Robust temporal alignment of multimodal cardiac sequences

Given the dynamic nature of cardiac function, correct temporal alignment of pre-operative models and intraoperative images is crucial for augmented reality in cardiac image-guided interventions. As such, the current study focuses on the development of an image-based strategy for temporal alignment of multimodal cardiac imaging sequences, such as cine Magnetic Resonance Imaging (MRI) or 3D Ultrasound (US). First, we derive a robust, modality-independent signal from the image sequences, estimated by computing the normalized crosscorrelation between each frame in the temporal sequence and the end-diastolic frame. This signal is a resembler for the left-ventricle (LV) volume curve over time, whose variation indicates di erent temporal landmarks of the cardiac cycle. We then perform the temporal alignment of these surrogate signals derived from MRI and US sequences of the same patient through Dynamic Time Warping (DTW), allowing to synchronize both sequences. The proposed framework was evaluated in 98 patients, which have undergone both 3D+t MRI and US scans. The end-systolic frame could be accurately estimated as the minimum of the image-derived surrogate signal, presenting a relative error of 1:6 1:9% and 4:0 4:2% for the MRI and US sequences, respectively, thus supporting its association with key temporal instants of the cardiac cycle. The use of DTW reduces the desynchronization of the cardiac events in MRI and US sequences, allowing to temporally align multimodal cardiac imaging sequences. Overall, a generic, fast and accurate method for temporal synchronization of MRI and US sequences of the same patient was introduced. This approach could be straightforwardly used for the correct temporal alignment of pre-operative MRI information and intra-operative US images.

Real-Time Multimodal Retinal Image Registration for a Computer Assisted Laser Photocoagulation System

An algorithm for the real-time registration of a retinal video sequence captured with a scanning digital ophthalmoscope (SDO) to a retinal composite image is presented. This method is designed for a computer-assisted retinal laser photocoagulation system to compensate for retinal motion and hence enhance the accuracy, speed, and patient safety of retinal laser treatments. The procedure combines intensity and feature-based registration techniques. For the registration of an individual frame, the translational frame-to-frame motion between preceding and current frame is detected by normalized cross correlation. Next, vessel points on the current video frame are identified and an initial transformation estimate is constructed from the calculated translation vector and the quadratic registration matrix of the previous frame. The vessel points are then iteratively matched to the segmented vessel centerline of the composite image to refine the initial transformation and register the video frame to the composite image. Criteria for image quality and algorithm convergence are introduced, which assess the exclusion of single frames from the registration process and enable a loss of tracking signal if necessary. The algorithm was successfully applied to ten different video sequences recorded from patients. It revealed an average accuracy of 2.47 ± 2.0 pixels (∼23.2 ± 18.8 μm) for 2764 evaluated video frames and demonstrated that it meets the clinical requirements.

Spatio-temporal alignment of pedobarographic image sequences

O documento em anexo encontra-se na versão post-print (versão corrigida pelo editor).

Hand gesture spotting and recognition using HMMs and CRFs in color image sequences

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2010

Vision-based representation and recognition of human activities in image sequences

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013

Towards Detecting Changes in Underwater Image Sequences

Detecting changes between images of the same scene taken at different times is of great interest for monitoring and understanding the environment. It is widely used for on-land application but suffers from different constraints. Unfortunately, Change detection algorithms require highly accurate geometric and photometric registration. This requirement has precluded their use in underwater imagery in the past. In this paper, the change detection techniques available nowadays for on-land application were analyzed and a method to automatically detect the changes in sequences of underwater images is proposed. Target application scenarios are habitat restoration sites, or area monitoring after sudden impacts from hurricanes or ship groundings. The method is based on the creation of a 3D terrain model from one image sequence over an area of interest. This model allows for synthesizing textured views that correspond to the same viewpoints of a second image sequence. The generated views are photometrically matched and corrected against the corresponding frames from the second sequence. Standard change detection techniques are then applied to find areas of difference. Additionally, the paper shows that it is possible to detect false positives, resulting from non-rigid objects, by applying the same change detection method to the first sequence exclusively. The developed method was able to correctly find the changes between two challenging sequences of images from a coral reef taken one year apart and acquired with two different cameras

Classification of urban multi-angular image sequences by aligning their manifolds

When dealing with multi-angular image sequences, problems of reflectance changes due either to illumination and acquisition geometry, or to interactions with the atmosphere, naturally arise. These phenomena interplay with the scene and lead to a modification of the measured radiance: for example, according to the angle of acquisition, tall objects may be seen from top or from the side and different light scatterings may affect the surfaces. This results in shifts in the acquired radiance, that make the problem of multi-angular classification harder and might lead to catastrophic results, since surfaces with the same reflectance return significantly different signals. In this paper, rather than performing atmospheric or bi-directional reflection distribution function (BRDF) correction, a non-linear manifold learning approach is used to align data structures. This method maximizes the similarity between the different acquisitions by deforming their manifold, thus enhancing the transferability of classification models among the images of the sequence.

People Recognition in Image Sequences by Supervised Learning

We describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by color-based and shape-based features. Recognition is carried out through combinations of Support Vector Machine classifiers (SVMs). Different types of multiclass strategies based on SVMs are explored and compared to k-Nearest Neighbors classifiers (kNNs). The system works in real time and shows high performance rates for people recognition throughout one day.

Towards Detecting Changes in Underwater Image Sequences

Detecting changes between images of the same scene taken at different times is of great interest for monitoring and understanding the environment. It is widely used for on-land application but suffers from different constraints. Unfortunately, Change detection algorithms require highly accurate geometric and photometric registration. This requirement has precluded their use in underwater imagery in the past. In this paper, the change detection techniques available nowadays for on-land application were analyzed and a method to automatically detect the changes in sequences of underwater images is proposed. Target application scenarios are habitat restoration sites, or area monitoring after sudden impacts from hurricanes or ship groundings. The method is based on the creation of a 3D terrain model from one image sequence over an area of interest. This model allows for synthesizing textured views that correspond to the same viewpoints of a second image sequence. The generated views are photometrically matched and corrected against the corresponding frames from the second sequence. Standard change detection techniques are then applied to find areas of difference. Additionally, the paper shows that it is possible to detect false positives, resulting from non-rigid objects, by applying the same change detection method to the first sequence exclusively. The developed method was able to correctly find the changes between two challenging sequences of images from a coral reef taken one year apart and acquired with two different cameras

A bridge-ship collision avoidance system based on FLIR image sequences

In this paper, a forward-looking infrared (FLIR) video surveillance system is presented for collision avoidance of moving ships to bridge piers. An image preprocessing algorithm is proposed to reduce clutter background by multi-scale fractal analysis, in which the blanket method is used for fractal feature computation. Then, the moving ship detection algorithm is developed from image differentials of the fractal feature in the region of surveillance between regularly interval frames. When the moving ships are detected in region of surveillance, the device for safety alert is triggered. Experimental results have shown that the approach is feasible and effective. It has achieved real-time and reliable alert to avoid collisions of moving ships to bridge piers.

Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Cardiac image fusion from stand-alone SPECT and CT: clinical experience

Myocardial perfusion imaging with SPECT (SPECT-MPI) and 64-slice CT angiography (CTA) are both established techniques for the noninvasive evaluation of coronary artery disease (CAD). Three-dimensional (3D) SPECT/CT image fusion may offer an incremental diagnostic value by integrating both sets of information. We report our first clinical experiences with fused 3D SPECT/CT in CAD patients. METHODS: Thirty-eight consecutive patients with at least 1 perfusion defect on SPECT-MPI (1-d adenosine stress/rest SPECT with (99m)Tc-tetrofosmin) and 64-slice CTA were included. 3D volume-rendered fused SPECT/CT images were generated and compared with the findings from the side-by-side analysis with regard to coronary lesion interpretation by assigning the perfusion defects to their corresponding coronary lesion. RESULTS: The fused SPECT/CT images added information on pathophysiologic lesion severity in 27 coronary stenoses (22%) of 12 patients (29%) (P<0.001). Among 40 equivocal lesions on side-by-side analysis, the fused interpretation confirmed hemodynamic significance in 14 lesions and excluded functional relevance in 10 lesions. In 3 lesions, assignment of perfusion defect and coronary lesion appeared to be reliable on side-by-side analysis but proved to be inaccurate on fused interpretation. Added diagnostic information by SPECT/CT was more commonly found in patients with stenoses of small vessels (P=0.004) and involvement of diagonal branches (P=0.01). CONCLUSION: In addition to being intuitively convincing, 3D SPECT/CT fusion images in CAD may provide added diagnostic information on the functional relevance of coronary artery lesions.

A Novel Prediction Method for Early Recognition of Global Human Behaviour in Image Sequences

Human behaviour recognition has been, and still remains, a challenging problem that involves different areas of computational intelligence. The automated understanding of people activities from video sequences is an open research topic in which the computer vision and pattern recognition areas have made big efforts. In this paper, the problem is studied from a prediction point of view. We propose a novel method able to early detect behaviour using a small portion of the input, in addition to the capabilities of it to predict behaviour from new inputs. Specifically, we propose a predictive method based on a simple representation of trajectories of a person in the scene which allows a high level understanding of the global human behaviour. The representation of the trajectory is used as a descriptor of the activity of the individual. The descriptors are used as a cue of a classification stage for pattern recognition purposes. Classifiers are trained using the trajectory representation of the complete sequence. However, partial sequences are processed to evaluate the early prediction capabilities having a specific observation time of the scene. The experiments have been carried out using the three different dataset of the CAVIAR database taken into account the behaviour of an individual. Additionally, different classic classifiers have been used for experimentation in order to evaluate the robustness of the proposal. Results confirm the high accuracy of the proposal on the early recognition of people behaviours.