scholarly journals Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU

2014 ◽  
Vol 2014 ◽  
pp. 1-13
Author(s):  
Jinwei Wang ◽  
Xirong Ma ◽  
Yuanping Zhu ◽  
Jizhou Sun
Keyword(s):  
Real Time ◽  
Graphics Processing Units ◽  
Parallel Implementation ◽  
Model Fitting ◽  
Parallel Architecture ◽  
High Dimensional ◽  
Appearance Model ◽  
Active Appearance Model ◽  
Fitting Algorithm ◽  
Active Appearance

The active appearance model (AAM) is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs) that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA) on the Nvidia’s GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures.

scholarly journals A Modified Active Appearance Model Based on an Adaptive Artificial Bee Colony

2014 ◽  
Vol 2014 ◽  
pp. 1-16 ◽  
Author(s):  
Mohammed Hasan Abdulameer ◽  
Siti Norul Huda Sheikh Abdullah ◽  
Zulaiha Ali Othman
Keyword(s):  
Face Recognition ◽  
Model Fitting ◽  
Optimization Method ◽  
Appearance Model ◽  
Active Appearance Model ◽  
Abc Algorithm ◽  
Model Based ◽  
Bee Colony ◽  
Active Appearance ◽  
Recognition Technique

Active appearance model (AAM) is one of the most popular model-based approaches that have been extensively used to extract features by highly accurate modeling of human faces under various physical and environmental circumstances. However, in such active appearance model, fitting the model with original image is a challenging task. State of the art shows that optimization method is applicable to resolve this problem. However, another common problem is applying optimization. Hence, in this paper we propose an AAM based face recognition technique, which is capable of resolving the fitting problem of AAM by introducing a new adaptive ABC algorithm. The adaptation increases the efficiency of fitting as against the conventional ABC algorithm. We have used three datasets: CASIA dataset, property 2.5D face dataset, and UBIRIS v1 images dataset in our experiments. The results have revealed that the proposed face recognition technique has performed effectively, in terms of accuracy of face recognition.

scholarly journals A Review Article for Active Appearance Model Fitting Based on Optimization Methods

2016 ◽  
Vol 12 (10) ◽  
pp. 1057-1063
Author(s):  
Mohammed Hasan Abdulameer ◽  
Dhurgham A. Mohammed ◽  
Hassan Farhan Rashag ◽  
Hasanein D. Rjeib
Keyword(s):  
Model Fitting ◽  
Optimization Methods ◽  
Review Article ◽  
Appearance Model ◽  
Active Appearance Model ◽  
Active Appearance

scholarly journals Real-time 3D face tracking based on active appearance model constrained by depth data

2014 ◽  
Vol 32 (11) ◽  
pp. 860-869 ◽  
Author(s):  
Nikolai Smolyanskiy ◽  
Christian Huitema ◽  
Lin Liang ◽  
Sean Eron Anderson
Keyword(s):  
Real Time ◽  
Face Tracking ◽  
Appearance Model ◽  
Active Appearance Model ◽  
3D Face ◽  
Depth Data ◽  
3D Face Tracking ◽  
Active Appearance

scholarly journals Tinjauan Literatur Sistematik Tentang Penerapan Motion Capture Pada Proses Produksi Animasi

2020 ◽  
Vol 6 (2) ◽  
pp. 28-34
Author(s):  
Qolbun Salim As Shidiqi ◽  
Ema Utami ◽  
Amir Fatah Sofyan
Keyword(s):  
Real Time ◽  
Motion Capture ◽  
Image Alignment ◽  
Appearance Model ◽  
Active Appearance Model ◽  
Face Modeling ◽  
Markerless Motion Capture ◽  
Active Appearance

Motion capture adalah metode atraktif untuk membuat gerakan dalam animasi komputer. Mocap dapat menyajikan gerakan yang realistis dan memberikan nuansa dan detil khususnya pada pameran tertentu. Mocap memungkinkan bagi aktor dan sutradara untuk bekerja bersama membuat gerakan tertentu yang diinginkan, yang itu akan sulit dilakukan pada animator yang bekerja secara manual. Teknologi motion capture dibutuhkan dalam berbagai aplikasi, khususnya animasi yang terus berkembang pesat. Teknik yang digunakan dapat menggunakan penanda maupun tanpa penanda (markerless). Ada banyak algoritma untuk motion capture salah satunya metode Active Appearance Model (AAM). Metode ini mampu melakukan capture titik-titik landmark pada wajah dengan baik. Penelitian ini diarahkan untuk mengembangkan teknik markerless motion capture dengan menggunakan AAM pada wajah. Dari metode yang ada perlu diketahui mana metode yang paling efektif untuk digunakan, untuk itu penelitian ini membandingkan dua metode AAM, yaitu IAIA (Inverse Additive Image Alignment) dan ICIA (Inverse Compositional Image Alignment) yang dilakukan secara real time. AAM merupakan metode yang sering digunakan pada pemodelan wajah (face modeling). Namun, AAM dapat juga bermanfaat untuk implementasi lainnya. Dalam aplikasi tertentu, langkah pertama adalah mencocokan AAM dengan gambar, yakni parameter model ditemukan terlebih dahulu untuk memaksi-malkan kecocokan antara contoh model dengan gambar input.

Sign in / Sign up

Export Citation Format

Share Document