Search Results (92)

Blind and visually impaired (BVI) people face significant challenges in perception, navigation, and safety during travel. Existing infrastructure (e.g., blind lanes) and traditional aids (e.g., walking sticks, basic audio feedback) provide limited flexibility and interactivity for complex environments. To solve this problem, we propose a real-time travel assistance system based on deep learning. The hardware comprises an NVIDIA Jetson Nano controller, an Intel D435i depth camera for environmental sensing, and SG90 servo motors for feedback. To address embedded device computational constraints, we developed a lightweight object detection and segmentation algorithm. Key innovations include a multi-scale attention feature extraction backbone, a dual-stream fusion module incorporating the Mamba architecture, and adaptive context-aware detection/segmentation heads. This design ensures high computational efficiency and real-time performance. The system workflow is as follows: (1) the D435i captures real-time environmental data; (2) the processor analyzes this data, converting obstacle distances and path deviations into electrical signals; (3) servo motors deliver vibratory feedback for guidance and alerts. Preliminary tests confirm that the system can effectively detect obstacles and correct path deviations in real time, suggesting its potential to assist BVI users. However, as this is a work in progress, comprehensive field trials with BVI participants are required to fully validate its efficacy. Full article

This research addresses the optimization and deployment of convolutional neural networks for eyeglasses detection on low-power edge devices. Multiple convolutional neural network architectures were trained and evaluated using the FFHQ dataset, which contains annotated eyeglasses in the context of faces with diverse facial features and eyewear styles. Several post-training quantization techniques, including Float16, dynamic range, and full integer quantization, were applied to reduce model size and computational demand while preserving detection accuracy. The impact of model architecture and quantization methods on detection accuracy and inference latency was systematically evaluated. The optimized models were deployed and benchmarked on Raspberry Pi 5 and NVIDIA Jetson Orin Nano platforms. Experimental results show that full integer quantization reduces model size by up to 75% while maintaining competitive detection accuracy. Among the evaluated models, MobileNet architectures achieved the most favorable balance between inference speed and accuracy, demonstrating their suitability for real-time eyeglasses detection in resource-constrained environments. These findings enable efficient on-device eyeglasses detection, supporting applications such as virtual try-ons and IoT-based facial analysis systems. Full article

This research study proposes an indoor temperature regulation predictive optimal control system that entails the use of both deep reinforcement learning and the Modbus TCP communication protocol. The designed architecture comprises distributed sub-parts, namely, distributed room-level units as well as a centralized main-part AI controller for maximizing efficient HVAC management in single-family residences as well as small-sized buildings. The system utilizes an LSTM model for forecasting temperature trends as well as an optimized control action using an envisaged DQN with predicted states, sensors, as well as user preferences. InfluxDB is utilized for gathering real-time environmental data such as temperature and humidity, as well as consumed power, and storing it. The AI controller processes these data to infer control commands for energy efficiency as well as thermal comfort. Experimentation on an NVIDIA Jetson Orin Nano as well as on a Raspberry Pi 4 proved the efficacy of the system, utilizing 8761 data points gathered hourly over 2023 in Cheonan, Korea. An added hysteresis-based mechanism for controlling power was incorporated to limit device wear resulting from repeated switching. Results indicate that the AI-based control system closely maintains target temperature setpoints with negligible deviations, affirming that it is a scalable, cost-efficient solution for intelligent climate management in buildings. Full article

This research presents an IoT-empowered adaptive mobility framework that integrates high-dimensional gesture recognition with edge-cloud orchestration for safety-critical human–machine interaction. The system architecture establishes a three-tier IoT network: a perception layer with 60 GHz FMCW radar and TOF infrared arrays (12-node mesh topology, 15 cm baseline spacing) for real-time motion tracking; an edge intelligence layer deploying a time-aware neural network via NVIDIA Jetson Nano to achieve up to 99.1% recognition accuracy with latency as low as 48 ms under optimal conditions (typical performance: 97.8% ± 1.4% accuracy, 68.7 ms ± 15.3 ms latency); and a federated cloud layer enabling distributed model synchronization across 32 edge nodes via LoRaWAN-optimized protocols (κ = 0.912 consensus). A reconfigurable chassis with three operational modes (standing, seated, balance) employs IoT-driven kinematic optimization for enhanced adaptability and user safety. Using both radar and infrared sensors together reduces false detections to 0.08% even under high-vibration conditions (80 km/h), while distributed learning across multiple devices maintains consistent accuracy (variance < 5%) in different environments. Experimental results demonstrate 93% reliability improvement over HMM baselines and 3.8% accuracy gain over state-of-the-art LSTM models, while achieving 33% faster inference (48.3 ms vs. 72.1 ms). The system maintains industrial-grade safety certification with energy-efficient computation. Bridging adaptive mechanics with edge intelligence, this research pioneers a sustainable IoT-edge paradigm for smart mobility, harmonizing real-time responsiveness, ecological sustainability, and scalable deployment in complex urban ecosystems. Full article

Haze significantly degrades image quality by reducing contrast and blurring object boundaries, which impairs the performance of computer vision systems. Among various approaches, single-image dehazing remains particularly challenging due to the absence of depth information. While Vision Transformer (ViT)-based models have achieved remarkable results by leveraging multi-head attention and large effective receptive fields, their high computational complexity limits their applicability in real-time and embedded systems. To address this limitation, we propose MLKD-Net, a lightweight CNN-based model that incorporates a novel Multi-Head Large Kernel Block (MLKD), which is based on the Multi-Head Large Kernel Attention (MLKA) mechanism. This structure preserves the benefits of large receptive fields and a multi-head design while also ensuring compactness and computational efficiency. MLKD-Net achieves a PSNR of 37.42 dB on the SOTS-Outdoor dataset while using 90.9% fewer parameters than leading Transformer-based models. Furthermore, it demonstrates real-time performance with 55.24 ms per image (18.2 FPS) on the NVIDIA Jetson Orin Nano in TensorRT-INT8 mode. These results highlight its effectiveness and practicality for resource-constrained, real-time image dehazing applications. Full article

This study proposes an intelligent agricultural pest monitoring system that integrates mechanical control with deep learning to address issues in traditional systems, such as pest accumulation interference, image contrast degradation under complex lighting, and poor balance between model accuracy and real-time performance. A three-axis coordinated separation device is employed, achieving a 92.41% single-attempt separation rate and 98.12% after three retries. Image preprocessing combines the Multi-Scale Retinex with Color Preservation (MSRCP) algorithm and bilateral filtering to enhance illumination correction and reduce noise. For overlapping pest detection, EfficientNetv2-S replaces the YOLOv5s backbone and is combined with an Adaptive Feature Pyramid Network (AFPN), achieving 95.72% detection accuracy, 94.04% mAP, and 127 FPS. For pest species recognition, the model incorporates a Squeeze-and-Excitation (SE) attention module and α-CIoU loss function, reaching 91.30% precision on 3428 field images. Deployed on an NVIDIA Jetson Nano, the system demonstrates a detection time of 0.3 s, 89.64% recall, 86.78% precision, and 1.136 s image transmission delay, offering a reliable solution for real-time pest monitoring in complex field environments. Full article

Face detection technology is essential for surveillance and security projects; however, algorithms designed to detect faces in color images often struggle in poor lighting conditions. In this paper, we describe the development of an embedded vision system designed to detect human faces by analyzing images captured with thermal infrared sensors, thereby overcoming the limitations imposed by varying illumination conditions. All variants of the Ultralytics YOLOv8 and YOLO11 models were trained on the Terravic Facial IR database and tested on the Charlotte-ThermalFace database; the YOLO11 model achieved slightly higher performance metrics. We compared the performance of two embedded system boards: the NVIDIA Jetson Orin Nano and the NVIDIA Jetson Xavier NX, while running the trained model in inference mode. The NVIDIA Jetson Orin Nano performed better in terms of inference time. The developed embedded vision system based on these platforms accurately detects faces in thermal images in real-time. Full article

Echocardiography is a fundamental tool in cardiovascular diagnostics, providing radiation-free real-time assessments of cardiac function. However, its accuracy strongly depends on operator expertise, resulting in inter-operator variability that affects diagnostic consistency. Recent advances in artificial intelligence have enabled new applications for real-time image classification and probe guidance, but these typically rely on large datasets and specialized hardware such as GPU-based or embedded accelerators, limiting their clinical adoption. Here, we address this challenge by developing a cognitive electronic unit that integrates convolutional neural network (CNN) models and an inertial sensor for assisted echocardiography. We show that our system—powered by an NVIDIA Jetson Orin Nano—can effectively classify standard cardiac views and differentiate good-quality from poor-quality ultrasound images in real time even when trained on relatively small datasets. Preliminary results indicate that the combined use of CNN-based classification and inertial sensor-based feedback can reduce inter-operator variability and may also enhance diagnostic precision. By lowering barriers to data acquisition and providing real-time guidance, this system has the potential to benefit both novice and experienced sonographers, helping to standardize echocardiographic exams and improve patient outcomes. Further data collection and model refinements are ongoing, progressing the way for a more robust and widely applicable clinical solution. Full article

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. Full article

Electric wheelchairs are the primary means of transportation that enable individuals with disabilities to move independently to their desired locations. This paper introduces a novel, low-cost smart wheelchair system designed to enhance the mobility of individuals with severe disabilities through hand gesture recognition. Additionally, the system aims to support low-income individuals who previously lacked access to smart wheelchairs. Unlike existing methods that rely on expensive hardware or complex systems, the proposed system utilizes an affordable webcam and an Nvidia Jetson Nano embedded computer to process and recognize six distinct hand gestures—“Forward 1”, “Forward 2”, “Backward”, “Left”, “Right”, and “Stop”—to assist with wheelchair navigation. The system employs the “You Only Look Once version 8n” (YOLOv8n) model, which is well suited for low-spec embedded computers, trained on a self-collected hand gesture dataset containing 12,000 images. The pre-processing phase utilizes the MediaPipe library to generate landmark hand images, remove the background, and then extract the region of interest (ROI) of the hand gestures, significantly improving gesture recognition accuracy compared to previous methods that relied solely on hand images. Experimental results demonstrate impressive performance, achieving 99.3% gesture recognition accuracy and 93.8% overall movement accuracy in diverse indoor and outdoor environments. Furthermore, this paper presents a control circuit system that can be easily installed on any existing electric wheelchair. This approach offers a cost-effective, real-time solution that enhances the autonomy of individuals with severe disabilities in daily activities, laying the foundation for the development of affordable smart wheelchairs. Full article

Advancements in embedded systems and Artificial Intelligence (AI) have enhanced the capabilities of Unmanned Aircraft Vehicles (UAVs) in computer vision. However, the integration of AI techniques o-nboard drones is constrained by their processing capabilities. In this sense, this study evaluates the deployment of object detection models (YOLOv8n and YOLOv8s) on both resource-constrained edge devices and cloud environments. The objective is to carry out a comparative performance analysis using a representative real-time UAV image processing pipeline. Specifically, the NVIDIA Jetson Orin Nano, Orin NX, and Raspberry Pi 5 (RPI5) devices have been tested to measure their detection accuracy, inference speed, and energy consumption, and the effects of post-training quantization (PTQ). The results show that YOLOv8n surpasses YOLOv8s in its inference speed, achieving 52 FPS on the Jetson Orin NX and 65 fps with INT8 quantization. Conversely, the RPI5 failed to satisfy the real-time processing needs in spite of its suitability for low-energy consumption applications. An analysis of both the cloud-based and edge-based end-to-end processing times showed that increased communication latencies hindered real-time applications, revealing trade-offs between edge (low latency) and cloud processing (quick processing). Overall, these findings contribute to providing recommendations and optimization strategies for the deployment of AI models on UAVs. Full article

Regular inspection of urban drainage pipes can effectively maintain the reliable operation of the drainage system and the production safety of residents. Aiming at the shortcomings of the CCTV inspection method used in the drainage pipe defect detection task, a PDS-YOLO algorithm that can be deployed in the pipe defect detection system is proposed to overcome the problems of inefficiency of manual inspection and the possibility of errors and omissions. First, the C2f-PCN module was introduced to decrease the model sophistication and decrease the model weight file size. Second, to enhance the model’s capability in detecting pipe defect edges, we incorporate the SPDSC structure within the neck network. Introducing a hybrid local channel MLCA attention mechanism and Wise-IoU loss function based on a dynamic focusing mechanism, the model improves the precision of segmentation without adding extra computational cost, and enhances the extraction and expression of pipeline defect features in the model. The experimental outcomes indicate that the mAP, F1-score, precision, and recall of the PDS-YOLO algorithm are improved by 3.4%, 4%, 4.8%, and 4.0%, respectively, compared to the original algorithm. Additionally, the model achieves a reduction in both the model’s parameter and GFLOPs by 8.6% and 12.3%, respectively. It saves computational resources while improving the detection accuracy, and provides a more lightweight model for the defect detection system with tight computing power. Finally, the PDS-YOLOv8n model is deployed to the NVIDIA Jetson Nano, the central console of the mobile embedded system, and the weight files are optimized using TensorRT. The test results show that the velocity of the model’s inference capabilities in the embedded device is improved from 5.4 FPS to 19.3 FPS, which can basically satisfy the requirements of real-time pipeline defect detection assignments in mobile scenarios. Full article

The use of Artificial Intelligence (AI) to detect defects such as concrete cracks in civil and transport infrastructure has the potential to make inspections less expensive, quicker, safer and more objective by reducing the need for on-site human labour. One deployment scenario involves using a drone to carry an embedded device and camera, with the device making localised predictions at the edge about the existence of defects using a trained convolutional neural network (CNN) for image classification. In this paper, we trained six CNNs, namely Resnet18, Resnet50, GoogLeNet, MobileNetV2, MobileNetV3-Small and MobileNetV3-Large, using transfer learning technology to classify images of concrete structures as containing a crack or not. To enhance the model’s robustness, the original dataset, comprising 3000 images of concrete structures, was augmented using salt and pepper noise, as well as motion blur, separately. The results show that Resnet50 generally provides the highest validation accuracy (96% with the original dataset and a batch size of 16) and the highest validation F1-score (95% with the original dataset and a batch size of 16). The trained model was then deployed on an Nvidia Jetson Nano device for real-time inference, demonstrating its capability to accurately detect cracks in both laboratory and field settings. This study highlights the potential of using transfer learning on Edge AI devices for Structural Health Monitoring, providing a cost-effective and efficient solution for automated crack detection in concrete structures. Full article

Aimed at the problems of a high leakage rate, a high cutting injury rate, and uneven root cutting in the existing combined garlic harvesting and root-cutting technology, we researched the key technologies used in a garlic harvester for adaptive root cutting based on machine vision. Firstly, research was carried out on the conveyor alignment and assembly of the garlic harvester to realize the adjustment of the garlic plant position and the alignment of the bulb’s upper surface before the roots were cut, to establish the parameter equations and to modify the structure of the conveyor to form the adaptive garlic root-cutting system. Then, a root-cutting test using the double-knife disk-type cutting device was carried out to examine the root-cutting ability of the cutting device. Finally, a bulb detector trained with the IRM-YOLO model was deployed on the Jetson Nano device (NVIDIA, Jetson Nano(4GB), Santa Clara, CA, USA) to conduct a harvester field trial study. The pass rate for the root cutting was 82.8%, and the cutting injury rate was 2.7%, which tested the root cutting performance of the adaptive root cutting system and its field environment adaptability, providing a reference for research into combined garlic harvesting technology. Full article

Advancements in deep learning and infrared sensors have facilitated the integration of RGB-thermal (RGBT) tracking technology in computer vision. However, contemporary RGBT tracking methods handle complex image data, resulting in inference procedures with a large number of floating-point operations and parameters, which limits their performance on general-purpose processors. We present a lightweight Siamese dual-stream infrared-enhanced RGBT tracking algorithm, called DuSiamIE.It is implemented on the low-power NVIDIA Jetson Nano to assess its practicality for edge-device applications in resource-limited settings. Our algorithm replaces the conventional backbone network with a modified MobileNetV3 and incorporates light-aware and infrared feature enhancement modules to extract and integrate multimodal information. Finally, NVIDIA TensorRT is used to improve the inference speed of the algorithm on edge devices. We validated our algorithm on two public RGBT tracking datasets. On the GTOT dataset, DuSiamIE achieved a precision (PR) of 83.4% and a success rate (SR) of 66.8%, with a tracking speed of 40.3 frames per second (FPS). On the RGBT234 dataset, the algorithm achieved a PR of 75.3% and an SR of 52.6%, with a tracking speed of 34.7 FPS. Compared with other algorithms, DuSiamIE exhibits a slight loss in accuracy but significantly outperforms them in speed on resource-constrained edge devices. It is the only algorithm among those tested that can perform real-time tracking on such devices. Full article