Figure - available from: Journal of Imaging (J. Imaging)
This content is subject to copyright.
S4AllCities schema with ICCS (VAEC via NVIDIA Jetson RTX2) and Tekniker (I.MX8M Plus) edge platforms transmitting video streaming and the number of people detected.
Source publication
Advances in Artificial intelligence (AI) and embedded systems have resulted on a recent increase in use of image processing applications for smart cities’ safety. This enables a cost-adequate scale of automated video surveillance, increasing the data available and releasing human intervention. At the same time, although deep learning is a very inte...
Citations
... These works are relevant to this study due to their emphasis on low-power object detection using variants of the YOLO architecture. For example, a human detection system was deployed on an embedded platform with an i.MX NPU [24]. In the context of unmanned aerial vehicles (UAVs), YOLOv3-Tiny was executed on an NPU-based platform achieving a mAP of 0.591 with only 6 million parameters [25], while another UAV implementation using YOLOv3 reached a mAP of 0.897 [26]. ...
This paper explores the application of artificial intelligence on edge devices to enhance security in critical infrastructures, with a specific focus on the use case of a battery-powered mobile system for fire detection in tunnels. The study leverages the YOLOv5 convolutional neural network (CNN) for real-time detection, focusing on a comparative analysis across three low-power platforms, NXP i.MX93, Xilinx Kria KV260, and NVIDIA Jetson Orin Nano, evaluating their performance in terms of detection accuracy (mAP), inference time, and energy consumption. The paper also presents a methodology for implementing neural networks on various platforms, aiming to provide a scalable approach to edge artificial intelligence (AI) deployment. The findings offer valuable insights into the trade-offs between computational efficiency and power consumption, guiding the selection of edge computing solutions in security-critical applications.
... For UAV control, different SoMs can be used such as NXP I.MX8M [209], Rockchip RK3399 [210], Qualcomm Snapdragon [211], and STM32 [212]. Regarding the work in reference [213], NXP I.MX8M provides a custom AI video-processing-focused hardware platform for the deployment of DL models. By integrating a Neural Co-Processing Unit (NCU), it enables the process of 2.3 tera operations per second, hence considerably reducing the processing time for the implemented DL models used in smart cities' smart-camera-systems. Similarly, in [214], Rockchip RK3399 serves as the SoM for video data (recorded in real time by a UAV) processing, providing more speed and prohibiting delays in video transmission in 5G networks. ...
The evolving technologies regarding Unmanned Aerial Vehicles (UAVs) have led to their extended applicability in diverse domains, including surveillance, commerce, military, and smart electric grid monitoring. Modern UAV avionics enable precise aircraft operations through autonomous navigation, obstacle identification, and collision prevention. The structures of avionics are generally complex, and thorough hierarchies and intricate connections exist in between. For a comprehensive understanding of a UAV design, this paper aims to assess and critically review the purpose-classified electronics hardware inside UAVs, each with the corresponding performance metrics thoroughly analyzed. This review includes an exploration of different algorithms used for data processing, flight control, surveillance, navigation, protection, and communication. Consequently, this paper enriches the knowledge base of UAVs, offering an informative background on various UAV design processes, particularly those related to electric smart grid applications. As a future work recommendation, an actual relevant project is openly discussed.
The rapid advancement of edge artificial intelligence (AI) has unlocked transformative applications across various domains. However, it also poses significant challenges in efficiently updating models on edge devices, which are often constrained by limited computational and communication resources. Here, we present low-rank adaptation method for Edge AI (LoRAE), Leveraging low-rank decomposition of convolutional neural networks (CNNs) weight matrices, LoRAE reduces the number of updated parameters to approximately 4% of traditional full-parameter updates, effectively mitigating the computational and communication challenges associated with model updates. Extensive experiments across image classification, object detection, and image segmentation tasks demonstrate that LoRAE significantly decreases the scale of trainable parameters while maintaining or even enhancing model accuracy. Using the YOLOv8x model, LoRAE achieves parameter reductions of 86.1%, 98.6%, and 94.1% across the three tasks, respectively, without compromising accuracy. These findings highlight the potential of LoRAE as an efficient and precise solution for resource-constrained edge AI systems.
The rapid advancement of smart cities, driven by innovative communication and information technologies (ICT), has transformed urban management. This paper introduces the robust SmartCityAI Lakehouse, a hybrid framework specifically designed to implement smart city solutions in IKN, the New Capital City of Indonesia. The proposed architecture seamlessly integrates diverse data sources and supports a wide range of applications, including real-time AI-driven transportation management, energy optimization, public safety enhancement, waste and water management, environmental monitoring, and air quality control. By leveraging both on-premises processing and scalable cloud infrastructure, this framework enhances urban sustainability and improves the quality of life for citizens. The paper also explores the key benefits and challenges of deploying this architecture, providing practical strategies for its implementation in complex urban environments.
