Coventry University Featured PhD Programmes
Peter MacCallum Cancer Centre Featured PhD Programmes
University College London Featured PhD Programmes

Automated human detection in crowded scenes using fused machine learning systems (Application Ref: SF19/EE/CIS/KHELIFI)

Faculty of Engineering and Environment

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
Dr F Khelifi , Dr A Belatreche Applications accepted all year round Self-Funded PhD Students Only

About the Project

Automated human detection in dense crowds has recently emerged as one of the key AI elements to address many problems in computer vision such as scene analysis, suspicious behaviour/fight detection and human tracking. This also constitutes the fundamental task for managing crowded events, such as protests, demonstrations, marathons, rallies, political speeches and musical concerts. However, when dealing with such crowded scenes for automated analysis, a number of challenges arise. This includes the limited number of pixels per target, undesirable noise due to illumination changes or blurring effects due to moving objects, and finally severe occlusions. In the literature, there have been a number of attempts to tackle these issues and achieve acceptable performance and the traditional approach mainly relies on multiscale object detection using low level local features such as HoG and SIFT with a machine learning system (or a combination of weak classifiers) trained over a large number of samples. However, such systems seem to fail to tackle the problem of severe occlusions especially when the object of interest is tiny or blurry in a scene. This research attempts to address this problem by investigating the challenge of occlusions from a statistical perspective and developing a number of robust classifiers that can be combined in a fusion method to refine the individual decisions and consequently enhance the detection performance. Statistical deep neural networks will be considered along with Gaussian Mixture models and support vector machines to form a comprehensive framework for automated human detection in dense crowds.

This project is supervised by Dr. Fouad Khelifi.

Eligibility and How to Apply:

Please note eligibility requirement:
• Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.

For further details of how to apply, entry requirements and the application form, see

Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. SF19/EE/CIS/KHELIFI) will not be considered.

Start Date: 1 March 2020 or 1 October 2020

Northumbria University takes pride in, and values, the quality and diversity of our staff. We welcome applications from all members of the community. The University holds an Athena SWAN Bronze award in recognition of our commitment to improving employment practices for the advancement of gender equality and is a member of the Euraxess network, which delivers information and support to professional researchers.

Funding Notes

This is an unfunded research project.


- F Ahmed, F Khelifi, A Lawgalv, A Bouridane (2019) “Comparative Analysis of a Deep Convolutional Neural Network for Source Camera Identification”, 2019 IEEE 12th International Conference on Global Security, Safety and Sustainability (ICGS3).

- C. Riachy, F. Khelifi, and A. Bouridane, “Video-based person re-identification using unsupervised tracklet matching,” in IEEE Access, vol. 7, pp. 20596–20606, 2019.

- F. Khelifi and A. Bouridane, ‘Perceptual Video Hashing for Content Identification and Authentication’ in IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, pp. 50-67, Jan. 2019.

- J. Almaghtuf and F. Khelifi 'Self Geometric Relationship Filter for Efficient SIFT Key-points Matching in Full and Partial Palmprint Recognition', in IET Biometrics, vol. 7, pp. 296-304, June 2018.

- F. Khan, F. Khelifi, M. A. Tahir, and A. Bouridane ‘Dissimilarity Gaussian Mixture Models for Efficient Offline Handwritten Text-Independent Identification using SIFT and RootSIFT Descriptors’ in IEEE Transactions on Information Forensics and Security, vol. 14, pp. 289-303, Feb. 2018.

- F. Khan, M. A. Tahir, F. Khelifi, and A. Bouridane ‘Robust Off-line Text Independent Writer Identification Using Bagged Discrete Cosine Transform Features’ Elsevier Expert Systems with Applications, vol. 71, pp. 404-415, Apr. 2017.

- McCarroll N., Belatreche A., Harkin J., Li Y. (2015) “Bio-inspired hierarchical framework for multi-view face detection and pose estimation,” in IEEE International Joint Conference on Neural Networks (IEEE IJCNN), Killarney, 2015.

- Aboozar T., Belatreche A, Li Y, Maguire L. (2015) DL-ReSuMe: A Delay Learning-Based Remote Supervised Method for Spiking Neurons. IEEE Transactions on Neural Networks and Learning Systems, 26 (12). pp. 3137-3149

- Wang J., Belatreche A., Maguire L., McGinnity T.M (2015) SpikeTemp: An Enhanced Rank-Order-Based Learning Approach for Spiking Neural Networks with Adaptive Structure. IEEE Transactions on Neural Networks and Learning Systems.
Search Suggestions

Search Suggestions

Based on your current searches we recommend the following search filters.

FindAPhD. Copyright 2005-2021
All rights reserved.