Measurement of energy expenditure is an important tool in sport science and medicine, especially when trying to estimate the extent and intensity of physical activity. However, most approaches still rely on sensors or markers, placed directly on the body. In this paper, we present a novel approach using a fully contact-less, fully automatic method, that relies on computer vision algorithms and widely available and inexpensive imaging sensors. We rely on the estimation of the optical and scene flow to calculate Histograms of Oriented Optical Flow (HOOF) descriptors, which we subsequently augment with the Histograms of Absolute Flow Amplitude (HAFA). Descriptors are fed into regression model, which allows us to estimate energy consumption, and to a lesser extent, the heart rate. Our method has been tested both in lab environment and in realistic conditions of a sport match. Results confirm that these energy expenditures could be derived from purely contact-less observations. The proposed method can be used with different modalities, including near infrared imagery, which extends its future potential.

Real-world environments, inhabited by people, still pose significant challenges to deep learning methods. Object occlusion is one of such problems. Humans deal with the occlusion in a complex way, by changing the viewpoint and using hands to manipulate the scene. However, not all robotic systems can do that due to cost or design constraints. The question we address in this paper is, how well modern object detection methods work on a model case of an intelligent household refrigerator, where numerous occlusions occur. To motivate our research, we actually performed a worldwide survey of refrigerator occupancy to realistically judge the extent of the problem, but the results could be generalized to any unstructured storage environment where people are in charge. The survey results enabled us to generate a dataset of photo-realistic renderings of a typical refrigerator interior, where the object identity, location, and the degree of the refrigerator occupancy are all readily available. Our results are represented as the Average Precision depending on a refrigerator occupancy for two well known deep models.

This work examines the differences between a human and a machine in object recognition tasks. The machine is useful as much as the output classification labels are correct and match the dataset-provided labels. However, very often a discrepancy occurs because the dataset label is different than the one expected by a human. To correct this, the concept of the target user population is introduced. The paper presents a complete methodology for either adapting the output of a pre-trained, state-of-the-art object classification algorithm to the target population or inferring a proper, user-friendly categorization from the target population. The process is called ‘user population re-targeting’. The methodology includes a set of specially designed population tests, which provide crucial data about the categorization that the target population prefers. The transformation between the dataset-bound categorization and the new, population-specific categorization is called the ‘Cognitive Relevance Transform’. The results of the experiments on the well-known datasets have shown that the target population preferred such a transformed categorization by a large margin, that the performance of human observers is probably better than previously thought, and that the outcome of re-targeting may be difficult to predict without actual tests on the target population.

ROSUS 2023 – Računalniška obdelava slik in njena uporaba v Sloveniji 2023 je strokovna računalniška konferenca, ki jo od leta 2006 naprej vsako leto organizira Inštitut za računalništvo iz Fakultete za elektrotehniko, računalništvo in informatiko, Univerze v Mariboru. Konferenca povezuje strokovnjake in raziskovalce s področij digitalne obdelave slik in strojnega vida z uporabniki tega znanja, pri čemer uporabniki prihajajo iz raznovrstnih industrijskih okolij, biomedicine, športa, zabavništva in sorodnih področij. Zbornik konference ROSUS 2023 združuje strokovne prispevke več deset avtorjev, od tega dva vabljena predavanje ter več demonstracijskih prispevkov. Prispevki podajajo najnovejše dosežke slovenskih strokovnjakov s področij digitalne obdelave slik in strojnega vida, osvetljujejo pa tudi trende in novosti na omenjenih strokovnih področjih. Velik poudarek prispevkov je na promoviranju ekonomske koristnosti aplikacij računalniške obdelave slik in vida v slovenskem prostoru. Takšne računalniške aplikacije zaradi visoke natančnosti, robustnosti in izjemnih hitrosti pri obdelovanju informacij nudijo namreč nove priložnosti za uveljavitev na trgu visokih tehnologij.

Segmentation is generally an ill-posed problem since it results in multiple solutions and is, therefore, hard to define ground truth data to evaluate algorithms. The problem can be naively surpassed by using only one annotator per image, but such acquisition doesn't represent the cognitive perception of an image by the majority of people. Nowadays, it is not difficult to obtain multiple segmentations with crowdsourcing, so the only problem that stays is how to get one ground truth segmentation per image. There already exist numerous algorithmic solutions, but most methods are supervised or don't consider confidence per human segmentation. In this paper, we introduce a new segmentation fusion model that is based on K-Modes clustering. Results obtained from publicly available datasets with human ground truth segmentations clearly show that our model outperforms the state-of-the-art on human segmentations.