Real-Time Human Detection Using Deep Learning on Embedded Platforms: A Review

Abstract

The detection of an object such as a human is very important for image understanding in the field of computer vision. Human detection in images can provide essential information for a wide variety of applications in intelligent systems. In this paper, human detection is carried out using deep learning that has developed rapidly and achieved extraordinary success in various object detection implementations. Recently, several embedded systems have emerged as powerful computing boards to provide high processing capabilities using the graphics processing unit (GPU). This paper aims to provide a comprehensive survey of the latest achievements in this field by using deep learning techniques in the embedded platforms. NVIDIA Jetson was chosen as a low power system designed to accelerate deep learning applications. This review highlights the performance of human detection models such as PedNet, multiped, SSD MobileNet V1, SSD MobileNet V2, and SSD inception V2 on edge computing. This survey provides an overview of these methods and compares their performance in accuracy and computation time for real-time applications. The experimental results show that the SSD MobileNet V2 model provides the highest accuracy with the fastest computation time compared to other models in our video datasets with several scenarios.

Benchmarking edge computing devices for grape bunches and trunks detection using accelerated object detection single shot multibox deep learning models

“…The authors could have a low accuracy drop (about 1 %) in the quantisation process for the NVIDIA Jetson TX2. The inference speed was about ten times slower in the NVIDIA Jetson TX2 (running at 18 FPS), as expected, but consumed 20 times less power, consuming only about 8 W. Suzen et al [21], Chiu et al [22], Rahmaniar and Hernawan [23], Martinez et al [24] also benchmark DL models efficiency between NVIDIA Jetson embedded boards. The NVIDIA Jetson AGX Xavier was the fastest board in the family but also the most powerexpensive.…”

Incremental and parallel proximal SVM algorithm tailored on the Jetson Nano for the ImageNet challenge

“…Because of tremendous growth in manufacturing powerful, low-cost embedded devices, the edge computing becomes a popular choice for machine learning and IoT projects (Ajani et al , 2021; Koul et al , 2019; Kulkarni et al , 2020; Kurniawan, 2021; Latif et al , 2021; Mazzia et al , 2020; Norris, 2020; Pooyandeh and Sohn, 2021; Rahmaniar and Hernawan, 2021; Taylor et al , 2018). The health applications, computer vision and deep learning are tailored on the Jetson Nano (Black, 2022; Budek, 2021; Franklin, 2019; Mishra and Devleker, 2021; Mittal, 2019; Mohan et al , 2021; Rehman et al , 2021; Zualkernan et al , 2022) and the Raspberry Pi (Daher et al , 2021; Glegola et al , 2021; Iodice, 2018).…”

“…For example, the Jetson Nano (Quad-core ARM A57 @ 1.43 GHz, 128-core NVIDIA Maxwell architecture-based GPU, 4 GB RAM) is only US$90. And then, the edge computing becomes an increasingly popular choice for machine learning and IoT projects, as illustrated in Ajani et al (2021), Koul et al (2019), Kulkarni et al (2020), Kurniawan (2021), Latif et al (2021), Mazzia et al (2020), Norris (2020), Pooyandeh and Sohn (2021), Rahmaniar and Hernawan (2021) and Taylor et al (2018).…”

Survey Paper Artificial and Computational Intelligence in the Internet of Things and Wireless Sensor Network

“…NN (Neural Network) is a computational intelligence inspired by the brain biological neural networks that mimic brain behavior from living things. NN methods have been used to solve many problems, from motor control [106], human detection [107], forecasting [108], [109], and many more. The system will do its job by considering previously accepted examples (called data training) [110].…”