I'm from Pakistan and currently working as a Marie Curie Early Stage Researcher for EVOCATION ITN in Visual Computing Lab which is a part of the prestigious ISTI-CNR research institute located in Pisa, Italy. As part of my scholarship, I am also pursuing my PhD studies at University of Pisa. I am currently working on projects related to 3D reconstruction and acquisition.
I am recruited for ESR07 position in EVOCATION ITN. My research is focused on 3D reconstruction and point cloud registration. I am currently working on automatic key-frame extraction for real-time video to 3D pipelines.
I worked as a Teaching Assistant for the course of Sensors, Perception and Actuation with instructor Ilya Afanasyev. My responsibility was to mark all homeworks, quizzes and exams according to instructor's guidelines.
ROS for beginners: Basics, Motion and OpenCV [certificate].
ROS for Beginners II: Localization, Navigation and SLAM [certificate].
Evaluating deep learning methods for low resolution point cloud registration in outdoor scenarios [pdf]
Point cloud registration is a fundamental task in 3D reconstruction and environment perception. We explore the performance of modern Deep Learning-based registration techniques, in particular Deep Global Registration (DGR) and Learning Multi-view Registration (LMVR), on an outdoor real world data consisting of thousands of range maps of a building acquired by a Velodyne LIDAR mounted on a drone. We used these pairwise registration methods in a sequential pipeline to obtain an initial rough registration. The output of this pipeline can be further globally refined. This simple registration pipeline allow us to assess if these modern methods are able to deal with this low quality data. Our experiments demonstrated that, despite some design choices adopted to take into account the peculiarities of the data, more work is required to improve the results of the registration.
Deep learning based trajectory estimation of vehicles in crowded and crossroad scenarios [pdf] [code][video]
[talk]
Trajectory estimation of vehicles is an important part of traffic surveillance systems and self driving cars. The difficulty of task lies in variations in light intensity, sizes of objects and real time detection. In the past decade vision based Convolutional Neural Networks have shown some promising results in the area. However, these methods still face problems in crowded and crossroad scenarios when objects are very close together. We propose tracking by detection based trajectory estimation pipeline which consists of two stages: The first stage is the detection and localization of vehicles and the second stage is building associations in bounding boxes and track the associated bounding boxes. We analyze the performance of Mask RCNN benchmark and fYOLOv3 on UA DETRAC dataset which is a large scale real life traffic dataset. We evaluate certain metrics like inference time, Intersection over union (IoU), Precision Recall (PR) curve and mean Average Precision (mAP). Experiments show that Mask RCNN outperforms YOLOv3. After that, we analyze the performance of centroid tracker and SORT tracker. Experiments show that SORT tracker gives us smoother trajectory as compared to noisy trajectory obtained from centroid tracker. However, SORT tracker based trajectory gives 4 pixels more Euclidean distance loss than Centroid tracker based trajectory.
ROS-based integration of smart space and mobile robot as internet of robotic things [pdf] [code]
The rapid developments in the field of Artificial Intelligence are bringing enhancements in the area of intelligent transport systems by overcoming the challenges of safety concerns. Traffic surveillance systems based on CCTV cameras can help us to achieve safe and sustainable transport systems. Trajectory estimation of vehicles is an important part of traffic surveillance systems and self-driving cars. The task is challenging due to the variations in illumination intensities, object sizes and real-time detection. We propose tracking by detection based trajectory estimation pipeline which consists of two stages: The first stage is the detection and localization of vehicles and the second stage is building associations in bounding boxes and track the associated bounding boxes. We analyze the performance of the Mask RCNN benchmark and YOLOv3 on the UA-DETRAC dataset and evaluate certain metrics like Intersection over Union, Precision-Recall curve, and Mean Average Precision. Experiments show that Mask RCNN Benchmark outperforms YOLOv3 in terms of accuracy. SORT tracker is applied on detected bounding boxes to estimate trajectories. The tracker is evaluated using mean absolute error. We demonstrate that the developed technique works successfully in crowded and crossroad scenarios.
