Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU

Abstract

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.

Intensity Profiles in Active Shape Model

“…By varying b, one can vary the shape X using Eq. (6). The variance of b, across the training set is given by .…”

“…Zhao et al [5] add a process of searching the most similar image to the target object from the training sample set and uses the shape model of the similar image instead of the average shape model to approximately express target object model. Wang et al [6] evoke the fine grain parallelism and applies it to the matching algorithm and reformulate it as a parallelizable algorithm. The parallel version of matching algorithm is implemented in a multi-core (CPU/GPU) environment.…”

Puzzlement Detection from Facial Expression Using Active Appearance Models and Support Vector Machines

“…We chose 32,768, because it is approximately the size of face area (36,000 pixels) in the frame, and it is integer multiples of 4,096, which can make our parallel algorithm of the AAM fitting on GPUs [28] achieves better real time performance than other length which is not integer multiples of 4,096. The example of such normalized textures is shown in the fourth column of Fig.…”

Algoritmos para agricultura de precisión utilizando computación de alto rendimiento

“…El kit de herramientas incluye Nsight Eclipse Edition, herramientas de depuración y creación de perfiles, incluida Nsight Compute, y una cadena de herramientas para aplicaciones de compilación cruzada (NVIDIA, 2015; J. Wang et al, 2014).…”