Papers
Statistical Hough Transform
IEEE trans. Pattern Analysis and Machine Intelligence, pp. 1502-1509, Vol. 31, No. 8, August 2009.
The Standard Hough Transform is a popular
method in image processing and is traditionally estimated using
histograms. Densities modelled with histograms in high dimensional
space and/or with few observations, can be very sparse
and highly demanding in memory. In this paper, we propose
first to extend the formulation to continuous kernel estimates.
Second, when dependencies in between variables are well taken
into account, the estimated density is also robust to noise and
insensitive to the choice of the origin of the spatial coordinates.
Finally our new statistical framework is unsupervised (all needed
parameters are automatically estimated) and flexible (priors can
easily be attached to the observations). We show experimentally
that our new modeling encodes better the alignment content of
images.
keywords: Hough transform, Radon transform, kernel
probability density function, uncertainty, line detection
Bayesian Classification for the Statistical Hough Transform
International Conference on Pattern Recognition, Florida USA, December 2008
We have introduced the Statistical Hough transform that extends the standard Hough transform by using a kernel mixture as a robust alternative to the 2 dimensional accumulator histogram. This work develops further this framework by proposing a Bayesian classification scheme to associate the spatial coordinates to one particular class defined in the Hough
space. In a first step, we segment the Hough space into meaningful classes. Then using the inverse Radon transform, we backproject the different classes into the image space. We illustrate our approach on a synthetic image and on real images.
- 79 Views
-
Like (1)
Improving the quality of colour colonoscopy videos
Co-authored with F. Vilarino and G. Lacey, EURASIP Journal on Image and Video Processing Volume (2008)
One of the widely used colonoscopes has a monochrome chipset recording successively at 60 Hz R,G, and B components
merged into one color video stream. Misalignments of the channels occur each time the camera moves, and this artefact impedes both online visual inspection by doctors and offline computer analysis of the image data. We propose to restore this artefact by first equalizing the color channels and then performing a robust camera motion estimation and compensation.
Automated Colour Grading using Colour Distribution Transfer
F. Pitie, A. Kokaram and R. Dahyot, Journal Computer Vision and Image Understanding (2007)
This article proposes an original method for grading the colours between different images or shots. The first stage of the method is to find a one-to-one colour mapping that transfers the palette of an example target picture to the original picture. This is performed using an original and parameter free algorithm that is able to transform any N-dimensional probability density function into another one. The proposed algorithm is iterative, non-linear and has a low computational cost. Applying the colour mapping on the original picture allows reproducing the same ‘feel’ as the target picture, but can also increase the graininess of the original picture, especially if the colour dynamic of the two pictures is very different. The second stage of the method is to reduce this grain artefact through an efficient post-processing algorithm that intends to preserve the gradient field of the original picture.
Browsing sports video: trends in sports-related indexing and retrieval work
A. Kokaram, N. Rea, R. Dahyot, M. Tekalp, P. Bouthemy, P. Gros, I. Sezan, IEEE Signal Processing Magazine ( 2006)
This paper aims to identify the current trends in sports-based indexing and retrieval work. It discusses the essential building blocks for any semantic-level retrieval system and acts as a case study in content analysis system design. While one of the major benefits of digital media and digital television in particular has been to provide users with more choices and a more interactive viewing experience, the freedom to choose has in fact manifested as the freedom to choose from the options the broadcaster provides. It is only through the use of automated content-based analysis that sports viewers will be given a chance to manipulate content at a much deeper level than that intended by broadcasters, and hence put true meaning into interactivity
Off-line multiple object tracking using candidate selection and the Viterbi algorithm
F. Pitie, S.-A. Berrani, A. Kokaram, & R. Dahyot, IEEE Conference on Image Processing (ICIP), 2005.
This paper presents a probabilistic framework for off-line multiple object tracking. At each timestep, a small set of deterministic candidates is generated which is guaranteed to contain the correct solution. Tracking an object within video then becomes possible using the Viterbi algorithm. In contrast with particle filter methods where candidates are numerous and random, the proposed algorithm involves a few candidates and results in a deterministic solution. Moreover, we consider here off-line applications where past and future information is exploited. This paper shows that, although basic and very simple, this candidate selection allows the solution of many tracking problems in different real-world applications and offers a good alternative to particle filter methods for off-line applications.
Classification and representation of semantic content in broadcast tennis videos
N. Rea, R. Dahyot & A. Kokaram, IEEE International Conference on Image Processing (ICIP), 2005.
This paper investigates the semantic analysis of broadcast tennis footage. We consider the spatio-temporal behaviour of an object in the footage as being the embodiment of a semantic event. This object is tracked using a colour based particle filter. The video syntax and audio features are used to help delineate the temporal boundaries of these events. For broadcast tennis footage, the system firstly parses the video sequence based on the geometry of the content in view and classifies the clip as a particular view type. The temporal behaviour of the serving player is modelled using a HMM. As a result, each model is representative of a particular semantic episode. Events are then summarised using a number of synthesised keyframes.
A Bayesian approach to object detection using probabilistic appearance-based models
Co-authored with Pierre Charbonnier and Fabrice Heitz, Journal Pattern Analysis & Applications (2004)
We introduce a Bayesian approach, inspired by probabilistic principal component analysis (PPCA) to detect objects in complex scenes using appearance-based models. The originality of the proposed framework is to explicitly take into account general forms of the underlying distributions, both for the eigenspace distribution and for the observation model. The approach combines linear data reduction techniques (to preserve computational efficiency), nonlinear constraints on the eigenspace distribution (to model complex variabilities) and non-linear (robust) observation models (to cope with clutter, outliers and occlusions).
keywords: PCA, M-estimators, Object detection in images
Inlier modeling for multimedia data analysis
R. Dahyot, N. Rea, A. Kokaram and N. Kingsbury, IEEE International Workshop on Multimedia Signal Processing (2004)
This paper presents a robust method to estimate the unknown standard deviation of a centred normal distribution from a mixture density. This method is applied to different signal processing problems. The first one concerns silence segmentation from audio data. The second application deals with colour class parameter extraction. In this later case, the mean is also estimated from the observations.
Joint audio visual retrieval for tennis broadcasts
R. Dahyot, A. Kokaram, N. Rea & H. Denman, ICASSP (2003)
In recent years, there has been increasing work in the area of content retrieval for sports. The idea is generally to extract important events or create summaries to allow personalisation of the media stream. While previous work in sports analysis has employed either the audio or video stream to achieve some goal, there is little work that explores how much can be achieved by combining the two streams. This paper combines both audio and image features to identify the key episode in tennis broadcasts. The image feature is based on image moments and is able to capture the essence of scene geometry without recourse to 3D modelling. The audio feature uses PCA to identify the sound of the ball hitting the racket. The features are modelled as stochastic processes and the work combines the features using a likelihood approach. The results show that combining the features yields a much more robust system than using the features separately.
N-Dimensional Probability Density Function Transfer and its Application to Colour Transfer
F. Pitié, A. Kokaram & R. Dahyot, IEEE International Conference on Computer Vision (ICCV), 2005.
This article proposes an original method to estimate a continuous transformation that maps one N-dimensional distribution to another. The method is iterative, non-linear, and is shown to converge. Only 1D marginal distribution is used in the estimation process, hence involving low computation costs. As an illustration this mapping is applied to color transfer between two images of different contents. The paper also serves as a central focal point for collecting together the research activity in this area and relating it to the important problem of automated color grading.
Unsupervised statistical detection of changing objects incamera-in-motion video
R. Dahyot, P. Charbonnier and F. Heitz, ICIP (2001)
Change detection in image sequences has mainly focused on the recovery of moving objects when the viewing system is static, or on the detection of simple production effects such as video shot boundaries or scene transitions. Camera motion is usually handled by the compensation of dominant motion, using motion estimation and segmentation schemes. We propose a novel statistical change detection method able to handle more complex events such as entering or exiting objects, or changes in object appearance, when the camera is moving. Temporal changes of objects are captured by analyzing the statistics of successive images. Considering an appropriate choice of image features, we show how it is possible to extract the statistics of changing objects from a pair of successive image histograms. Changing objects are then located by statistical backprojection techniques. The method is completely unsupervised and does not require any motion estimation or motion compensation. It is illustrated here on real world road scenes exhibiting large camera motion
Robust Visual Recognition of Color Images
R. Dahyot, P. Charbonnier & F. Heitz, CVPR (2000)
In this paper, a robust pattern recognition system, using an appearance-based representation of color images is described. Standard appearance-based approaches are not robust to outliers, occlusions or segmentation errors. The approach proposed here relies on robust M-estimators, involving non-quadratic and possibly non-convex energy functions. To deal with the minimization of non-convex functions in a deterministic framework, we introduce an estimation scheme relying on M-estimators used in continuation, from convex functions to hard redescending non-convex estimators. At each step of the robust estimation scheme, the non-quadratic criterion is minimized using the half-quadratic theory. This leads to a weighted least square algorithm, which is easy to implement. The proposed robust estimation scheme does not require any user interaction because all necessary parameters are previously estimated. The method is illustrated on a road sign recognition application. Experiments show significant improvements with respect to standard estimation schemes.
Add Comment