International Journal on Artificial Intelligence Tools

Hidden Markov models (HMMs) are a popular approach for modeling sequential data, typically based on the assumption of a first-order Markov chain. In other words, only one-step back dependencies are modeled which is a rather unrealistic assumption in most applications. In this paper, we propose a method for postulating HMMs with approximately infinitely-long time-dependencies. Our approach considers the whole history of model states in the postulated dependencies, by making use of a recently proposed nonparametric Bayesian method for modeling label sequences with infinitely-long time dependencies, namely the sequence memoizer. We manage to derive training and inference algorithms for our model with computational costs identical to simple first-order HMMs, despite its entailed infinitely-long time-dependencies, by employing a mean-field-like approximation. The efficacy of our proposed model is experimentally demonstrated.

Measuring the distance is an important task in many clustering and image-segmentation algorithms. The value of the distance decides whether two image points belong to a single or, respectively, to two different image segments. The Euclidean distance is used quite often. In more complicated cases, measuring the distances along the surface that is defined by the image function may be more appropriate. The geodesic distance, i.e. the shortest path in the corresponding graph, has become popular in this context. The problem is that it is determined on the basis of only one path that can be viewed as infinitely thin and that can arise accidentally as a result of imperfections in the image. Considering the k shortest paths can be regarded as an effort towards the measurement of the distance that is more reliable. The drawback remains that measuring the distance along several paths is burdened with the same problems as the original geodesic distance. Therefore, it does not guarantee significantly better results. In addition to this, the approach is computationally demanding. This paper introduces the resistance-geodesic distance with the goal to reduce the possibility of using a false accidental path for measurement. The approach can be briefly characterised in such a way that the path of a certain chosen width is sought for, which is in contrast to the geodesic distance. Firstly, the effective conductance is computed for each pair of the neighbouring nodes to determine the local width of the path that could possibly run through the arc connecting them. The width computed in this way is then used for determining the costs of arcs; the arcs whose use would lead to a small width of the final path are penalised. The usual methods for computing the shortest path in a graph are then used to compute the final distances. The corresponding theory and the experimental results are presented in this paper.

Visual tracking in low frame rate (LFR) videos has many inherent difficulties for achieving accurate target recovery, such as occlusions, abrupt motions and rapid pose changes. Thus, conventional tracking methods cannot be applied reliably. In this paper, we offer a new scheme for tracking objects in low frame rate videos. We present a method of integrating multiple metrics for template matching, as an extension for the particle filter. By inspecting a large data set of videos for tracking, we show that our method not only outperforms other related benchmarks in the field, but it also achieves better results both visually and quantitatively, once compared to actual ground truth data.

Vehicle and pedestrian tracking is a key component for vision-based safety analysis which can use motion and appearance cues of road users. Since appearance-based detectors generate false alarms and provide lower speed, motion-based detectors are preferred but they work poorly when pedestrians or vehicles stop due to traffic signals. In this paper, a tracking system is proposed to track waiting and moving road users by fusion of motion and appearance cues at detection level. The enhanced optical flow tracker handles the partial occlusion problem, and it cooperates with the detection module to provide long-term tracks of vehicles and pedestrians. The system evaluation shows 13% and 43% improvement in tracking of vehicles and pedestrians respectively, and finally heat-maps show benefits of using the proposed system through the visual depiction of intersection usage.

To meet the demands of an aging society, research on intelligent/robotic wheelchairs have been receiving a lot of attention. In elderly care facilities, care workers are required to communicate with the elderly in order to maintain both their mental and physical health. While this is regarded as important, having a conversation with someone on a wheelchair while pushing it from behind in a traditional setting would interfere with their smooth and natural conversation. So we are developing a robotic wheelchair system which allows companions and wheelchair users to move in a natural formation. This paper reports on an investigation to learn the patterns of human behavior when the wheelchair users and their companions communicate while walking together. The ethnographic observation reveals a natural formation of positioning for both companions and wheelchair users. Based on this investigation, we propose a multiple robotic wheelchair system which can maintain desirable formations for communication between wheelchairs.