Eduardo Parrilla

Handling occlusion in object tracking in stereoscopic video sequences

In this paper, we study simple algorithms for three-dimensional tracking objects in a stereo video sequence, by combining optical flow and stereo vision. This method is not able to handle the occlusion of the moving objects when they disappear due to an obstacle. To improve the performance of this method, we propose the use of adaptive filters and neural networks to predict the expected instantaneous velocities of the objects. In the previous works, this system has been successfully proved in two-dimensional tracking.

Handling occlusion in optical flow algorithms for object tracking

In this paper, we study simple algorithms for tracking objects in a video sequence, based on the selection of landmark points representative of the moving objects in the first frame of the sequence to be analyzed. The movement of these points is estimated using a sparse optical-flow method. Methods of this kind are fast, but they are not very robust. Particularly, they are not able to handle the occlusion of the moving objects in the video. To improve the performance of optical flow-based methods, we propose the use of adaptive filters and neural networks to predict the expected instantaneous velocities of the objects, using the predicted velocities as indicators of the performance of the tracking algorithm. The efficiency of these strategies in handling occlusion problems are tested with a set of synthetic and real video sequences.

Object tracking with a stereoscopic camera: exploring the three-dimensional space

The experimental analysis of three-dimensional (3D) movement is of great importance to introduce students to knowledge of the actual physical world. However, the difficulties of collecting 3D data make it little suitable for beginner physics students. In this work, we propose an experiment to analyse 3D motion in stationary and rotating systems. A projectile is launched from a rotating platform. The tracking of the projectile is carried out with the assistance of a stereoscopic camera and simplified object tracking techniques. The experiment can be modelled through the well-known transformation equations between an inertial reference system and a non-inertial one with constant angular velocity. The simplicity of the method and the agreement between the experimental data and the theoretical model make the experiment accessible to undergraduate physics students. In this way, they can easily measure a 3D movement and verify its theoretical equations.

3D-Based Resources Fostering the Analysis, Use, and Exploitation of Available Body Anthropometric Data

Today, there is an increasing availability of human body 3D data and an increasing number of anthropometric owners. This is due to the fact of the progressive conduction of large national surveys using high resolution 3D scanners and due to the increasing number of low-cost technologies for acquiring body shape with electronic consumer devices like webcams, smartphones or Kinect. However, the commercial use and exploitation in industry of digital anthropometric data is still limited to the use of 1D measurements extracted from this vast 3D information. There is a lack of universal resources enabling: to conjointly use and analyse datasets regardless from the source or type of scanning technology used, the flexible measurement extraction beyond pre-defined sets, and the analysis of the information contained in human shapes. This paper presents four software tool solutions aimed at addressing different user profiles and needs regarding the use and exploitation of the increasing number of 3D anthropometric data

Fuzzy control for obstacle detection in object tracking

In previous works, we have studied a fast and robust object tracking system based on optical flow. To solve the occlusion problem, we have developed a combined tracking system based on optical flow and adaptive filters. The critical point of the system is the coupling between optical flow and predictive algorithms. This coupling is governed by parameters such as tolerance, the absolute value of the difference between the value of velocity calculated by the optical flow and the estimated value. In this paper, we propose the use of a fuzzy control system to solve this coupling problem between the different velocities. This technique will provide great robustness to the tracking algorithm.

Fuzzy control for obstacle detection in stereo video sequences

One of the most important problems in 3D tracking is the occlusion effect produced by obstacles. To solve this problem, we have developed a tracking system based on optical flow and stereo vision, combined with adaptive filters to predict the expected 3D velocities of objects. The critical point of the system is the coupling between tracking and predictive algorithms. We propose the use of a fuzzy control system to solve this coupling problem between the different velocities. This technique has been previously tested in 2D video sequences, providing great robustness to the tracking algorithm.

Low-cost 3D foot scanner using a mobile app

The major finding of the present study was that the KS was improved around 10% with the use of IACS. No statistically significant difference was found in BV, PC, AS and IF. However, there was a trend that the AS and PC increased 9% and 5%, respectively. The significant increase of KS and a trend of increase of AS could possibly be explained by the foot arch and heel cup support which can provide evenly distributing pressure under the feet, maintaining alignment of the skeleton of lower extremity and further resulting in the KS and AS (Mulford et al., 2008). However, we found that the BV and PC were not statistically significant between IACS and FI. Although previous study indicated that one of the key factor of BV and PC was the ability to drive the body over a stabilized stride leg (Kageyama et al., 2014), this little improvement of BV and PC might be explained by the high level of the subjects in this study. Further study could include subjects of low level. Previous study indicated that the insole was one of the important factors for attenuating the IM (Chiu and Shiang, 2007). However, IM attenuation could be influenced by insole thickness or stiffness. Therefore, we suggested that thickness or stiffness of IACS was probably not enough to attenuate the IM. In conclusion, IACS provided KS and AS during baseball pitching.

Optical flow method in phase-contrast microscopy images for the diagnosis of primary ciliary dyskinesia through measurement of ciliary beat frequency. Preliminary results

Primary ciliary dyskinesia (PCD) implies cilia with dysmotility or total absence of motility, which may result in sinusitis, chronicbronchitis, bronchiectasis and male infertility. A large number of deficiencies detectable on the ultrastructural level give rise to PCD, but patients with normal cilia ultrastructure are common. An early diagnosis is very important since PCD can cause permanent lung damage. Diagnosis can be difficult and is based on an abnormal ciliary beat frequency (CBF) and beat pattern, accompanied by specific abnormalities of the ciliary axoneme or normal ultrastructural cilia. In this paper, we present a method to determine CBF through the analysis of phase-contrast microscopy imaging acquired using digital high speed video techniques. Beat frequency measurements are made estimating cilia motion by means of an optical flow algorithm. A previous coregistration process is performed to eliminate cell movements due to cilia motion. The algorithm is tested on several isolated ciliar cells, concluding that this method is a robust technique to determine CBF.

Data-driven three-dimensional reconstruction of human bodies using a mobile phone app

The advances and availability of technologies for the acquisition, registration and analysis of the three-dimensional (3D) shape of human bodies (or body parts) are resulting in the formation of large databases of parameterised meshes from which digital human body models can be derived. Such models can be used for the data-driven reconstruction of parameterised human body shapes from partial information such as one-dimensional (1D) measurements or 2D images. In this paper, we propose a new method for the reconstruction of 3D bodies from images gathered with a smartphone or tablet. Moreover, the method is implemented into a prototype app and tested at different levels through three experimental studies including synthetic models, 1:10 scale figurines and real children. The results demonstrate the feasibility of acquiring reliable anthropometric information easily at home by non-experts. This method and implementation have great potential for their application to the personalisation, size recommendation and virtual try-on simulation of wearable products.

Low-Cost Data-Driven 3D Reconstruction and its Applications

This paper describes two approaches for estimating human 3D shapes (i.e. full bodies or feet) using a regular smartphone or just entering a set of parameters (e.g. age, gender and self-taken measurements). The proposed approaches are based on data-driven 3D reconstructions, using parameterised shape spaces created from large 3D body or feet databases. The reconstruction algorithm finds the combination of shape parameters that best matches either the silhouettes extracted from the images or the body measurements entered. Despite not being actual body scanners, these solutions are easy-to-use and can provide enough accuracy for applications such as virtual try-on, made-to-measure or size allocation of certain types of wearables. Moreover, they can be distributed to the final consumer or to the points of sale at a really reduced cost (or even for free), thus overcoming the main barriers to the massive spreading of body scanners’ use to e-commerce, retail shops, new production pipelines or new business models. In order to illustrate these technologies, some examples of application to different contexts are provided, namely virtual worlds, e-commerce and personalisation.