Real-time gait biometrics for surveillance applications: A review

Parashar, Anubha; Parashar, Apoorva; Abate, Andrea F.; Shekhawat, Rajveer Singh; Rida, Imad

doi:10.1016/j.imavis.2023.104784

Cited by 17 publications

(2 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gait as a biometric can have many applications such as, 1) Surveillance and Security: Utilizing gait recognition for surveillance purposes as a method in video surveillance to accurately identify and monitor individuals in public spaces, airports, and vital infrastructure locations. [15], [16], [17] and 2) Law enforcement: through threat detections to increase the public safety incorporating from various threats, including acts of terrorism, incidents of mass shootings, and instances of suicide bomb [18], [19], [20]. 3) Healthcare: HGR is widely used in the field of the healthcare especially to discover gait abnormalities and fall detection of patients and elderly people [21], [22], [23].…”

Section: B Applicationsmentioning

confidence: 99%

Human Gait Recognition Based on Deep Learning: A Review

Atrushi,

Adnan Mohsin Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

Human gait recognition as a branch of biometric identification, has witnessed remarkable progress in recent years, thanks to the integration of deep learning techniques. This paper presents a comprehensive review of the latest advancements in the field, specifically focusing on the transformative role of deep learning methodologies. Recent research papers highlight novel approaches in gait recognition, including deferent models proposed that is consisted of using more than one approach together to increase the accuracy. Subsequently, we undertake a comprehensive investigation of the most relevant literature and present an analysis of gait recognition techniques employing deep learning. We discuss the models, systems, accuracy, applications, and datasets utilized in these studies, aiming to outline and structure the research landscape and literature in this domain. Methods for acquiring gait data are distinguished between capturing video frame, radar signals, or from wearable sensors as well as from the available online datasets that are large-scale and significantly contributed to the advancement of deep learning models. The study also shows the verity applications that can utilize human gait recognition to achieve certain goals.

show abstract

Section: B Applicationsmentioning

confidence: 99%

Human Gait Recognition Based on Deep Learning: A Review

Atrushi,

Adnan Mohsin Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

show abstract

“…A plethora of innovative studies on the Vision Transformer (ViT) structure is noteworthy, propelling the advancements of deep learning on various fronts. Researchers have continuously enhanced ViT's image feature extraction capabilities by introducing more efficient Transformer variants [11], such as Convolutional Visual Transformer (CVIT) and Pyramid Layered Networks (PDN) [12]. Novel attention mechanisms [13]- [15] have been designed to comprehensively analyze image information, facilitating more precise target recognition.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Crop Disease Detection With EfficientNet Convolutional Group-Wise Transformer

Feng,

Ong,

Teh

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Crop diseases, as one of the major problems in global agricultural production, lead to crop yield reduction, death, and even total extinction, with serious impacts on farmers and the food supply. Traditionally, crop diseases are identified by visual inspection and based on the experience of farmers and agricultural experts, a method that not only consumes human resources but also has a certain degree of subjectivity and inaccuracy. The development of artificial intelligence technology successfully achieves real-time monitoring, automatic identification, and intelligent decision by combining the Internet of Things (IoT) technology and cloud computing technology. Herein, we proposed an EfficientNet Convolutional Group-Wise Transformer (EGWT) architecture. The local features of crop leaf images are extracted by EfficientNet convolution and then input into a group-wise transformer architecture. In the group-wise transformer process, the input features are divided into multiple groups. An attention mechanism is used within each group to calculate correlations between features. After calculating the intra-group attention, the output features of each group are stitched together to form the final output features. Our proposed model achieves 99.8% accuracy on the PlantVillage dataset, 86.9% accuracy on the cassava dataset, and 99.4% accuracy on the Tomato leaves dataset, with the least number of parameters 23.04M in the state-of-the-art convolutional combinatorial transformer hybrid model. The experimental results indicate that the proposed model has the best accuracy and optimal model complexity so far compared to other neural networks based on CNN, transformer, and the hybrid structure of CNN and transformer.

show abstract

Smart Gait Healthcare Applications: Walking Status and Gait Biometrics

Chen,

Lee

2024

SpringerBriefs in Applied Sciences and Technology

View full text Add to dashboard Cite

Real-time gait biometrics for surveillance applications: A review

Cited by 17 publications

References 68 publications

Human Gait Recognition Based on Deep Learning: A Review

Human Gait Recognition Based on Deep Learning: A Review

Enhanced Crop Disease Detection With EfficientNet Convolutional Group-Wise Transformer

Smart Gait Healthcare Applications: Walking Status and Gait Biometrics

Contact Info

Product

Resources

About