BUILDING DETECTION THROUGH SATELLITE IMAGERY

remote sensing

LOCALIZING FIREARM CARRIERS

object detection

DOMAIN ADAPTATION OF SEMANTIC SEGMENTATION

domain adaptation

Real-world Anomaly Detection

in Surveillance Videos

WHO WE ARE

Intelligent Machines Lab, is an endeavour to establish close working relationship among researchers, engineers and developers in the areas of robotics, artificial intelligence, human computer interaction and machine learning. We are interested in solving theoretical problems and extending existing boundaries of research. However, our objective is to mold and extend the technology so that it could be used to solve practical problems.

One of our aim to excite the student about these technologies, instigate enthusiasm in them to use technologies to create solutions for solving everyday problems and enable them to make their solutions practical. Currently we are working on the following areas

Robotics
Computer Vision
Machine Learning
Human Robot Interaction
Geographic Information System (GIS)

IML NEWS

  • Congratulations Muhammad Akhtar Munir, paper from our lab has been accepted at NeurIPS 2021.
  • Congratulations! Our paper is accepted in CVPR2021
  • Congratulations to Dr. Adnan Siddiqui (PI), Dr. Khurram Bhatti (co-PI) and Dr. Mohsen Ali (co-PI) for research grant under the “AI for Earth” innovation program of National Geographic and Microsoft. Project is titled “AI4GLOF: AI for Glacial Lake Outburst Floods hazard potential assessment in Chitral, Pakistan
  • Congratulations to Dr. Waqas Sultani for securing research grant from Facebook
  • Congratulations to Dr. Rehan Hafiz (PI) and Dr. Mohsen Ali (co-PI) for securing research grant for the project “AI Assisted Feature Extraction & Matching for 3D Point Cloud Formation” from Electronics and Telecommunications Research Institute (ETRI), South Korea

RESEARCH GROUPS

CVML Group

Computer Vision and Machine Learning (CVML) research group address the wide range of problems including Affective Computing, Remote Sensing, Object Detection, Semantic Segmentation and Anomaly Detection…

MedAI Group

Producing state of the art research in medical imaging using AI and Computer Vision

WHAT WE DO

REMOTE SENSING

We at ITU are studying satellite and aerial imagery to develop tools that will assist Government and Non-Government organization in analyzing urban population, road structure, urban and rural structural development, agricultural regions …

ECONOMICS FROM AFAR

We at ITU are studying satellite and aerial imagery to develop tools that will assist Government and Non-Government organization in analyzing urban population, road structure, urban and rural structural development, agricultural regions, animal migrations and destruction caused by natural disasters.

DOMAIN ADAPTATION

Semantic segmentation is a challenging problem due to pixel level annotations requirement. Deep Convolutional Neural Networks (DCNNs) are performing with tremendous results on Semantic Segmentation problem…

ANAMOLY DETECTION

In addition to proposing a new anomaly detection method, we introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as …

MOVING OBJECT SEGMENTATION IN VIDEOS

Video object segmentation aims at clustering pixels in videos into objects or background. In this project, instead of treating deep learning as a black box and fixating on infinite iterations on the network design, we have focused on …

AFFECTIVE COMPUTING

With the recent advancement of social media networks, a large fraction of world population is now able to socially interact with each other. Previously people used to write long paragraphs to convey their thoughts but now-a-days they prefer to …

HUMAN-ROBOT INTERACTION SYSTEM

The Robot-Receptionist project is an idea initiated in Information Technology University as an effort to create a user-friendly intelligent Robot which will help people by giving required assistance. This robot uses Computer Vision …

OBJECT DETECTION

Automatic detection of firearms is important for enhancing security and safety of people, however, it is a challenging task owing to the wide variations in shape, size, and appearance of firearms. Viewing angle variations and occlusions by …

RESEARCH HIGHLIGHTS

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation by Mohsen Ali and Naseer Subhani got accepted in Europe Conference on Computer Vision (ECCV 2020)

Weakly-supervised domain adaptation for built-up region segmentation in aerial and satellite imagery by Mohsen Ali and Javed Iqbal got accepted in ISPRS Journal of Photogrammetry and Remote Sensing

Localizing firearm carriers by identifying human-object pairs by Abdul Basit, Muhammad Akhtar Munir, Mohsen Ali and Arif Mahmood got accepted in ISPRS IEEE International Conference on Image Processing 2020.

Destruction from sky: Weakly Supervised Approach for Destruction Detection in Satellite Imagery by Muhammad Usman Ali, Waqas Sultani and Mohsen Ali got accepted in ISPRS Journal of Photogrammetry and Remote Sensing 2020.

EpO-Net: Exploiting Geometric Constraints on Dense Trajectories for MotionSaliency by Muhammad Faisal, Ijaz Akhter, Mohsen Ali, Richard Hartley got accepted in WACV, 2020.

MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling by Javed Iqbal and Mohsen Ali got accepted in WACV, 2020.

Want to join us?

Meet our faculty members

Dr. Mohsen Ali Assistant Professor
PhD – University of Florida
Dr. Waqas Sultani Assistant Professor
Ph.D. Computer Science, Center for Research in Computer Vision, University of Central Florida, USA
Dr. Arif Mahmood Associate Professor
Ph.D. in Computer Science from the Lahore University of Management Sciences (LUMS)