Craig Henderson

PhD Research Student exploring techniques in Computer Vision, Machine Learning using C++11

My research interests centre around object tracking and retrieval in video and temporal still images, particularly in low frame-rate and multi-angle scene imaging such as CCTV. I am experimenting with object search and re-identification with a goal to locating offenders in previous footage by way of distinctive clothing or markings such as tatoos.

Older projects, publications and research can be found here


Large-scale forensic analysis of security images and videos

with Professor Ebroul Izquierdo

6th Doctoral Consortium, BMVC 2014, Nottingham, 5th September 2014

Our research is concerned with the practical application of computer vision in the forensic analysis of security images and videos. Contemporary literature make use of high-definition images and Hollywood feature films in their datasets, and there is little or no assessment of algorithms' performance using poor quality images with variable frame rates and uncontrolled lighting conditions such as security video.

Work so far has produced a methodology for matching features across low quality images that yields an improved results over existing feature matching techniques. Future work will involve innovation in search and retrieval online machine learning to train models from unlabelled data, and segmentation of one-shot videos to aid computer and human analysis of long-running video sequences. We are motivated to produce an integrated system for police investigators to use a query-by-example search and retrieval system with relevance feedback and machine learning to incrementally discover evidence in criminal investigations.

address = {Nottingham},
author = {Henderson, Craig and Izquierdo, Ebroul},
booktitle = {6th Doctoral Consortium at BMVC 2014},
title = {{Large-scale forensic analysis of security images and videos}},
year = {2014}

Robust Feature Matching in the Wild

with Professor Ebroul Izquierdo

under review

Image Quality at Distance

We introduce a novel combinatorial feature descriptor and distance calculation method that efficiently unites texture and color attributes to discriminate feature correspondence in low quality images. Our goal is to define a lightweight method of improving the discriminatory properties of popular feature descriptors to enable correspondences to be found in images that lack consistent texture due to blurring, or have poor color definition.

The method is straight-forward to implement, efficient in computation and occupies only 10 integers of storage per descriptor, making it suitable for large-scale and real-time applications. We test our method on a variety of real-world security videos and demonstrate an improvement in the ability to match features between images compared with the standard feature descriptors extracted from the same set of feature points. We use key point features from Harris Corners, BRISK, SIFT and SURF as well as MSER and MSCR region detectors to provide a comprehensive analysis of our generic method, and show an improvement in feature matching accuracy in nearly all experiments and a feature matching performance of a 138-dimensional descriptor to rival a state-of-the-art 384-dimension color descriptor.

Boosting feature matching accuracy with colour information PDF (poster)

with Professor Ebroul Izquierdo

BMVA Summer School, Swansea, May 2014

ViiHM Workshop, Stratford-upon-Avon, September 2014

We boost the performance of discriminative matching of features between colour images, with

  • a space-efficient and generic extension for any feature descriptor
  • a novel distance measure calculation