Early Warning System for Forest Fire Detection

Early Warning System for Forest Fire Detection

The overall goal of this project is to develop Forest Fire Monitoring System which is cost-effective, locally indigenized, scalable and feasible for application in Pakistani context. Based on this premise, instead of the high-end and costly thermal camera, NCRA-Agricultural Robotics Lab (NARL) at LUMS is proposing to use standard RGB cameras with night vision capabilities….

Water Quality Assessment Using Visual Sensors

Water Quality Assessment Using Visual Sensors

Mohbat Tharani, Abdul Wahab Amin, Fezan Rasool, Muhammad Maaz, Murtaza Taj, Abubakr Muhammad Summary In the absence of an effective trash management framework, trash is often illegally dumped in rivers and canals running through urban areas, contaminating freshwater and blocking drainage lines which result in urban floods. When this contaminated water reaches agricultural fields, it…

IEEEJSTAR2020 – Kiln-Net: A gated neural network for detection of brick kilns in South Asia
| |

IEEEJSTAR2020 – Kiln-Net: A gated neural network for detection of brick kilns in South Asia

Usman Nazir, Usman Khalid Mian, Muhammad Usman Sohail, Murtaza Taj and Momin Uppal Abstract: The availability of high-resolution satellite imagery has enabled several new applications. One such application is identification of brick kilns for the elimination of modern day slavery which is also one of UN’s Sustainable Development Goals (SDG). This requires automated analysis of…

NRSfM using Local Rigidity

NRSfM using Local Rigidity

Abstract We show that typical nonrigid structure can often be approximated well as locally rigid sub-structures in time and space. Specifically, we assume that: 1) the structure can be approximated as rigid in a short local time window and 2) some point- pairs stay relatively rigid in space, maintaining a fixed distance between them during…

3D Metric Rectification using Angle Regularity

3D Metric Rectification using Angle Regularity

Abstract We propose Automatic Metric Rectification of projectively distorted 3D structures for man-made scenes using Angle Regularity. Man-made scenes, such as buildings, are characterized by a profusion of mutually orthogonal planes and lines. Assuming the availability of planar segmentation, we search for the rectifying 3D homography  which maximizes the number of orthogonal plane-pairs in the…

2D Pose Detection and Tracking

2D Pose Detection and Tracking

More information: Video | PDF Text Reference: Ali Hassan and Murtaza Taj, “2D articulated human pose tracking: A hybrid approach”, IEEE International Conference on Image Processing (ICIP), 2014 Bibtex Reference: @inproceedings{ResNet3DLeakyReLU2019,    author = “Ali Hassan and Murtaza Taj”,    title = “2D articulated human pose tracking: A hybrid approach”,     booktitle = “IEEE International Conference on…

Shape from Angle Regularity

Shape from Angle Regularity

Urban architecture is characterized by a profusion of straight lines that meet orthogonally. This simple observation leads to a flexible definition of the man-made world and the distortion in these regular angles serves as a new shape-from-X cue. This project formulates the idea and explores its applications in various scenarios in detail. Publications Some initial results…

Bilinear Spatiotemporal Basis Models – Project Page

Bilinear Spatiotemporal Basis Models – Project Page

Ijaz Akhter, Tomas Simon, Sohaib Khan, Iain Matthews, Yaser Sheikh Abstract A variety of dynamic objects, such as faces, bodies, and cloth, are represented in computer graphics as a collection of moving spatial landmarks. Spatiotemporal data is inherent in a number of graphics applications including animation, simulation, and object and camera tracking. The principal modes…

Trajectory Basis for Nonrigid Structure from Motion – Project Page

Trajectory Basis for Nonrigid Structure from Motion – Project Page

Ijaz Akhter, Yaser Sheikh, Sohaib Khan, Takeo Kanade Abstract Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes. These basis are object dependent and therefore have to be estimated anew for each video sequence. In contrast, we propose a dual approach to describe the evolving…