Master of Science / School of Family Studies and Human Services / Bronwyn S. Fees / Jennifer R. Francois / The mother-infant relationship affects the child’s exploratory and separation behavior, how the child perceives strangers, and significantly impacts the conceptual framework of typical social relationships in the infant’s brain. The purpose of this study was to examine infants’ regulatory strategies, specifically, the relationship between the mother-infant dyad, and the infant’s response to a stressful situation. Eight, 5-month-old infants and their mothers participated in the Face-to-Face Still-Face experiment and a play session to assess maternal sensitivity. Data from the mother-infant dyads were collected during each phase of the Face-to-Face Still-Face paradigm (i.e., play, still-face, and reunion). Maternal sensitivity was assessed using an adapted version of Ainsworth’s four scales of maternal sensitivity. The infant’s strategies for re-engagement with the mother were assessed using eye-tracking methodology to identify specific eye gaze behaviors used during each phase of the still-face experiment. The infants who had more sensitive mothers showed an increase in fixation duration during the reunion phase of the procedure, which could be indicative of a trusting relationship in which the child knows the mother is there to help them regain control of their emotions. Implications of these findings are discussed for the use of eye-tracking methodology as a more flexible and potentially more accurate measure of studying infants’ patterns of ocular focus.

A pose estimation method is proposed for measuring the position and orientation of a biopsy needle. The technique is to be used as a touchless needle guide system for guidance of percutaneous procedures with 4D ultrasound. A pair of uncalibrated, light-weight USB cameras are used as inputs. A database is prepared offline, using both the needle line estimated from camera-captured images and the true needle line recorded from an independent tracking device. A nonparametric learning algorithm determines the best fit model from the database. This model can then be used in real-time to estimate the true position of the needle with inputs from only the camera images. Simulation results confirm the feasibility of the method and show how a small, accurately made database can provide satisfactory results. In a series of tests with cameras, we achieved an average error of 2.4mm in position and 2.61° in orientation. The system is also extended to real ultrasound imaging, as the two miniature cameras capture images of the needle in air and the ultrasound system captures a volume as the needle moves through the workspace. A new database is created with the estimated 3D position of the needle from the ultrasound volume and the 2D position and orientation of the needle calculated from the camera images. This study achieved an average error of 0.94 mm in position and 3.93° in orientation. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

Sound source localization with microphone arrays has received considerable attention as a means for the automated tracking of individuals in an enclosed space and as a necessary component of any general-purpose speech capture and automated camera pointing system. A novel computationally efficient method compared to traditional source localization techniques is proposed and is both theoretically and experimentally investigated in this research. This thesis first reviews the previous work in this area. The evolution of a new localization algorithm accompanied by an array structure for audio signal localization in three dimensional space is then presented. This method, which has similarities to the structure of the eye, consists of a novel hemispherical microphone array with microphones on the shell and one microphone in the center of the sphere. The hemispherical array provides such benefits as 3D coverage, simple signal processing and low computational complexity. The signal processing scheme utilizes parallel computation of a special and novel closeness function for each microphone direction on the shell. The closeness functions have output values that are linearly proportional to the spatial angular difference between the sound source direction and each of the shell microphone directions. Finally by choosing directions corresponding to the highest closeness function values and implementing linear weighted spatial averaging in those directions we estimate the sound source direction. The experimental tests validate the method with less than 3.10 of error in a small office room. Contrary to traditional algorithmic sound source localization techniques, the proposed method is based on parallel mathematical calculations in the time domain. Consequently, it can be easily implemented on a custom designed integrated circuit. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

No description available.

This thesis presents a real-time multi-face tracking system, which is able to track multiple faces for live videos, broadcast, real-time conference recording, etc. The real-time output is one of the most significant advantages. Our proposed tracking system is comprised of three parts: face detection, feature extraction and tracking. We deploy a three-layer Convolutional Neural Network (CNN) to detect a face, a one-layer CNN to extract the features of a detected face and a shallow network for face tracking based on the extracted feature maps of the face. The performance of our multi-face tracking system enables the tracker to run in real-time without any on-line training. This algorithm does not need to change any parameters according to different input video conditions, and the runtime cost will not be affected significantly by an the increase in the number of faces being tracked. In addition, our proposed tracker can overcome most of the generally difficult tracking conditions which include video containing a camera cut, face occlusion, false positive face detection, false negative face detection, e.g. due to faces at the image boundary or faces shown in profile. We use two commonly used metrics to evaluate the performance of our multi-face tracking system demonstrating that our system achieves accurate results. Our multi-face tracker achieves an average runtime cost around 0.035s with GPU acceleration and this runtime cost is close to stable even if the number of tracked faces increases. All the evaluation results and comparisons are tested with four commonly used video data sets.

Tracking multiple articulated objects (such as a human body) and handling occlusion between them is a challenging problem in automated video analysis. This work proposes a new approach for accurately and steadily visual tracking people, which should function even if the system encounters occlusion in video sequences. In this approach, targets are represented with a Gaussian mixture, which are adapted to regions of the target automatically using an EM-model algorithm. Field speeds are defined for changed pixels in each frame based on the probability of their belonging to a particular person's blobs. Pixels are matched to the models using a fast numerical level set method. Since each target is tracked with its blob's information, the system is capable of handling partial or full occlusion during tracking. Experimental results on a number of challenging sequences that were collected in non-experimental environments demonstrate the effectiveness of the approach.

This master thesis deals with tracking the moving object in image. The result of the thesis is designed algorithm which is implemented in the programming language C#. This algorithm improves the functionallity of an existing tracking algorithm.

This master thesis deals with tracking the moving object in image. The result of the thesis is designed algorithm which is implemented in the programming language C#. This algorithm improves the functionallity of an existing tracking algorithm.

archives@tulane.edu / As bilingual populations continue to increase in the US, more research is needed to understand how multilingual language learning may affect child development, especially when developing early literacy skills. To address this question, the current study investigates the differences between monolingual and French-English bilingual children’s handwriting through the use of eye-tracking technology. A sample of 39 second-grade students participated in the study, in which they copied a series of French, English, and nonsense stimulus words of varying lengths. Eye-tracking videos were coded frame-by-frame to assess differences in copying times, reading fluency defined by lookbacks, and motor continuity defined by pen lifts. GLMM analyses suggested evidence for bilingual code switching in which the bilingual group showed increases in stimulus looking times and writing times compared to the monolingual group. As language familiarity increased for the bilingual group, writing became more efficient as evidenced by shorter lookback durations. Furthermore, French and nonsense words were found to require more lookbacks and longer lookbacks than English words across the two groups, suggesting the more familiar English words led to more efficient writing in this particular sample. Further research is needed to determine if these results translate to other languages or if they may change across development. / 1 / Riana Gaudet

Indiana University-Purdue University Indianapolis (IUPUI) / Self driving cars becoming more popular nowadays, which transport with it's own intelligence and take appropriate actions at adequate time. Safety is the key factor in driving environment. A simple fail of action can cause many fatalities. Computer Vision has major part in achieving this, it help the autonomous vehicle to perceive the surroundings. Detection is a very popular technique in helping to capture the surrounding for an autonomous car. At the same time tracking also has important role in this by providing dynamic of detected objects. Autonomous cars combine a variety of sensors such as RADAR, LiDAR, sonar, GPS, odometry and inertial measurement units to perceive their surroundings. Driver-assistive technologies like Adaptive Cruise Control, Forward Collision Warning system (FCW) and Collision Mitigation by Breaking (CMbB) ensure safety while driving. Perceiving the information from environment include setting up sensors on the car. These sensors will collect the data it sees and this will be further processed for taking actions. The sensor system can be a single sensor or multiple sensor. Different sensors have different strengths and weaknesses which makes the combination of them important for technologies like Autonomous Driving. Each sensor will have a limit of accuracy on it's readings, so multi sensor system can help to overcome this defects. This thesis is an attempt to develop a multi sensor multi object tracking method to perceive the surrounding of the ego vehicle. When the Object detection gives information about the presence of objects in a frame, Object Tracking goes beyond simple observation to more useful action of monitoring objects. The experimental results conducted on KITTI dataset indicate that our proposed state estimation system for Multi Object Tracking works well in various challenging environments.