Active and Assisted Living (AAL) technologies aim to enhance the quality of life of older adults and promote successful aging. While video-based AAL solutions offer rich capabilities for better healthcare management in older age, they pose significant privacy risks. To mitigate the risks, we developed a video-based monitoring system that incorporates different privacy-preserving filters. We deployed the system in one assistive technology center and conducted a qualitative study with older adults and other stakeholders involved in care provision. Our study demonstrates diverse users’ perceptions and experiences with video-monitoring technology and offers valuable insights for the system’s further development. The findings unpack the privacy-versus-safety trade-off inherent in video-based technologies and discuss how the privacy-preserving mechanisms within the system mitigate privacy-related concerns. The study also identifies varying stakeholder perspectives towards the system in general and highlights potential avenues for developing video-based monitoring technologies in the AAL context.

Abstract Human skin segmentation is a crucial task in computer vision and biometric systems, yet it poses several challenges such as variability in skin colour, pose, and illumination. This paper presents a robust data-driven skin segmentation method for a single image that addresses these challenges through the integration of contextual information and efficient network design. In addition to robustness and accuracy, the integration into real-time systems requires a careful balance between computational power, speed, and performance. The proposed method incorporates two attention modules, Body Attention and Skin Attention, that utilize contextual information to improve segmentation results. These modules draw attention to the desired areas, focusing on the body boundaries and skin pixels, respectively. Additionally, an efficient network architecture is employed in the encoder part to minimize computational power while retaining high performance. To handle the issue of noisy labels in skin datasets, the proposed method uses a weakly supervised training strategy, relying on the Skin Attention module. The results of this study demonstrate that the proposed method is comparable to, or outperforms, state-of-the-art methods on benchmark datasets.

Abstract This paper reviews the state of the art in visual privacy protection techniques, with particular attention paid to techniques applicable to the field of Active and Assisted Living (AAL). A novel taxonomy with which state-of-the-art visual privacy protection methods can be classified is introduced. Perceptual obfuscation methods, a category in this taxonomy, is highlighted. These are a category of visual privacy preservation techniques, particularly relevant when considering scenarios that come under video-based AAL monitoring. Obfuscation against machine learning models is also explored. A high-level classification scheme of privacy by design, as defined by experts in privacy and data protection law, is connected to the proposed taxonomy of visual privacy preservation techniques. Finally, we note open questions that exist in the field and introduce the reader to some exciting avenues for future research in the area of visual privacy.

The overexploitation of seas and oceans is a major problem that affects the world's fisheries. One of the main consequences is the loss of marine biodiversity that affects not only the ecosystem themselves but also the fishing industries. Nowadays, the fishing sector is immersed in a crucial process of digitization, as it is a traditional sector that lacks, among other things, complete, accurate, and reliable information on fish catches. Being able to know the species that arrive at fish markets can give stakeholders a detailed picture of the general health of the fisheries, as well as that of the populations of particular species of interest, to take appropriate actions. This paper presents an automated monitoring system of fish catches in fish markets based on computer vision and deep learning methods. Specifically, the system can identify instances of fish species based on Yolact models. Experiments have been performed comparing different network backbone architectures using the newly introduced DeepFish dataset for direct in-tray recognition,

This work presents an approach to detect moving objects from Unmanned Aerial Vehicles (UAV). A common framework for most of the existing techniques is using image registration to warp consecutive frames as an ego-motion compensation step and applying frame differencing to detect the moving objects. Assuming a planar scene, we propose the exploitation of telemetry information available from Global Positioning and Inertial Navigation Systems (GPS/INS) to estimate a similarity transformation matrix that would map the image points from one frame to another. In this work, we show that the telemetry-based image registration combined with global registration methods produces more accurate results than the traditional image registration techniques in case of a scene with poor or no texture. To segment the moving objects, we employ the probabilistic background modelling method with mixture of Gaussian distributions.

Track let plots (TPs) describe the motion patterns of a small crowd or a large group of people in a given short time span. This feature can be useful in the context of a Bag-of-Words modelling for the recognition of events or actions that unfold in the scene. This work describes a method where evidence from multiple viewpoints is combined. By obtaining this feature for each of the views, and synchronising the available video streams, a feature-level fusion method by concatenation can be effortlessly applied. The presented system is able to recognise specific events in large groups of people from multiple cameras, and to perform equally well as compared to the best single view available. Furthermore, the dimension of the concatenated feature can be reduced by one order of magnitude without loss of performance.