Ayoub El-Alami

UAV-based imaging systems often require real-time image stitching capabilities for tasks such as mapping, surveillance, and environmental monitoring. Traditional approaches typically rely on homography-based transformations, which, although robust, are computationally demanding. These methods often require reestimating transformation parameters for each video frame due to continuous camera motion, significantly increasing computational load and making real-time performance challenging, especially in resource-constrained drone applications. This study proposes an optimized image stitching method based on explicit rotation, scaling, and translation transformations derived from predefined anchor points. Designed for scenarios that involve relatively stable and flat scenes with known anchor markers, this approach removes the reliance on complex matrix operations. Evaluation on experimental footage demonstrates that the method reduces computational complexity, achieving processing times approximately 36% of those required by conventional homography-based methods. Visual assessments and alignment accuracy metrics indicate that the proposed method maintains the same alignment quality, making it particularly suitable for real-time UAV operations and embedded vision applications where computational efficiency is critical.

With the decreasing cost of traffic cameras and rapid advancement in computer vision and artificial intelligence, developing robust traffic surveillance systems has become more feasible and practical. These systems can easily outperform traditional human monitoring systems, as they can collect and analyze traffic data coming from multiple cameras efficiently. A good understanding of this data allows the detection easily road anomalies in real time and in an autonomous way. Therefore, an intelligent traffic system typically consists of three components: object detection, object tracking, and behavior analysis components. In this paper, we present a review of some of the well-known object detection techniques used in traffic video surveillance. The review begins with a brief introduction to the history of object detection and the evolution of its techniques. Then we review separately the two main approaches of detection, which are traditional and deep learning approaches of detection. Finally, an experimental analysis has been conducted to evaluate and compare the performance of some of the recent relevant detection methods in terms of speed and precision, in detecting vehicles in a traffic scenario.