Adrienne Heinrich

Automatic Imaging System With Decision Support for Inspection of Pigmented Skin Lesions and Melanoma Diagnosis

In this paper, we describe an automatic system for inspection of pigmented skin lesions and melanoma diagnosis, which supports images of skin lesions acquired using a conventional (consumer level) digital camera. More importantly, our system includes a decision support component, which combines the outcome of the image classification with context knowledge such as skin type, age, gender, and affected body part. This allows the estimation of the personal risk of melanoma, so as to add confidence to the classification. We found that our system classified images with an accuracy of 86%, with a sensitivity of 94%, and specificity of 68%. The addition of context knowledge was indeed able to point to images that were erroneously classified as benign, albeit not to all of them.

Optimization of Hierarchical 3DRS Motion Estimators for Picture Rate Conversion

There is a continuous pressure to lower the implementation complexity and improve the quality of motion-compensated picture rate conversion methods. Since the concept of hierarchy can be advantageously applied to many motion estimation methods, we have extended and improved the current state-of-the-art motion estimation method in this field, 3-D Recursive Search (3DRS), with this concept. We have explored the extensive parameter space and present an analysis of the importance and influence of the various parameters for the application of picture rate conversion. Since well-performing motion estimation methods for picture rate conversion show a tradeoff between prediction accuracy and spatial motion field consistency, determining the optimal tradeoff is an important part of the analysis. We found that the proposed motion estimators are superior to multiple existing techniques as well as standard 3DRS with regard to performance at a low computational complexity.

A Novel Performance Measure for Picture Rate Conversion Methods

Motion compensated interpolation (MCI) is crucial for motion portrayal improvement of modern displays, and film judder elimination. As MCI complexity grows, subjective optimization becomes cumbersome and elaborate. We present an objective metric that matches perception better than earlier measures and apply it to evaluate recent MCI algorithms.

Robust and Sensitive Video Motion Detection for Sleep Analysis

In this paper, we propose a camera-based system combining video motion detection, motion estimation, and texture analysis with machine learning for sleep analysis. The system is robust to time-varying illumination conditions while using standard camera and infrared illumination hardware. We tested the system for periodic limb movement (PLM) detection during sleep, using EMG signals as a reference. We evaluated the motion detection performance both per frame and with respect to movement event classification relevant for PLM detection. The Matthews correlation coefficient improved by a factor of 2, compared to a state-of-the-art motion detection method, while sensitivity and specificity increased with 45% and 15%, respectively. Movement event classification improved by a factor of 6 and 3 in constant and highly varying lighting conditions, respectively. On 11 PLM patient test sequences, the proposed system achieved a 100% accurate PLM index (PLMI) score with a slight temporal misalignment of the starting time ( 1 s) regarding one movement. We conclude that camera-based PLM detection during sleep is feasible and can give an indication of the PLMI score.

Body movement analysis during sleep based on video motion estimation

To assess sleep in the home situation, wrist actigraphy is often used. However, it requires an on-body sensor which may disturb sleep and primarily collects data on the movement of one wrist only. Video actigraphy, by estimating motion from captured infrared images, overcome these issues. In this paper, we compare activity levels from wrist and full body video actigraphy in a home setting. Video actigraphy correctly found 19 % more small and medium movements that were missed by the wrist sensor. We further show that similar values of sleep efficiency (SE, %) are obtained from simultaneous recordings of video and wrist actigraphy, and we compared both to reference SE values provided by a full polysomnography (PSG). The proposed video actigraphy proved convenient and easy to use in real home situations. It successfully found movements originating from under the blanket, and turned out robust to various sleeping positions, different illumination conditions, viewing angles, beds and blankets. Our results suggest that on-body actigraph sensors can be successfully replaced with the proposed video-based solution for the application of unobtrusive sleep monitoring and analysis.

Robust Motion Estimation Design Methodology

For motion-adaptive video retiming methods, the quest to lower the implementation complexity and improve the quality of motion estimation algorithms still continues. Comparing different motion estimators (MEs) and/or fine-tuning ME parameters is a time-consuming task, and it is even more demanding to identify the MEs with a robust performance among all the well-performing MEs. Therefore, a computer-aided design methodology is required to effectively explore the large design space. Such a methodology requires objective performance metrics. As it is hard to find perfect metrics, we present a design methodology that can use suboptimal measures and still identify robust MEs. The proposed methodology is demonstrated using two different MEs.

Lifestyle applications from sleep research

Most of the research performed in the area of movement analysis of sleeping subjects has been targeted at sleep stage classification or monitoring of sleep disorders. In this paper, we present an innovative approach and show how movement analysis of sleeping subjects can be used to enable new lifestyle related applications. The first application we propose shows how a sleeping subject’s movement pattern can be used to build an intelligent wake-up light system. The second application targets an intelligent baby monitor that informs parents about changes of their baby’s pose in its sleep. For the two proposed systems, we present design considerations and initial results showing the potential of camera-based movement analysis in sleep related applications outside the common interest.

Multi-distance motion vector clustering algorithm for video-based sleep analysis

Overall health and daily functioning deteriorate with poor sleep. To improve ones sleep, sleep monitoring can help identifying causes of sleep problems. As an advantage over traditional wrist actigraphy used in home sleep monitoring solutions, video contains more comprehensive movement information. Particularly, different body movements can be distinguished which is beneficial for a more detailed sleep analysis. We developed an efficient K-Means clustering method with a multi-distance seeding technique to find the dominant cluster candidates. An integrated multi-distance dissimilarity measure was used for the subsequent clustering. We present an automatic content-dependent weight tuning method for the dissimilarity measure to balance between different distance descriptors. This discriminative algorithm partitions similar body movements in the same cluster. We were able to produce several dissimilarity measures producing clusters that agreed 67% with manual clustering of motion vectors by one expert. Similar clustering characteristics were preferred by both the five expert annotators and the suggested clustering algorithm. This gives us confidence that the proposed optimization method can be used in the future.

Shared-bed person segmentation based on motion estimation

Video-based sleep analysis is a topic with important applications, and shared-bed occurs frequently in the context of sleep. One difficulty for the shared-bed situation is to assign the movements to the correct person because they can occur in close proximity and even overlapping. To manage to achieve person segmentation in the shared-bed situation, in this paper we propose an approach to correctly segment the region of persons based on motion estimation. In our approach, considering the consistency of the motion vectors, specifically their length and angle, the adjacent blocks are clustered. The generated clusters are then assigned to a person according to temporal correlation. The occupied region of the person is updated each frame based on the assignment result of the clusters. The proposed approach tackles the segmentation issue when the two persons are close to each other or even overlap, and the accuracy of the segmentation is beyond 82% in the data set we acquired.