Publications by authors named "Muhammad Hanzla"
Article Synopsis
- The study addresses challenges in vehicle detection and classification faced by advanced traffic monitoring systems, highlighting limitations of traditional methods that need high computational power and struggle with various data types.
- An innovative multi-phase approach for detecting vehicles in aerial images is introduced, utilizing techniques like image enhancement, contour-based segmentation, and advanced feature extraction methods, culminating in object classification using deep learning networks.
- The new method shows significant improvements in accuracy, achieving 96.6% on the UAVID dataset and 97% on the VAID dataset, demonstrating its effectiveness over existing techniques for better traffic monitoring.
Introduction: Unmanned aerial vehicles (UAVs) are widely used in various computer vision applications, especially in intelligent traffic monitoring, as they are agile and simplify operations while boosting efficiency. However, automating these procedures is still a significant challenge due to the difficulty of extracting foreground (vehicle) information from complex traffic scenes.
Methods: This paper presents a unique method for autonomous vehicle surveillance that uses FCM to segment aerial images.