Rapid urban development in Morocco has led to increased construction activities and significant environmental concerns. Recently Zenata city has undergone significant urban development, marking a crucial step in its trajectory toward a modern smart city. As a part of this growth, our research incorporates an innovative method within the You Only Look Once version 8 (YOLOv8) model, representing a significant advance over conventional methods. The YOLO algorithm has been updated with new features and improvements that infuse our work with a dash of innovation. YOLOv8 integration improves construction and irregular construction detection accuracy beyond what is possible with traditional applications. We trained our algorithm using orthophoto captured by DJI MATRICE 300 RTK drone split into georeferenced tiles and annotated using LabelImg software. Through this process, we were able to create a solid 742 image dataset for training, testing, and validation purposes related to construction. Utilizing drone imagery and the YOLOv8 object detection algorithm, buildings and construction irregularities are detected with high accuracy after 300 training epochs on Kaggle's GPU P100. Insights for early detection and effective building site management are provided by this all-encompassing strategy, which supports Zenata City's sustainable urban growth.

These days, road accidents are one of Morocco's biggest problems. Fatigue, drowsiness, and driver behavior are among the primary causes.This research aims to develop an embedded system by image processing and computer vision to ensure driving safety by monitoring driver behavior and assist drivers to awaken from micro-sleep or fatigue due to long driving hours and various other reasons. Indeed, the driver inattention, drowsiness or driver fatigue can be detected. The suggested method is designed to support drivers if needed, based on the vehicle velocity. Once the driver crosses a certain speed limit, the program starts face detection and analyzing this data to determine whether the driver is tired, sleepy, or inattentive. This activates different alarm depending on the criticality level. It can sound a voice alert to help him wake up and drive more cautiously. The system is based on AI algorithms in image processing based on OpenCV libraries and the Python language to capture the movements of the driver's eyes and head when starting the automobile. Every algorithm is run on a Raspberry-Pi 4 card, and numerous experimentation series have demonstrated overall credible performance with success accuracy of over 93% in EAR and MAR calculations.

Urban monitoring has become a field of interest in small cities to track the growth of urban areas in different regions around the world. Semantic segmentation of buildings through drone imagery has emerged as an effective solution. In the present research, the efficiency of three deep learning models, U-Net, SegNet, and a proposed hybrid algorithm, was evaluated. Several metrics, including precision, recall, mean intersection over union (mIoU), intersection over union (IoU), F1 score, accuracy, and loss function, were used to assess the quality of segmentation. A test set of 133 annotated image tiles was used for evaluation. The results showed that the proposed algorithm was resistant to varying urban textures and achieved an accuracy of 98% with a loss function value of 6%. In comparison, U-Net achieved 97% accuracy with a loss function value of 9%, and SegNet achieved 95% accuracy with a loss function value of 11%. The study’s results are constrained by the fact that it used the Zenata City urban data, which might limit its utility to other urban areas. This comparative analysis advanced automated urban monitoring by offering interesting details about the strengths and limitations of each model, thus guiding the choice of the most suitable image segmentation technique for building and construction applications. This study demonstrates practical applications in urban planning and construction analysis by automating building detection using deep learning. Accurate building segmentation from drone imagery improves land use planning, infrastructure development, and smart city decision-making, ultimately contributing to more effective urban management.

Reliable navigation in GPS-denied environments remains a critical challenge for autonomous vehicles (AVs), particularly in urban canyons, tunnels, and areas with adverse weather. GPS-based localization systems often fail under these conditions, highlighting the need for resilient, multimodal solutions. This paper introduces a radar-assisted localization approach that combines LiDAR, Inertial Measurement Units (IMUs), and deep learning techniques for robust navigation. The proposed approach combines sensor fusion, Kalman filtering, Gaussian Mixture Models (GMM), and Nonlinear AutoRegressive with eXogenous inputs (NARX) system identification within a unified probabilistic framework. The framework provides continuous real-time localization and environment mapping while enabling short-horizon prediction of the slave robot’s motion based on master robot observations. By forecasting the slave robot’s future states several seconds ahead, the method enhances tracking accuracy, coordination, and overall system robustness in dynamic environments. By fusing sensor data through a Convolutional Recurrent Neural Network (CRNN), our system maintains reliable mapping even in GPS-challenging environments. Radar’s ability to detect objects through weather obstructions, LiDAR’s high-resolution spatial mapping, and IMU data for real-time vehicle tracking work together to reduce the limitations of each individual sensor. To enhance accuracy, we apply Kalman filtering for state estimation and prediction within the GMM-based framework, rather than solely for post-processing or trajectory smoothing, addressing sensor noise and drift. Through simulations and real-world indoor data, we demonstrate the system’s ability to deliver accurate, continuous pose estimation, even in challenging conditions, with low localization errors characterized by RMSE values of 0.12 m, 0.15 m, and 0.28 m along the X, Y, and Z axes, respectively, and sub-meter maximum position deviations. This work represents a significant step toward GPS-independent navigation for AVs and can extend to domains such as aerial drones, offering pathways to more reliable autonomous systems. Future work will address outdoor validation and scalability.