Heterogeneous Acceleration of HAR Applications

Rodriguez-Borbon, Jose M.; Ma, Xiaoyin; Roy-Chowdhury, Amit K.; Najjar, Walid

doi:10.1109/tcsvt.2019.2895304

Cited by 4 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies on heterogeneous parallel processing are not limited to CPUs and GPUs [51], [52]. Rodriguez-Borbon et al [51] use a field-programmable gate array (FPGA) along with CPUs and GPUs to partition and pipeline applications, resulting in an increased processing speed and energy efficiency compared to GPU homogeneous system. Yang et al [52] propose a heterogeneous parallel processor containing many processing elements to increase processing speed by parallelizing multiple tasks.…”

Section: B Optimization Of Deep Learning Inference On Heterogeneous S...mentioning

confidence: 99%

CP-CNN: Computational Parallelization of CNN-based Object Detectors in Heterogeneous Embedded Systems for Autonomous Driving

et al. 2023

View full text Add to dashboard Cite

The success of research using convolutional neural network (CNN)-based camera sensor processing for autonomous driving has accelerated the development of autonomous driving vehicles. Since autonomous driving algorithms require high-performance computing for fast and accurate perception, a heterogeneous embedded platform consisting of a graphics processing unit (GPU) and a power-efficient dedicated deep learning accelerator (DLA) has been developed to efficiently implement deep learning algorithms in limited hardware environments. However, because the hardware utilization of these platforms remains low, performance differences such as processing speed and power efficiency between the heterogeneous platform and an embedded platform with only GPUs remain insignificant. To address this problem, this paper proposes an optimization technique that fully utilizes the available hardware resources in heterogeneous embedded platforms using parallel processing on DLA and GPU. Our proposed power-efficient network inference method improves processing speed without losing accuracy based on analyzing the problems encountered when dividing the networks between DLA and GPU for parallel processing. Moreover, the high compatibility of the proposed method is demonstrated by applying the proposed method to various CNN-based object detectors. The experimental results show that the proposed method increases the processing speed by 77.8%, 75.6%, and 55.2% and improves the power efficiency by 84%, 75.9%, and 62.3% on YOLOv3, SSD, and YOLOv5 networks, respectively, without an accuracy penalty.INDEX TERMS Autonomous vehicle, convolutional neural network, embedded platform, low-power design, parallel processing, real-time system.

show abstract

Section: B Optimization Of Deep Learning Inference On Heterogeneous S...mentioning

confidence: 99%

CP-CNN: Computational Parallelization of CNN-based Object Detectors in Heterogeneous Embedded Systems for Autonomous Driving

et al. 2023

View full text Add to dashboard Cite

show abstract

“…HAR has been studied for applications in healthcare monitoring, smart homes, security, medical imaging, robot/ human interaction, personal assistants, and surveillance [18][19][20]. Many researchers have discussed various HAR approaches based on the technologies or algorithms used for activity recognition [21][22][23][24][25].…”

Section: Related Workmentioning

confidence: 99%

HIT HAR: Human Image Threshing Machine for Human Activity Recognition Using Deep Learning Models

Poulose

Kim

Han

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In recent days, research in human activity recognition (HAR) has played a significant role in healthcare systems. The accurate activity classification results from the HAR enhance the performance of the healthcare system with broad applications. HAR results are useful in monitoring a person’s health, and the system predicts abnormal activities based on user movements. The HAR system’s abnormal activity predictions provide better healthcare monitoring and reduce users’ health issues. The conventional HAR systems use wearable sensors, such as inertial measurement unit (IMU) and stretch sensors for activity recognition. These approaches show remarkable performances to the user’s basic activities such as sitting, standing, and walking. However, when the user performs complex activities, such as running, jumping, and lying, the sensor-based HAR systems have a higher degree of misclassification results due to the reading errors from sensors. These sensor errors reduce the overall performance of the HAR system with the worst classification results. Similarly, radiofrequency or vision-based HAR systems are not free from classification errors when used in real time. In this paper, we address some of the existing challenges of HAR systems by proposing a human image threshing (HIT) machine-based HAR system that uses an image dataset from a smartphone camera for activity recognition. The HIT machine effectively uses a mask region-based convolutional neural network (R-CNN) for human body detection, a facial image threshing machine (FIT) for image cropping and resizing, and a deep learning model for activity classification. We demonstrated the effectiveness of our proposed HIT machine-based HAR system through extensive experiments and results. The proposed HIT machine achieved 98.53% accuracy when the ResNet architecture was used as its deep learning model.

show abstract

Leveraging Smart Sensors for Human Function Traceability

Kaur

Kumar

et al. 2023

2023 International Conference on Advancement in Computation &Amp; Computer Technologies (InCACCT)

View full text Add to dashboard Cite

Heterogeneous Acceleration of HAR Applications

Cited by 4 publications

References 50 publications

CP-CNN: Computational Parallelization of CNN-based Object Detectors in Heterogeneous Embedded Systems for Autonomous Driving

CP-CNN: Computational Parallelization of CNN-based Object Detectors in Heterogeneous Embedded Systems for Autonomous Driving

HIT HAR: Human Image Threshing Machine for Human Activity Recognition Using Deep Learning Models

Leveraging Smart Sensors for Human Function Traceability

Contact Info

Product

Resources

About