Single Shot Appearance Model (Ssam) for Multi-Target Tracking

Ullah, Mohib; Ullah, Habib; Cheikh, Faouzi Alaya

doi:10.2352/issn.2470-1173.2019.7.iriacv-466

Cited by 15 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jain et al [23] proposed a model based on a single deep convolutional neural network comprised of convolution layers and deep residual blocks. Ullah et al [24] trained a deep Siamese neural network with a contrastive loss to calculate the difference between image patches. The network has potential applications in tracking, image retrieval, and facial emotion recognition.…”

Section: Visual Signal Based Emotion Classificationmentioning

confidence: 99%

Facial Emotion Recognition Using Hybrid Features

Alreshidi

Ullah

2020

Informatics

Self Cite

View full text Add to dashboard Cite

Facial emotion recognition is a crucial task for human-computer interaction, autonomous vehicles, and a multitude of multimedia applications. In this paper, we propose a modular framework for human facial emotions’ recognition. The framework consists of two machine learning algorithms (for detection and classification) that could be trained offline for real-time applications. Initially, we detect faces in the images by exploring the AdaBoost cascade classifiers. We then extract neighborhood difference features (NDF), which represent the features of a face based on localized appearance information. The NDF models different patterns based on the relationships between neighboring regions themselves instead of considering only intensity information. The study is focused on the seven most important facial expressions that are extensively used in day-to-day life. However, due to the modular design of the framework, it can be extended to classify N number of facial expressions. For facial expression classification, we train a random forest classifier with a latent emotional state that takes care of the mis-/false detection. Additionally, the proposed method is independent of gender and facial skin color for emotion recognition. Moreover, due to the intrinsic design of NDF, the proposed method is illumination and orientation invariant. We evaluate our method on different benchmark datasets and compare it with five reference methods. In terms of accuracy, the proposed method gives 13% and 24% better results than the reference methods on the static facial expressions in the wild (SFEW) and real-world affective faces (RAF) datasets, respectively.

show abstract

Section: Visual Signal Based Emotion Classificationmentioning

confidence: 99%

Facial Emotion Recognition Using Hybrid Features

Alreshidi

Ullah

2020

Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The average of the gradients from the shared weights is used to update the weights as given in equations in (8).…”

Section: The Earlier Important Progress In Deep Learning Was Deepmentioning

confidence: 99%

“…However, for a seamless integration among the IoT networks, an elegant model is compulsory. A few models are proposed in the literature including the ones in [5][6][7][8]. However, most of the existing models were concern about certain networks.…”

Section: Introductionmentioning

confidence: 99%

The Internet of Things for Crowd Panic Detection

Ullah¹,

Altamimi²,

Ramadan³

2020

IJACSA

Self Cite

View full text Add to dashboard Cite

Crowd behavior detection is important for the smart cities applications such as people gathering for different events. However, it is a challenging problem due to the internal states of the crowd itself and the surrounding environment. This paper proposes a novel crowd behavior detection framework based on a number of parameters. We first exploit a computer vision approach based on scale invariant feature transform (SIFT) to classify the crowd behavior either into panic or normalness. We then consider a number of other parameters from the surroundings namely crowd coherency, social interaction, motion information, randomness in crowd speed, internal chaos level, crowd condition, crowd temporal history, and crowd vibration status along with time stamp. Subsequently, these parameters are fed to deep learning model during training stage and the behavior of the crowd is detected during the testing stage. The experimental results show that proposed method renders significant performance in terms of crowd behavior detection.

show abstract

“…Serious games are also called applied games and this concept of gaming is used by industries like defense [3], health care [4], emergency management [5], [6], education [7], exploration [8], city planning [9], engineering [10], and politics [11]. In addition to this, computer vision and deep learning based techniques can be exploited in gaming context to analyze performances of sports players through tracking [12], [13] in an virtual environment [14], detection [15], [16], analysing anomalous behaviour [17], [18], simulating individual [19], [20] and crowd behaviour [21]- [25] for public infrastructure design [26], [27], and a variety of other multi media applications [28], [29]. Fig.…”

Section: Introductionmentioning

confidence: 99%

Serious Games and Gamification: A Systematic Literature Review

Khan¹,

Khan²,

Safaev³

2020

Preprint

View full text Add to dashboard Cite

Keeping in mind the increasing trend and need for serious games in science education, we have done a systematic literature review. These papers show the trends and patterns of research carried out in this field from the year 2011 to 2020. Specifically, we investigated country-wise concentration and the most common evaluation methods. Literature is reviewed from IEEEexplore, Springer, and Scopus. Moreover, we discussed the role of Augmented Reality(AR) games in teaching physics. Lastly, we have discussed the positive and negative aspects of serious games in science education in particular, and the trend of using serious games in the past decade in education in general.

show abstract

Single Shot Appearance Model (Ssam) for Multi-Target Tracking

Cited by 15 publications

References 0 publications

Facial Emotion Recognition Using Hybrid Features

Facial Emotion Recognition Using Hybrid Features

The Internet of Things for Crowd Panic Detection

Serious Games and Gamification: A Systematic Literature Review

Contact Info

Product

Resources

About