Human Activity Recognition Using Local Shape Descriptors
Sharath Venkatesha,Matthew Turk +1 more
- pp 3704-3707
TLDR
A method for human activity recognition in videos, based on shape analysis, that achieves an accuracy of 87%, and is comparable to other state-of-the-art methods.Abstract:
We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human action and build an action descriptor using a Bag of Features method. We also use the temporal relation among matching interest points across successive video frames. Further, an SVM is trained on these action descriptors to classify the activity in the scene. The method is invariant to the length of the video sequence, and hence it is suitable in online activity recognition. We have demonstrated the results on an action database consisting of nine actions like walk, jump, bend, etc., by twenty people, in indoor and outdoor scenarios. The proposed method achieves an accuracy of 87%, and is comparable to other state-of-the-art methods.read more
Citations
More filters
Journal ArticleDOI
Abnormal human activity recognition system based on R-transform and kernel discriminant technique for elderly home care
Zafar Ali Khan,Won Sohn +1 more
TL;DR: A system for elderly care by recognizing six abnormal activities; forward fall, backward fall, chest pain, faint, vomit, and headache, selected from the daily life activities of elderly people is presented.
Journal ArticleDOI
Single- and two-person action recognition based on silhouette shape and optical point descriptors
TL;DR: It is found that the joint action descriptor shows the best performance among the proposed descriptors due to its high discriminative power and also outperforms state-of-the-art approaches.
Journal ArticleDOI
An approach for model assissment for activity recognition
TL;DR: The paper introduces general concept of Dual Leave-Group-of-Sources-Out cross-validation procedure, which provides reliable way for model parameters optimization in practical applications and prevents overestimation of recognition quality from point of view generalization capability.
Proceedings ArticleDOI
A spatiotemporal descriptor based on radial distances and 3D joint tracking for action classification
Sherif Azary,Andreas Savakis +1 more
TL;DR: An efficient 3D descriptor combining radial distance measures on 2D video sequences with 3D joint tracking on depth data for action classification through Manifold Learning using supervised Locality Preserving Projections (sLPP).
Journal ArticleDOI
Dendritic Cells Feature Extraction using Geometric Features and 1D Fourier Descriptors
Anis Azwani Muhd Suberi,Wan Nurshazwani Wan Zakaria,Razali Tomari,Nurmiza Othman,Nik Farhan Nik Fuad +4 more
TL;DR: Two pattern matching approaches based on Geometric and 1D Fourier Descriptors (FDs) to classify Dendritic Cells from Phase Contrast Microscopy (PCM) image containing a mix of T-cells and debris are proposed.
References
More filters
Proceedings ArticleDOI
Recognizing human actions: a local SVM approach
TL;DR: This paper construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition and presents the presented results of action recognition.
Journal ArticleDOI
The recognition of human movement using temporal templates
Aaron F. Bobick,James W. Davis +1 more
TL;DR: A view-based approach to the representation and recognition of human movement is presented, and a recognition method matching temporal templates against stored instances of views of known actions is developed.
Proceedings ArticleDOI
Actions as space-time shapes
TL;DR: The method is fast, does not require video alignment and is applicable in many scenarios where the background is known, and the robustness of the method is demonstrated to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action and low quality video.
Journal ArticleDOI
Actions as Space-Time Shapes
TL;DR: The method is fast, does not require video alignment, and is applicable in many scenarios where the background is known, and the robustness of the method is demonstrated to partial occlusions, nonrigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low-quality video.
Proceedings ArticleDOI
Event Detection in Crowded Videos
TL;DR: This work proposes a technique for event recognition in crowded videos that reliably identifies actions in the presence of partial occlusion and background clutter, enabling robustness against occlusions and actor variability.
Related Papers (5)
A novel local feature descriptor based on energy information for human activity recognition
Human Activity Recognition Using the 4D Spatiotemporal Shape Context Descriptor
Natasha Kholgade,Andreas Savakis +1 more
Integration of moment invariants and uniform local binary patterns for human activity recognition in video sequences
Swati Nigam,Ashish Khare +1 more