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

Publications

Low level feature detectors and their invariance to Bilateral Symmetry

with Professor Ebroul Izquierdo

Under review; 20th April 2015

Abstract

We investigate the capability of low level feature detectors to consistently define feature keypoints in an image and its horizontally reflected (mirrored) image. It is our assertion that a feature detector that is invariant to the horizontally symmetric orientation of an image is a useful attribute for pattern detection tasks. We assess ten of the most popular feature detectors on a popular dataset of 8,677 images in 101 categories covering natural scenes, drawings, photographs, faces, animals and more. We define a set of error measurements to help us to understand the reasons for variance in keypoint position, size and angle of orientation, and we use SIFT descriptors extracted from the keypoints to measure feature matching accuracy in feature space compared with matching sub-pixel image coordinates. We conclude that the FAST and STAR detectors are perfectly invariant to bilateral symmetry, \emph{Good Features to Track} and the Harris Corner detector are invariant after feature matching, and others vary in their robustness. SIFT is the least invariant of all the detectors that we test.

Minimal Hough Forest training for pattern detection in Query by Example video search

with Professor Ebroul Izquierdo

Under review; 16th April 2015

Abstract

We assess configuration parameters of a Hough Forest and their impact on performance to achieve good pattern detection in images without need or opportunity for large-scale training. Our motivation is the application of Query-by-Example video search where a region of interest in a video frame image is selected by the user as a query sample. We describe a method to discover training images from the single query region and assess the impact of tuning standard Hough Forest parameters on the application of pattern detection using a very small training set of data. We introduce a novel method by which to improve training performance and precision in pattern detection by adaptive selection of the patch size and the number of patches used. We show results using challenging street-scene videos demonstrating our method to improve precision and performance over static general-purpose Hough Forest parameters used in the literature.

Robust feature matching in long-running poor quality videos

with Professor Ebroul Izquierdo

Under review; 23rd December 2014

Abstract

We describe a methodology that is designed to match key point and region-based features in real-world images, acquired from long-running security cameras with no control over the environment. We detect frame duplication and images from static scenes that have no activity to prevent processing saliently identical images, and describe a novel 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 that are 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 demonstrate an improvement in accuracy of matching key points between images compared with state-of-the-art feature descriptors. 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 36% of the storage requirements.

Image Quality at Distance

Robust Feature Matching in the Wild

with Professor Ebroul Izquierdo

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

Abstract and BibTex

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}
}

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

Abstract

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.

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

Abstract and BibTex

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