Real time human face detection and tracking

Chatrath, Jatin; Gupta, Pankaj; Ahuja, Puneet; Goel, Aryan; Arora, Shaifali Madan

doi:10.1109/spin.2014.6777046

Cited by 27 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early algorithms for robust and fast human and face detection were published in the beginning of the millennium [10], [11]. Still today, OpenCV library based on the Viola-Jones algorithm [11] is routinely employed in many real-time face detection techniques resulting in augmented face region in the image data stream [12]- [15].…”

Section: Related Workmentioning

confidence: 99%

Embedded Implementation of a Deep Learning Smile Detector

Ghazi

Happonen

Boutellier

et al. 2018

2018 7th European Workshop on Visual Information Processing (EUVIP)

View full text Add to dashboard Cite

In this paper we study the real time deployment of deep learning algorithms in low resource computational environments. As the use case, we compare the accuracy and speed of neural networks for smile detection using different neural network architectures and their system level implementation on NVidia Jetson embedded platform. We also propose an asynchronous multithreading scheme for parallelizing the pipeline. Within this framework, we experimentally compare thirteen widely used network topologies. The experiments show that low complexity architectures can achieve almost equal performance as larger ones, with a fraction of computation required.

show abstract

Section: Related Workmentioning

confidence: 99%

Embedded Implementation of a Deep Learning Smile Detector

Ghazi

Happonen

Boutellier

et al. 2018

2018 7th European Workshop on Visual Information Processing (EUVIP)

View full text Add to dashboard Cite

show abstract

“…The authors in [15] discuss some famous and basic algorithms of object detection and tracking and also give their general applications and results.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Empowering Blind Tennis via Music

Pirani¹,

Kulkarni²,

Ali³

et al. 2018

IJCA

View full text Add to dashboard Cite

Lawn Tennis is one of the most popular sports all around the world. Especially, during last few years, a great deal of highend technology is being used to follow every point of every match of the Tennis Tournaments. Unfortunately, visually challenged players cannot take the pleasure of following and playing this sport completely as they face the challenge of determining the position of the ball accurately on the court which increases their stress and anxiety levels and hence numerous players eventually give up. The training period is difficult not only for the visually-impaired players but also the coaches because the players have to be trained rigorously to determine how the ball is being hit, from where it is currently, and where the ball will land on the court. So, there is a high need for a system that makes the sport more enjoyable and less stressful for the visually-impaired people. Moreover, the existing system to play the sport of Blind Tennis makes use of sound balls, special balls that rattle when they bounce. This paper presents a comprehensive survey of Blind Tennis, the existing technologies that analyze the game and propose a system that would enable the visually-impaired people to not only play the sport but also follow the sport with enthusiasm just like general public by following every point of the match closely.

show abstract

“…When used in its real form, AdaBoost learning function boosts the performance of a simple learning algorithm (sometimes called weak). AdaBoost has capability to achieve large margins rapidly that is one of the key features of this algorithm [12].…”

Section: Adaboost For Feature Selectionmentioning

confidence: 99%