Hieu Tat Nguyen

Active learning using pre-clustering

The paper is concerned with two-class active learning. While the common approach for collecting data in active learning is to select samples close to the classification boundary, better performance can be achieved by taking into account the prior data distribution. The main contribution of the paper is a formal framework that incorporates clustering into active learning. The algorithm first constructs a classifier on the set of the cluster representatives, and then propagates the classification decision to the other samples via a local noise model. The proposed model allows to select the most representative samples as well as to avoid repeatedly labeling samples in the same cluster. During the active learning process, the clustering is adjusted using the coarse-to-fine strategy in order to balance between the advantage of large clusters and the accuracy of the data representation. The results of experiments in image databases show a better performance of our algorithm compared to the current methods.

Watersnakes: energy-driven watershed segmentation

The watershed algorithm from mathematical morphology is powerful for segmentation. However, it does not allow incorporation of a priori information as segmentation methods that are based on energy minimization. In particular, there is no control of the smoothness of the segmentation result. In this paper, we show how to represent watershed segmentation as an energy minimization problem using the distance-based definition of the watershed line. A priori considerations about smoothness can then be imposed by adding the contour length to the energy function. This leads to a new segmentation method called watersnakes, integrating the strengths of watershed segmentation and energy based segmentation. Experimental results show that, when the original watershed segmentation has noisy boundaries or wrong limbs attached to the object of interest, the proposed method overcomes those drawbacks and yields a better segmentation.

Fast occluded object tracking by a robust appearance filter

We propose a new method for object tracking in image sequences using template matching. To update the template, appearance features are smoothed temporally by robust Kalman filters, one to each pixel. The resistance of the resulting template to partial occlusions enables the accurate detection and handling of more severe occlusions. Abrupt changes of lighting conditions can also be handled, especially when photometric invariant color features are used, The method has only a few parameters and is computationally fast enough to track objects in real time.

A gradient descent rule for spiking neurons emitting multiple spikes

A supervised learning rule for Spiking Neural Networks (SNNs) is presented that can cope with neurons that spike multiple times. The rule is developed by extending the existing SpikeProp algorithm which could only be used for one spike per neuron. The problem caused by the discontinuity in the spike process is counteracted with a simple but effective rule, which makes the learning process more efficient. Our learning rule is successfully tested on a classification task of Poisson spike trains. We also applied the algorithm on a temporal version of the XOR problem and show that it is possible to learn this classical problem using only one spiking neuron making use of a hair-trigger situation.

Occlusion robust adaptive template tracking

We propose a new method for tracking rigid objects in image sequences using template matching. A Kalman filter is used to make the template adapt to changes in object orientation or illumination. This approach is novel since the Kalman filter has been used in tracking mainly for smoothing the object trajectory. The performance of the Kalman filter is further improved by employing a robust and adaptive filtering algorithm. Special attention is paid to occlusion handling.

Robust Tracking Using Foreground-Background Texture Discrimination

This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be dealt with. When modelling the target alone (and not its distinction from the background), changes of lighting or changes of viewpoint can invalidate the internal target model. As the main contribution, we propose a new model for the detection of the target using foreground/background texture discrimination. The background is represented as a set of texture patterns. During tracking, the algorithm maintains a set of discriminant functions each distinguishing one pattern in the object region from background patterns in the neighborhood of the object. The idea is to train the foreground/background discrimination dynamically, that is while the tracking develops. In our case, the discriminant functions are efficiently trained online using a differential version of Linear Discriminant Analysis (LDA). Object detection is performed by maximizing the sum of all discriminant functions. The method employs two complementary sources of information: it searches for the image region similar to the target object, and simultaneously it seeks to avoid background patterns seen before. The detection result is therefore less sensitive to sudden changes in the appearance of the object than in methods relying solely on similarity to the target. The experiments show robust performance under severe changes of viewpoint or abrupt changes of lighting.

Spatio-Temporal Context for Robust Multitarget Tracking

In multitarget tracking, the main challenge is to maintain the correct identity of targets even under occlusions or when differences between the targets are small. The paper proposes a new approach to this problem by incorporating the context information. The context of a target in an image sequence has two components: the spatial context including the local background and nearby targets and the temporal context including all appearances of the targets that have been seen previously. The paper considers both aspects. We propose a new model for multitarget tracking based on the classification of each target against its spatial context. The tracker searches a region similar to the target while avoiding nearby targets. The temporal context is included by integrating the entire history of target appearance based on probabilistic principal component analysis (PPCA). We have developed a new incremental scheme that can learn the full set of PPCA parameters accurately online. The experiments show robust tracking performance under the condition of severe clutter, occlusions, and pose changes

Tracking nonparameterized object contours in video

We propose a new method for contour tracking in video. The inverted distance transform of the edge map is used as an edge indicator function for contour detection. Using the concept of topographical distance, the watershed segmentation can be formulated as a minimization. This new viewpoint gives a way to combine the results of the watershed algorithm on different surfaces. In particular, our algorithm determines the contour as a combination of the current edge map and the contour, predicted from the tracking result in the previous frame. We also show that the problem of background clutter can be relaxed by taking the object motion into account. The compensation with object motion allows to detect and remove spurious edges in background. The experimental results confirm the expected advantages of the proposed method over the existing approaches.

Detection of moving objects in video using a robust motion similarity measure

This correspondence deals with the segmentation of a video clip into independently moving visual objects. This is an important step in structuring video data for storage in digital libraries. The method follows a bottom-up approach. The major contribution is a new well-founded measure for motion similarity leading to a robust method for merging regions. The improvements with respect to existing methods have been confirmed by experimental results.

Tracking Aspects of the Foreground against the Background

In object tracking, change of object aspect is a cause of failure due to significant changes of object appearances. The paper proposes an approach to this problem without a priori learning object views. The object identification relies on a discriminative model using both object and background appearances. The background is represented as a set of texture patterns. The tracking algorithm then maintains a set of discriminant functions each recognizing a pattern in the object region against the background patterns that are currently relevant. Object matching is then performed efficiently by maximization of the sum of the discriminant functions over all object patterns. As a result, the tracker searches for the region that matches the target object and it also avoids background patterns seen before. The results of the experiment show that the proposed tracker is robust to even severe aspect changes when unseen views of the object come into view.