional Space-Time Oriented Gradients for 3D Visual Pattern Analysis

Norouznezhad, Ehsan; Harandi, Mehrtash; Bigdeli, Abbas; Baktash, Mahsa; Postula, Adam; Lovell, Brian C.

doi:10.1007/978-3-642-33712-3_53

Cited by 14 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we also compare with the LBP-TOP [5] as it was tested on most of the datasets and also combines an analysis of three orthogonal planes. The results of LBP-TOP are provided in [65] and [49] with the original author's implementation [5] for the former and their own implementation for the latter. Our method obtains consistent high accuracy results on all the datasets and overall outperforms all other methods in the literature.…”

Section: Resultsmentioning

confidence: 99%

Convolutional neural network on three orthogonal planes for dynamic texture classification

Andrearczyk

Whelan

2018

Pattern Recognition

View full text Add to dashboard Cite

Dynamic Textures (DTs) are sequences of images of moving scenes that exhibit certain stationarity properties in time such as smoke, vegetation and fire. The analysis of DT is important for recognition, segmentation, synthesis or retrieval for a range of applications including surveillance, medical imaging and remote sensing. Deep learning methods have shown impressive results and are now the new state of the art for a wide range of computer vision tasks including image and video recognition and segmentation. In particular, Convolutional Neural Networks (CNNs) have recently proven to be well suited for texture analysis with a design similar to a filter bank approach. In this paper, we develop a new approach to DT analysis based on a CNN method applied on three orthogonal planes x y, xt and y t . We train CNNs on spatial frames and temporal slices extracted from the DT sequences and combine their outputs to obtain a competitive DT classifier. Our results on a wide range of commonly used DT classification benchmark datasets prove the robustness of our approach. Significant improvement of the state of the art is shown on the larger datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Convolutional neural network on three orthogonal planes for dynamic texture classification

Andrearczyk

Whelan

2018

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…For LBP-based methods, using 2D descriptors on three orthogonal planes has so far been proven more successful and this approach is frequently used also by non LBP-based methods (Andrearczyk and Whelan [1]; Arashloo and Kittler [3]; Arashloo et al [2]; Xu et al [83]). A variant of this idea proposed by Norouznezhad et al [55] is to replace the three orthogonal planes with nine spatio-temporal symmetry planes and apply a histogram of oriented gradients on these planes. Similarly, the directional number transitional graph (DNG) by Rivera et al [64] is evaluated on nine spatiotemporal cross sections of a video.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Texture Recognition Using Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields

Jansson

Lindeberg

2018

J Math Imaging Vis

View full text Add to dashboard Cite

This work presents a first evaluation of using spatio-temporal receptive fields from a recently proposed time-causal spatiotemporal scale-space framework as primitives for video analysis. We propose a new family of video descriptors based on regional statistics of spatio-temporal receptive field responses and evaluate this approach on the problem of dynamic texture recognition. Our approach generalises a previously used method, based on joint histograms of receptive field responses, from the spatial to the spatio-temporal domain and from object recognition to dynamic texture recognition. The time-recursive formulation enables computationally efficient time-causal recognition. The experimental evaluation demonstrates competitive performance compared to state of the art. In particular, it is shown that binary versions of our dynamic texture descriptors achieve improved performance compared to a large range of similar methods using different primitives either handcrafted or learned from data. Further, our qualitative and quantitative investigation into parameter choices and the use of different sets of receptive fields highlights the robustness and flexibility of our approach. Together, these results support the descriptive power of this family of time-causal spatio-temporal receptive fields, validate our approach for dynamic texture recognition and point towards the possibility of designing a range of video analysis methods based on these new time-causal spatio-temporal primitives.

show abstract

“…8 (left) for an illustration for the LPB variant of Kellokumpu et al (2008)). The idea of three orthogonal plane is extended by Norouznezhad et al (2012) to nine symmetric planes.…”

Section: Pixel Pattern Descriptorsmentioning

confidence: 99%

Going deeper into action recognition: A survey

Herath

Harandi

Porikli

2017

Image and Vision Computing

564

298

View full text Add to dashboard Cite

Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation. Over the last decade, human action analysis evolved from earlier schemes that are often limited to controlled environments to nowadays advanced solutions that can learn from millions of videos and apply to almost all daily activities. Given the broad range of applications from video surveillance to human-computer interaction, scientific milestones in action recognition are achieved more rapidly, eventually leading to the demise of what used to be good in a short time. This motivated us to provide a comprehensive review of the notable steps taken towards recognizing human actions. To this end, we start our discussion with the pioneering methods that use handcrafted representations, and then, navigate into the realm of deep learning based approaches. We aim to remain objective throughout this survey, touching upon encouraging improvements as well as inevitable fallbacks, in the hope of raising fresh questions and motivating new research directions for the reader.

show abstract

Directional Space-Time Oriented Gradients for 3D Visual Pattern Analysis

Cited by 14 publications

References 29 publications

Convolutional neural network on three orthogonal planes for dynamic texture classification

Convolutional neural network on three orthogonal planes for dynamic texture classification

Dynamic Texture Recognition Using Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields

Going deeper into action recognition: A survey

Contact Info

Product

Resources

About