A Monocular vision positioning and tracking system based on deep neural network

Abstract

In order to locate the mobile robots in three-dimensional indoor environment, mostly global navigation satellite system-denied space, a monocular visual space positioning algorithm based on deep neural network is proposed. First, we employ the lightweight YOLOv5 algorithm for target detection, and the LibTorch deep learning framework is used for model deployment to improve the inference speed. Moreover, a multi-layer perceptron (MLP) neural network with four inputs and two outputs is constructed, which regress the coordinates of the robot in the field coordinate system to complete the target localization, and this method is compared with the mathematical model solving algorithm to reflect the accuracy and superiority of positioning algorithm based on deep neural network. The proposed positioning and tracking system has been successfully applied to ICRA robot competition, and results show that the positioning error estimated by our method is within 10cm whilst having good real-time performance.

Advancements in Ai for Ultrasound-guided Sub-arachnoid Block: Implications for Ghana's Healthcare Sector

“…17 Moreover, AI technology can contribute to reducing complications associated with traditional methods of sub-arachnoid block that rely solely on human judgment. 18 Studies [19][20][21] have shown that AI-assisted procedures result in higher success rates compared to those performed without AI guidance. This increased success rate translates into improved patient outcomes by minimizing instances of failed blocks or inadequate pain relief.…”

“…This allows anesthesiologists to accurately visualize the needle tip without constant probe adjustment, improving accuracy and reducing procedure time. A study by Li et al, 25 exemplifies the use of AI-based needle tracking technology for SAB. They developed an AI algorithm that tracks the needle tip using a combination of ultrasound and electromagnetic tracking systems.…”

“…Through automated image analysis and needle tracking technology, AI algorithms can improve accuracy and safety during these procedures. Concrete illustrations from studies conducted by Chen et al, 26 and Li et al, 27 demonstrate how AI has been successfully used to enhance real-time imaging during SAB procedures. These advancements have significant implications for anesthesia practice, as they can improve patient outcomes, reduce complications, and enhance overall procedural efficiency.…”

“…By considering these variables along with real-time ultrasound images, AI algorithms can provide precise guidance to anesthesiologists during SAB procedures. A notable example is the work done by Li et al, 29 , who developed an AI algorithm that automatically calculates the optimal needle depth for SAB based on patient-specific characteristics. The algorithm was trained using a large dataset of ultrasound images and patient data, allowing it to accurately predict the ideal needle depth for successful block placement.…”

“…52 AI technology can analyze ultrasound images in real-time and provide instant feedback on needle placement during sub-arachnoid blocks. 53 This would allow less experienced practitioners to perform these procedures safely and effectively under remote guidance from experts if needed. Furthermore, such costeffective solutions enable medical facilities across Ghana to offer better services at affordable rates without compromising on quality.…”