Craig Henderson

Second Year 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 distinctive clothing, bags or markings such as tatoos.

Older projects, publications and research can be found here

Tutorial

The impurity of security video footage

with Dr Saverio G. Blasi and Faranak Sobhani

15-17th July 2015 International Conference on Imaging for Crime Detection and Prevention, London

Much of the state-of-the-art research in video processing is driven by the broadcasting and entertainment industry, therefore algorithms are tailored for processing of commercial videos with high production quality and limited variation in camera movement, colour definition or illumination. Similarly, most of the research on video processing of CCTV footage makes use of selected videos, with a controlled or limited variation in movement or quality. Video footage used for a large-scale police investigation is very different. Content is acquired from many sources (fixed cameras, fixed-path moving cameras, remote-operator-controlled street cameras, body-mounted cameras or mobile phone footage), under diverse illumination and weather conditions (indoor or outdoor). Clearly, police forces face enormous challenges with analysing such diversified content. Automated analysis of such videos is very challenging. In this tutorial, we will show some typical videos from real police investigations, reviewing the major difficulties in processing such kind of content. We will also hear from the Metropolitan Police in London about the practicality of acquiring data from many different sources. The typically poor quality of videos is a particular problem for practitioners seeking to develop automated processing techniques. Video corruption and unreliable metadata are widespread. Finally, we will take a deep-dive into some of the encoding violations that equipment manufacturers use for their proprietary playback devices.

See our accompanying research paper On the impurity of street-scene video footage.

Publications

On the impurity of street-scene video footage

with Dr Saverio G. Blasi and Faranak Sobhani

15-17th July 2015 International Conference on Imaging for Crime Detection and Prevention, London

The Metropolitan Police in London have found that the opportunity to use computer vision technology in the analysis of real-world street-scene video is severely limited because of the practical constraints in the variety and poor quality of videos available to them. Consequently, in a large criminal investigation, police forces employ numerous officers and volunteers to watch many hours of camera footage to locate, identify and trace the movements of suspects, victims, witnesses, luggage and other inanimate objects. Their goal is to piece together a story of events leading up to an incident, and to determine what happened afterwards. In this paper, we present the technical challenges facing researchers in developing computer vision technique to process from the wild street-scene videos.

Robust Feature Matching in the Wild

with Professor Ebroul Izquierdo

25-30th July 2015 Science and Information Conference, London

Image Quality at Distance

Finding corresponding key points in images from security camera videos is challenging. Images are generally low quality and acquired in uncontrolled conditions with visual distortions caused by weather, crowded scenes, emergency lighting or the high angle of the camera mounting. We describe a methodology to match features between images that performs especially well with real-world images. We introduce a novel \emph{blur sensitive feature detection} method, a combinatorial feature descriptor and a distance calculation that efficiently unites texture and colour attributes to discriminate feature correspondence in low quality images. Our methods are tested by performing key point matching on real-world security images such as outdoor CCTV videos, and we 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, SIFT, SURF, BRISK and FAST as well as MSER and MSCR region detectors to provide a comprehensive analysis of our generic method. We demonstrate feature matching using a 138-dimensional descriptor that improves the matching performance of a state-of-the-art 384-dimension colour descriptor with just 40% of the storage requirements.

@inproceedings{Henderson2015,
address = {London},
author = {Henderson, Craig and Izquierdo, Ebroul},
booktitle = {Science and Information Conference},
title = {{Robust Feature Matching in the Wild}},
year = {2015}
}

Large-scale forensic analysis of security images and videos

with Professor Ebroul Izquierdo

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

DOI: 10.13140/2.1.2859.0887



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.

@inproceedings{Henderson2014,
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}
doi = {10.13140/2.1.2859.0887},
url = {http://dx.doi.org/10.13140/2.1.2859.0887}
}

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