Academic work

I work in the field of computer vision in the machine intelligence lab in the engineering department of the University of Cambridge.

Research Topics

• 3B Microscopy
• FAST corner detection
• Testing corner detection
• Object detection
• Tracking vehicles from the air
• 3D Tracking
• Radial distortion calibration
• Surveillanve and sensor networks
• Applications to science
• Automated label placement
• Mapping Python to C++

Links

• Publications .
• Presentations .
• Videos .
• Corner detector testing .
• Hydrosys

Projects

3B Microscopy

• Susan Cox
• Most recent paper: Bayesian localization microscopy reveals nanoscale podosome dynamics
• Main page and software: 3bmicroscopy.com
• Videos supplementary information

Tracking vehicles from the air

• Automatic creation of urban velocity fields from aerial video
• Improving multiple target tracking in structured environments using velocity priors
• Acquisition and registration of aerial video imagery of urban traffic
• Camera distortion self-calibration using the plumb-line constraint and minimal Hough entropy

Object Detection and Grammar Guided Feature Extraction

• Most recent paper: Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction
• Main page

Convert-XY

Convert-XY was developed to enable writing programs in a natural mix of C++ and Python. It allows the mising of dynamic types with statically instantiated C++ templates, and maintains a natural type system in both languages.

• Damian Eads
• Convert-XY: type-safe interchange of C++ and Python containers for NumPy extensions
• Main page
• Software

FAST corner detection

This work presenst the FAST (Features from Accelerated Segment Test) and the FAST-ER (FAST-Enhanced Repeatability) corner detectors. Full source code for both using existing detectors and creating new detectors is available.

• Most recent paper: Faster and better: A machine learning approach to corner detection
• Main page

Radial distortion autocalibration

Radial distortion can be deduced from a single image by finding parameters which make straight lines in the world straight in the image.

• Most recent paper: Camera distortion self-calibration using the plumb-line constraint and minimal Hough entropy

Surveillance and distributed sensor networks

• Energy efficient sensor node implementations
• Sensor network based vehicle classification and license plate identification system
• Radiation detection and situation management by distributed sensor networks
• Improving multiple target tracking in structured environments using velocity priors
• A recurrent velocity filter for detecting large numbers of moving objects

Science

• Comment on: Pinning frequencies of the collective modes in α-uranium
• Evidence for the charge-density-wave nature of the stripe phase in manganites
• Accurate extraction of reciprocal space information from transmission electron microscopy images
• Strain control of superlattice implies weak charge-lattice coupling in La_0.5Ca_0.5MnO₂

Corner detector testing

The repeatability of a corner detector is an important factor in determining its performance. This work makes available a dataset for easil ymeasuring the repeatability of a corner detector.

• Most recent paper: Faster and better: A machine learning approach to corner detection
• Main page

Automatic label placement

Label placement is an important topic in augmented reality. This work presents an efficient method for unobtrusice placement of labels in live video without the need for a model.

• Most recent paper: Real-time Video Annotations for Augmented Reality
• Main page

3D Model Based Tracking

3D tracking can be made to be very robust by fusing corner point and edge based information. Additionally, curved 3D object can be tracked from a model with edge based tracking and a hidden line renderer.

• Most recent paper: Fusing points and lines for high performance tracking
• Main page

Updated February 26^th 2014, 05:49