A Novel Hardware Architecture for Human Detection using HOG-SVM Co-Optimization

Nguyen, Ngo-Doanh; Bui, Duy-Hieu; Tran, Xuan‐Tu

doi:10.1109/apccas47518.2019.8953123

Cited by 14 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This subsection gives a mathematical outline of both the link budget predictions, as well as the proposed AI framework [24][25][26][27][28][29]. Regarding the link budget predictions this would include Free Space Path Loss (FSPL), Receiver Signal Strength (RSS), Signal to Interference and Noise Ratio (SINR), and Throughput.…”

Section: Mathematical Calculationmentioning

confidence: 99%

“…Throughput is the amount of data received by the user in a unit of time. Therefore, equations of the link budget predictions can be seen as per equations ( 1 The mathematical representation of the proposed AI framework that include HOG and OpenCV techniques can be seen as per equations ( 5) to (25):…”

Section: Mathematical Calculationmentioning

confidence: 99%

“…If the source image size was 224x244 pixels so it will be return to 224x224 pixels after being manipulated to detected people. 𝑑𝑠𝑡 = (𝐷 𝑥 𝑠𝑟𝑐)² ⋅ 𝐷 𝑦𝑦 𝑠𝑟𝑐 + (𝐷 𝑦 𝑠𝑟𝑐)² ⋅ 𝐷 𝑥𝑥 𝑠𝑟𝑐 − 2𝐷 𝑥 𝑠𝑟𝑐 ⋅ 𝐷 𝑦 𝑠𝑟𝑐 ⋅ 𝐷 𝑥𝑦 𝑠𝑟𝑐 (25) where 𝐷 x , 𝐷 y are the source image derivatives, 𝐷 xx , 𝐷 yy are the delivered image derivatives, and 𝐷 xy is the mixed derivative of them.…”

Section: Mathematical Calculationmentioning

confidence: 99%

See 2 more Smart Citations

Developing CubeSat and AI Framework for Crowd Management Case of Short-Term Large-Scale Events

Almalki¹,

Mutawi²,

Turkistani³

et al. 2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Many consequences can be resulted in mismanagement of crowd, which might get people injured or even lose their lives. Thus, crowd management helps in controlling overcrowded areas during events, and allowing authorities to monitor, manage and reduce incidents. Space science and technology have made huge leap in crowd management, let alone when this technology integrated with Artificial intelligent. Hence, space-based systems like CubeSats are seen as the best approach to help monitoring and providing various reasons. For instance, wide coverage footprint, collect specific area data simultaneously, assist in aerial photography, as well as providing wide range of wireless communications services that can integrate appropriately with AI and wearable devices. This work aims to design a CubeSat vehicle to manage crowds during short-term, large-scale events. The proposed system is, also, coupled with AI framework along with the camera and wearable devices to monitor the crowds' performance continuously by relying on two aspects: Firstly, aerial imaging (e.g., photos and videos). Secondly, using wearable devices that can be worn to monitor vital signs of crowds. Moreover, the proposed system can independently relieve congestion, as well as notify the ground controller of all problems to take further actions. The obtained results confirm that the proposed innovative solution is for crowd management with accuracy reached 95%, and MSE equal to 0.049.

show abstract

Section: Mathematical Calculationmentioning

confidence: 99%

Section: Mathematical Calculationmentioning

confidence: 99%

Section: Mathematical Calculationmentioning

confidence: 99%

See 1 more Smart Citation

Developing CubeSat and AI Framework for Crowd Management Case of Short-Term Large-Scale Events

Almalki¹,

Mutawi²,

Turkistani³

et al. 2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…After creating 3D shapes, Histogram of Oriented Gradients (HOG) is applied to extract unique features. In order to apply HOG [77], all images are first preprocessed to make their dimensions 64 × 128 pixels. Bounding boxes are drawn around each human in the image and the gradient of each human in the image is calculated separately.…”

Section: D Cartesian-plane Featuresmentioning

confidence: 99%

Modeling Two-Person Segmentation and Locomotion for Stereoscopic Action Identification: A Sustainable Video Surveillance System

et al. 2021

View full text Add to dashboard Cite

Due to the constantly increasing demand for automatic tracking and recognition systems, there is a need for more proficient, intelligent and sustainable human activity tracking. The main purpose of this study is to develop an accurate and sustainable human action tracking system that is capable of error-free identification of human movements irrespective of the environment in which those actions are performed. Therefore, in this paper we propose a stereoscopic Human Action Recognition (HAR) system based on the fusion of RGB (red, green, blue) and depth sensors. These sensors give an extra depth of information which enables the three-dimensional (3D) tracking of each and every movement performed by humans. Human actions are tracked according to four features, namely, (1) geodesic distance; (2) 3D Cartesian-plane features; (3) joints Motion Capture (MOCAP) features and (4) way-points trajectory generation. In order to represent these features in an optimized form, Particle Swarm Optimization (PSO) is applied. After optimization, a neuro-fuzzy classifier is used for classification and recognition. Extensive experimentation is performed on three challenging datasets: A Nanyang Technological University (NTU) RGB+D dataset; a UoL (University of Lincoln) 3D social activity dataset and a Collective Activity Dataset (CAD). Evaluation experiments on the proposed system proved that a fusion of vision sensors along with our unique features is an efficient approach towards developing a robust HAR system, having achieved a mean accuracy of 93.5% with the NTU RGB+D dataset, 92.2% with the UoL dataset and 89.6% with the Collective Activity dataset. The developed system can play a significant role in many computer vision-based applications, such as intelligent homes, offices and hospitals, and surveillance systems.

show abstract

“…These HAR systems can use machine learning or deep learning techniques to decode the activities of daily living by extracting data from motion, ambient, or vision-based sensors [13][14][15][16]. Modern smart devices manipulate the data and thus cannot be utilized…”

Section: Introductionmentioning

confidence: 99%

Biosensor-Based Multimodal Deep Human Locomotion Decoding via Internet of Healthcare Things

Javeed,

Abdelhaq,

Algarni

et al. 2023

Micromachines

View full text Add to dashboard Cite

Multiple Internet of Healthcare Things (IoHT)-based devices have been utilized as sensing methodologies for human locomotion decoding to aid in applications related to e-healthcare. Different measurement conditions affect the daily routine monitoring, including the sensor type, wearing style, data retrieval method, and processing model. Currently, several models are present in this domain that include a variety of techniques for pre-processing, descriptor extraction, and reduction, along with the classification of data captured from multiple sensors. However, such models consisting of multiple subject-based data using different techniques may degrade the accuracy rate of locomotion decoding. Therefore, this study proposes a deep neural network model that not only applies the state-of-the-art Quaternion-based filtration technique for motion and ambient data along with background subtraction and skeleton modeling for video-based data, but also learns important descriptors from novel graph-based representations and Gaussian Markov random-field mechanisms. Due to the non-linear nature of data, these descriptors are further utilized to extract the codebook via the Gaussian mixture regression model. Furthermore, the codebook is provided to the recurrent neural network to classify the activities for the locomotion-decoding system. We show the validity of the proposed model across two publicly available data sampling strategies, namely, the HWU-USP and LARa datasets. The proposed model is significantly improved over previous systems, as it achieved 82.22% and 82.50% for the HWU-USP and LARa datasets, respectively. The proposed IoHT-based locomotion-decoding model is useful for unobtrusive human activity recognition over extended periods in e-healthcare facilities.

show abstract

A Novel Hardware Architecture for Human Detection using HOG-SVM Co-Optimization

Cited by 14 publications

References 10 publications

Developing CubeSat and AI Framework for Crowd Management Case of Short-Term Large-Scale Events

Developing CubeSat and AI Framework for Crowd Management Case of Short-Term Large-Scale Events

Modeling Two-Person Segmentation and Locomotion for Stereoscopic Action Identification: A Sustainable Video Surveillance System

Biosensor-Based Multimodal Deep Human Locomotion Decoding via Internet of Healthcare Things

Contact Info

Product

Resources

About