Search

Accurately diagnosing Alzheimer’s disease is essential for improving elderly health. Meanwhile, accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer’s disease. However, most of the existing methods perform Alzheimer’s disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two tasks. To address this challenging problem, we propose a novel multi-task learning method, which uses feature interaction to explore the relationship between Alzheimer’s disease diagnosis and mini-mental state examination score prediction. In our proposed method, features from each task branch are firstly decoupled into candidate and non-candidate parts for interaction. Then, we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches, which can promote the learning of each task. We validate the effectiveness of our proposed method on multiple datasets. In Alzheimer’s disease neuroimaging initiative 1 dataset, the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86% and 2.5, respectively. Experimental results show that our proposed method outperforms most state-of-the-art methods. Our proposed method enables accurate Alzheimer’s disease diagnosis and mini-mental state examination score prediction. Therefore, it can be used as a reference for the clinical diagnosis of Alzheimer’s disease, and can also help doctors and patients track disease progression in a timely manner.

Bicycle helmets are a main measure for injury prevention in case of a crash and are a central variable in transport safety studies. Despite this, helmet use data is only collected sporadically, as the observation of helmet use in traffic by human observers is costly and time-consuming. An automated method for the accurate registration of bicycle helmet use would enable the broad and precise registration of cyclists’ helmet use. In this paper, we develop and test a computer vision-based detection method that can be applied to traffic video data. We record bicycle traffic at two observation sites in Copenhagen, Denmark, and annotate a dataset of 4000 cyclists, registering their helmet use. We then train a state-of-the-art object detection algorithm on the detection of cyclists and helmet use. The developed model has good accuracy in registering active cyclists. For helmet use registration on the test data set, there was an underestimation of 0.52% (algorithm registered helmet use: 50.23%; actual helmet use: 50.75%). Cross-testing the algorithm, i.e., training on one observation site and applying it to another, results in a larger underestimation of bicycle helmet use between 5.28% and 6.31%. Finally, we apply the algorithm to a week of video data from two Copenhagen sites, identifying commuting-related peaks of cyclists and registering helmet use differences between the observation sites. This study shows that computer vision algorithms are a feasible method for the automated detection of bicycle helmet use. Further research needs to be conducted to make the site transfer more robust and to increase accuracy levels.

Visual saliency prediction remains an academic challenge due to the diversity and complexity of natural scenes as well as the scarcity of eye movement data on where people look in images. In many practical applications, digital images are inevitably subject to distortions, such as those caused by acquisition, editing, compression or transmission. A great deal of attention has been paid to predicting the saliency of distortion-free pristine images, but little attention has been given to understanding the impact of visual distortions on saliency prediction. In this paper, we first present the CUDAS database - a new distortion-aware saliency benchmark, where eye-tracking data was collected for 60 pristine images and their corresponding 540 distorted formats. We then conduct a statistical evaluation to reveal the behaviour of state-of-the-art saliency prediction models on distorted images and provide insights on building an effective model for distortion-aware saliency prediction. The new database is made publicly available to the research community.

In subjective full-reference image quality assessment, a reference image is distorted at increasing distortion levels. The differences between perceptual image qualities of the reference image and its distorted versions are evaluated, often using degradation category ratings (DCR). However, the DCR has been criticized since differences between rating categories on this ordinal scale might not be perceptually equidistant, and observers may have different understandings of the categories. Pair comparisons (PC) of distorted images, followed by Thurstonian reconstruction of scale values, overcomes these problems. In addition, PC is more sensitive than DCR, and it can provide scale values in fractional, just noticeable difference (JND) units that express a precise perceptional interpretation. Still, the comparison of images of nearly the same quality can be difficult. We introduce boosting techniques embedded in more general triplet comparisons (TC) that increase the sensitivity even more. Boosting amplifies the artefacts of distorted images, enlarges their visual representation by zooming, increases the visibility of the distortions by a flickering effect, or combines some of the above. Experimental results show the effectiveness of boosted TC for seven types of distortion (color diffusion, jitter, high sharpen, JPEG 2000 compression, lens blur, motion blur, multiplicative noise). For our study, we crowdsourced over 1.7 million responses to triplet questions. We give a detailed analysis of the data in terms of scale reconstructions, accuracy, detection rates, and sensitivity gain. Generally, boosting increases the discriminatory power and allows to reduce the number of subjective ratings without sacrificing the accuracy of the resulting relative image quality values. Our technique paves the way to fine-grained image quality datasets, allowing for more distortion levels, yet with high-quality subjective annotations. We also provide the details for Thurstonian scale reconstruction from TC and our annotated dataset, KonFiG-IQA, containing 10 source images, processed using 7 distortion types at 12 or even 30 levels, uniformly spaced over a span of 3 JND units.

Video quality assessment (VQA) methods focus on particular degradation types, usually artificially induced on a small set of reference videos. Hence, most traditional VQA methods under-perform in-the-wild. Deep learning approaches have had limited success due to the small size and diversity of existing VQA datasets, either artificial or authentically distorted. We introduce a new in-the-wild VQA dataset that is substantially larger and diverse: KonVid-150k. It consists of a coarsely annotated set of 153,841 videos having five quality ratings each, and 1,596 videos with a minimum of 89 ratings each. Additionally, we propose new efficient VQA approaches (MLSP-VQA) relying on multi-level spatially pooled deep-features (MLSP). They are exceptionally well suited for training at scale, compared to deep transfer learning approaches. Our best method, MLSP-VQA-FF, improves the Spearman rank-order correlation coefficient (SRCC) performance metric on the commonly used KoNViD-1k in-the-wild benchmark dataset to 0.82. It surpasses the best existing deep-learning model (0.80 SRCC) and hand-crafted feature-based method (0.78 SRCC). We further investigate how alternative approaches perform under different levels of label noise, and dataset size, showing that MLSP-VQA-FF is the overall best method for videos in-the-wild. Finally, we show that the MLSP-VQA models trained on KonVid-150k sets the new state-of-the-art for cross-test performance on KoNViD-1k and LIVE-Qualcomm with a 0.83 and 0.64 SRCC, respectively. For KoNViD-1k this inter-dataset testing outperforms intra-dataset experiments, showing excellent generalization.

Automated detection of motorcycle helmet use through video surveillance can facilitate efficient education and enforcement campaigns that increase road safety. However, existing detection approaches have a number of shortcomings, such as the inabilities to track individual motorcycles through multiple frames, or to distinguish drivers from passengers in helmet use. Furthermore, datasets used to develop approaches are limited in terms of traffic environments and traffic density variations. In this paper, we propose a CNN-based multi-task learning (MTL) method for identifying and tracking individual motorcycles, and register rider specific helmet use. We further release the HELMET dataset, which includes 91,000 annotated frames of 10,006 individual motorcycles from 12 observation sites in Myanmar. Along with the dataset, we introduce an evaluation metric for helmet use and rider detection accuracy, which can be used as a benchmark for evaluating future detection approaches. We show that the use of MTL for concurrent visual similarity learning and helmet use classification improves the efficiency of our approach compared to earlier studies, allowing a processing speed of more than 8 FPS on consumer hardware, and a weighted average F-measure of 67.3% for detecting the number of riders and helmet use of tracked motorcycles. Our work demonstrates the capability of deep learning as a highly accurate and resource efficient approach to collect critical road safety related data.