Naeem Akhter

Naeem Akhter

Auto-generated profile, based on publicly available information

Naeem Akhter

Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, Islamabad 45650, Pakistan

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2023 in IEEE Access
Verified
Journal Article
Open access
MSMaria Siddiqua
Maria Siddiqua
samir brahimsamir brahim
samir brahim
NANaeem Akhter
Naeem Akhter
AZAneela Zameer
Aneela Zameer
JKJavaid Khurshid
Javaid Khurshid
Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded with blue-green tones and mud affecting marine navigation. While most techniques in the literature are designed to restore only one or a few degradations using a single model, using separate architectures for each restoration process is computationally expensive. To address this, an all-in-one Multidomain Attention-based Conditional Generative Adversarial Network (MACGAN) is proposed to improve scene visibility for optimal ground, aerial, and marine navigation, using the same set of parameters across all domains. The MACGAN is a lightweight network with four encoder and decoder blocks and multiple attention blocks in between, which enhances the image restoration process by focusing on the most important features. The performance of MACGAN is compared qualitatively and quantitatively with various state-of-the-art image-to-image translation models, all-in-one adverse weather removal models, and single-effect removal models. Further, MACGAN is tested on real-world unseen image domains, such as smog, dust, fog, rain, snow, and lightning. The results demonstrate that MACGAN can improve scene visibility and has good generalizability. An ablation study is also conducted to assess the impact of the discriminator and attention blocks in MACGAN, and the results confirm the effectiveness of the proposed architecture, which includes a discriminator and three attention blocks.

1 July 2020 in IEEE Access
Verified
Journal Article
Open access
RARashid Ali
Rashid Ali
PYPeng Yunfeng
Peng Yunfeng
AAAhmad Ali
Ahmad Ali
HAHaider Ali
Haider Ali
NANaeem Akhter
Naeem Akhter
AJAbdul Jalil
Abdul Jalil
Most of the Thermal (Infrared) cameras nowadays are equipped with a motorized lens for focusing a scene manually. The subjective nature of manual focusing makes it an inefficient and cumbersome process. In contrast, Autofocusing (AF) obtains the best focused image based on a quantitative measure with the benefits of convenience and intelligence. Various AF systems for visual cameras have been developed, but relatively less amount of work has been done for thermal imaging systems. This paper presents a Vision and Control based Autofocusing System (VCAFS) comprising: (1) an uncooled thermal camera with motorized lens, (2) a passive contrast-based focus measure, (3) a smoothing operator to avoid local extrema, and (4) two different lens motion controllers. Experimental results show the efficacy of the proposed system on live videos even when the scene and its depth are continuously changing.

23 January 2024 in International Journal of Image and Graphics
Verified
Journal Article
Closed access
MSMaria Siddiqua
Maria Siddiqua
NANaeem Akhter
Naeem Akhter
AZAneela Zameer
Aneela Zameer
JKJavaid Khurshid
Javaid Khurshid

28 April 2021 in arXiv
Verified
Preprint
Open access
PDF file
MAMinhaj Uddin Ansari
Minhaj Uddin Ansari
TBTalha Bilal
Talha Bilal
NANaeem Akhter
Naeem Akhter
Deep learning based 3D reconstruction of single view 2D image is becoming increasingly popular due to their wide range of real-world applications, but this task is inherently challenging because of the partial observability of an object from a single perspective. Recently, state of the art probability based Occupancy Networks reconstructed 3D surfaces from three different types of input domains: single view 2D image, point cloud and voxel. In this study, we extend the work on Occupancy Networks by exploiting cross-domain learning of image and point cloud domains. Specifically, we first convert the single view 2D image into a simpler point cloud representation, and then reconstruct a 3D surface from it. Our network, the Double Occupancy Network (D-OccNet) outperforms Occupancy Networks in terms of visual quality and details captured in the 3D reconstruction.