Browsing by Author "Dr. Aksam Iftikhar"

Now showing 1 - 3 of 3

Computer Vision-Based Data Acquisition System for Retail Intelligence
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Talha Sajid , Sufyan Ahmed , Zain Ahsan; FA17-BCS-012 , FA17-BCS-076 , FA17-BCS-151; Dr. Aksam Iftikhar; LHR TP 7509
Advancement in the use of artificial intelligence has now become an important factor in almost all sectors. Computer vision combined with artificial intelligence can eventually become a major advancement in the field of asset management. Computer vision, when used with a flexible chain management system, can be used to predict stocks, purchases, and demands. At the moment, when it comes to focusing on maintaining the supply, it has advanced solutions for the manufacturer, retailer, and retailer that can be the way forward in the ever-changing industries. The problem faced in today’s supply chain mechanism is that when the product reaches its final destination, the number of the products are not the same as it were at the beginning that was being transferred by the Industry, and this has become one of the main problems in today’s era. The main purpose of this paper is to provide a solution to maintain the stock and management by utilizing the computer vision technology using tools and technologies mention in the paper, which can be useful to the industry in many ways.
Monocular 3D Object Detection for Autonomous Vehicle
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Wasif Maqsood; SP20-RCS-012; LHR TP 8669; Dr. Aksam Iftikhar
Currently, Environment perception, 3D objects detection and the distance of objects from the camera is one of the hot topics in computer vision and in robotics, which is widely explored by scientists to achieve maximum accuracy of detection for autonomous vehicles. For reliable and safe driving, it is necessary that self-driving cars can perceive the environmental surroundings accurately. 3D object detection and their distance estimation are a challenging task because of different angles of moving vehicles and computational resources required to process video data. Distance estimation from the camera is used in all autonomous vehicles and robots for safe driving. In this research, a two-stage deep learning architecture is proposed for 3D object detection, their pose estimation and then the distance of objects using monocular cameras installed in vehicles. In contrast to stoneworker methods which only regress 3D dimensions, we propose a method in which using deep neural network we regress 2D bounding boxes, geometric estimation and the distance from the camera and then use these estimations for regressing accurate 3D object properties and estimate pose to construct the stable 3D bounding box. Our models is tested on the KITTI Dataset, which consists of images of vehicles in different environments. The dataset contains separate repositories for training and testing purposes (7481 and 7518 images, respectively) with main target classes (cars, pedestrians).In this Thesis we discussed deep learning techniques for computer vision. More precisely, we are focusing on the 3D bounding boxes and distance estimation from the scene by using only single for autonomous vehicles and robots. In this chapter we present an introductory approach for the problem and also present our contributions and objectives of this thesis.
Towards adaptation of industry 4.0 standards in Quality Inspection of Packaging material
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-11-20) Hassam Imtiaz; FA16-BSE-039; Mariam Taimoor; FA16-BSE-087; Minahil Humayun Babri; FA16-BSE-070; Dr. Aksam Iftikhar
This project aims to offer quality inspection of the packaging material using the fourth industrial revolution (Industrial 4.0). The system uses camera measures for quality assessment of the products. The system performs quality inspection tests on the packaging material to assure the standards of the product. The tests include the identification of the dirt spots in the finished products, if the product has any dirt spot, the system rejects that product. The dirt spot can be of any type like blots or stains. The second test is print template analysis, in this test the system identifies if the front panel is being shifted at the back or is according to the industrial quality standards. The third test is Code Structure Legibility, which performs barcode detection and verification of its legibility. The system performs all the tests through intelligent Computer Vision and Machine Learning algorithms. The basic aim behind this project is to promote the fourth industrial revolution and Artificial Intelligence in Pakistan because our country is lacking in both. Deployment of this system will include a camera, a computer with design and implementation of industrial standard HMI.