Mostafa Pordel

Australian National University, Umeå University

Papers

Total Citations

H-Index

About

Mostafa Pordel’s research sits at the intersection of computer vision, robotics, and intelligent automation, with a particular focus on leveraging depth-sensing technologies for real-world applications. His work has pioneered the integration of low-cost sensors—such as the Microsoft Kinect—into object detection and classification systems, making advanced image analysis more accessible and practical. In his most cited paper, “Semi-Automatic Image Labelling Using Depth Information” (2015, 9 citations), Pordel introduced a novel approach that uses depth data to streamline the labor-intensive process of creating ground-truth labels for object detection, a critical step for training machine learning models. This contribution directly addresses a bottleneck in computer vision research. Earlier, in “Integrating Kinect Depth Data with a Stochastic Object Classification Framework for Forestry Robots” (2012, 3 citations), he demonstrated how combining RGB and depth images can enable robots to robustly classify natural objects like trees, bushes, and stones in unstructured forest environments. Pordel’s work is notable for its practical orientation—bridging sensor hardware with stochastic modeling to improve autonomous navigation and environmental perception. His research continues to influence the development of cost-effective, semi-automated tools for image annotation and field robotics.