Using graph cuts in GPUs for color based human skin segmentation

Lattari, Lucas Grassano; Montenegro, Anselmo; Conci, Aura; Clua, Esteban; Mota, Virgínia Fernandes; Vieira, Marcelo Bernardes; Lizarraga, Gabriel

doi:10.3233/ica-2011-0357

Cited by 9 publications

(9 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, a face detection algorithm is a crucial step in the proposed technique. Initially, algorithms based on skin color segmentation [15] were considered because of their reduced computational cost, which is a requirement for implementation in mobile platforms. However, experiments using the mobile camera showed that this approach is not robust to noise, variations in environment, and ethnic differences.…”

Section: Face Detectionmentioning

confidence: 99%

Enhanced real-time head pose estimation system for mobile device

Neto

Duarte

Barreto

et al. 2014

ICA

View full text Add to dashboard Cite

This article proposes a real-time Head Pose Estimation (HPE) technique designed to be used in mobile devices. The method enables the interaction between the user and mobile devices using the device's inbuilt camera. The proposed technique is composed of different computer vision methods, which were optimized to operate in a restricted environment. The method has three Degrees of Freedom (DOF), roll, yaw and pitch. The HPE is obtained using these movements. Experiments were conducted using 363 videos of 27 different people taken in varied scenarios with changes in illumination and background. The results demonstrate the robustness and efficiency of the proposed method.

show abstract

Section: Face Detectionmentioning

confidence: 99%

Enhanced real-time head pose estimation system for mobile device

Neto

Duarte

Barreto

et al. 2014

ICA

View full text Add to dashboard Cite

show abstract

“…Examples of works in the area of GPU implementations are [6,17,18]. Using a GPU, it is even possible to run complex algorithms like graph cuts in realtime as presented by Lattari et al [17].…”

Section: Related Workmentioning

confidence: 99%

“…Using a GPU, it is even possible to run complex algorithms like graph cuts in realtime as presented by Lattari et al [17].…”

Section: Related Workmentioning

confidence: 99%

Parallel implementation of a real-time high dynamic range video system

Guthier

Kopf

Wichtlhuber

et al. 2014

ICA

View full text Add to dashboard Cite

Abstract. This article describes the use of the parallel processing capabilities of a graphics chip to increase the processing speed of a high dynamic range (HDR) video system. The basis is an existing HDR video system that produces each frame from a sequence of regular images taken in quick succession under varying exposure settings. The image sequence is processed in a pipeline consisting of: shutter speeds selection, capturing, color space conversion, image registration, HDR stitching, and tone mapping. This article identifies bottlenecks in the pipeline and describes modifications to the algorithms that are necessary to enable parallel processing. Time-critical steps are processed on a graphics processing unit (GPU). The resulting processing time is evaluated and compared to the original sequential code. The creation of an HDR video frame is sped up by a factor of 15 on the average.

show abstract

“…The use of GPU [7] has always been related to graphic or image applications since it offers the possibility of carrying out the same operations over multiple data, such as applications of object tracking [26], image sequences analysis [11], crowd simulation [42], or even a new approach for automatic human skin segmentation [22].…”

Section: State Of the Art And Objectivesmentioning

confidence: 99%

Multichannel massive audio processing for a generalized crosstalk cancellation and equalization application using GPUs

Belloch

González

Martínez-Zaldívar

et al. 2013

ICA

View full text Add to dashboard Cite

Multichannel acoustic signal processing has undergone major development in recent years due to the increased complexity of current audio processing applications, which involves the processing of multiple sources, channels, or filters. A general scenario that appears in this context is the immersive reproduction of binaural audio without the 1 use of headphones, which requires the use of a crosstalk canceler. However, Generalized Crosstalk Cancellation and Equalization (GCCE) requires high computing capacity, which is a considerable limitation for real-time applications. This paper discusses the design and implementation of all the processing blocks of a multichannel convolution on a GPU for real-time applications. To this end, a very efficient filtering method using specific data structures is proposed, which takes advantage of overlap-save filtering and filter fragmentation. It has been shown that, for a real-time application with 22 inputs and 64 outputs, the system is capable of managing 1408 filters of 2048 coefficients with a latency time less than 6 ms. The proposed GPU implementation can be easily adapted to any acoustic environment, demonstrating the validity of these co-processors for managing intensive multichannel audio applications.

show abstract

Using graph cuts in GPUs for color based human skin segmentation

Cited by 9 publications

References 53 publications

Enhanced real-time head pose estimation system for mobile device

Enhanced real-time head pose estimation system for mobile device

Parallel implementation of a real-time high dynamic range video system

Multichannel massive audio processing for a generalized crosstalk cancellation and equalization application using GPUs

Contact Info

Product

Resources

About