Iskanje po katalogu digitalne knjižnice

Opis: This study focuses on the segmentation part in the development of a potato-sorting system that utilizes camera input for the segmentation and classification of potatoes. The key challenge addressed is the need for efficient segmentation to allow the sorter to handle a higher volume of potatoes simultaneously. To achieve this, the study employs a region-based convolutional neural network (R-CNN) approach for the segmentation task, while trying to achieve more precise segmentation than with classic CNN-based object detectors. Specifically, Mask R-CNN is implemented and evaluated based on its performance with different parameters in order to achieve the best segmentation results. The implementation and methodologies used are thoroughly detailed in this work. The findings reveal that Mask R-CNN models can be utilized in the production process of potato sorting and can improve the process.
Ključne besede: image segmentation, potato sorting, neural network, mask RCNN, object detection, production process, machine learning, AI
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 10
Celotno besedilo (5,97 MB)
Gradivo ima več datotek! Več...

Opis: This paper introduces a new method for the region segmentation of images. The approach is based on the raster-scan paradigm and builds the segments incrementally. The pixels are processed in the raster-scan order, while the construction of the segments is based on a distance metric in regard to the already segmented pixels in the neighbourhood. The segmentation procedure operates in linear time according to the total number of pixels. The proposed method, named the RSM (raster-scan segmentation method), was tested on selected images from the popular benchmark datasets MS COCO and DIV2K. The experimental results indicate that our method successfully extracts regions with similar pixel values. Furthermore, a comparison with two of the well-known segmentation methods—Watershed and DBSCAN—demonstrates that the proposed approach is superior in regard to efficiency while yielding visually similar results.
Ključne besede: segment, image analysis, distance metric, Watershed, DBSCAN
Objavljeno v DKUM: 05.12.2024; Ogledov: 0; Prenosov: 4
Povezava na datoteko

Opis: Instagram is an essential visual social media platform where tourism organizations can present their destinations. These presentations could feature authentic natural and cultural sites, be user-generated, etc. Dubrovnik is a prominent tourism destination in Croatia. In 2011, it became famous as an onsite filming location for the globally popular TV series Game of Thrones. In this thesis, we investigate whether the Croatian National Tourism Organisation and the Dubrovnik Local Tourism Organisation present the city as a film destination featuring Game of Thrones or as an authentic destination featuring its heritage and nature. We explore destination image construction, including identity, authenticity, decision-making, and promotion. We also discuss film-induced tourism and the role of social media, mainly through user-generated content and Instagram. For our research, we employed content and thematic analysis using a summative approach to analyze photos from 2016 to 2020 on the official Instagram profiles of the National and Local Tourism Organisations, totaling 1.034 photos. The results show that the National Tourism Organisation uses Dubrovnik’s relationship with Game of Thrones to fabricate the authenticity of the destination image, while the Local Tourism Organisation focuses solely on heritage and nature, thus guarding its authenticity. This discrepancy highlights different communication strategies and underscores the importance of understanding these differences for effective destination marketing, providing insights for more cohesive and authentic promotional strategies
Ključne besede: film-induced tourism, social media, destination image, authenticity, Dubrovnik, Game of Thrones
Objavljeno v DKUM: 16.10.2024; Ogledov: 0; Prenosov: 17
Celotno besedilo (3,83 MB)

Opis: The goal of this study was to develop an automated monitoring system for the detection of pigs’ bodies, heads and tails. The aim in the first part of the study was to recognize individual pigs (in lying and standing positions) in groups and their body parts (head/ears, and tail) by using machine learning algorithms (feature pyramid network). In the second part of the study, the goal was to improve the detection of tail posture (tail straight and curled) during activity (standing/moving around) by the use of neural network analysis (YOLOv4). Our dataset (n = 583 images, 7579 pig posture) was annotated in Labelbox from 2D video recordings of groups (n = 12–15) of weaned pigs. The model recognized each individual pig’s body with a precision of 96% related to threshold intersection over union (IoU), whilst the precision for tails was 77% and for heads this was 66%, thereby already achieving human-level precision. The precision of pig detection in groups was the highest, while head and tail detection precision were lower. As the first study was relatively time-consuming, in the second part of the study, we performed a YOLOv4 neural network analysis using 30 annotated images of our dataset for detecting straight and curled tails. With this model, we were able to recognize tail postures with a high level of precision (90%).
Ključne besede: pig, welfare, image processing, object detection, deep learning, smart farming
Objavljeno v DKUM: 11.07.2024; Ogledov: 87; Prenosov: 9
Celotno besedilo (48,11 MB)
Gradivo ima več datotek! Več...

Opis: Marine phanerogams are considered biological sentinels or indicators since any modification in seagrass meadow distribution and coverage signals negative changes in the marine environment. In recent decades, seagrass meadows have undergone global losses at accelerating rates, and almost one-third of their coverage has disappeared globally. This study focused on the dynamics of seagrass meadows in the northern Adriatic Sea, which is one of the most anthropogenically affected areas in the Mediterranean Sea. Seagrass distribution data and remote sensing products were utilized to identify the stable and dynamic parts of the seagrass ecosystem. Different seagrass species could not be distinguished with the Sentinel-2 (BOA) satellite image. However, results revealed a generally stable seagrass meadow (283.5 Ha) but, on the other hand, a stochastic behavior in seagrass meadow retraction (90.8 Ha) linked to local environmental processes associated with anthropogenic activities or climate change. If systemized, this proposed approach to monitoring seagrass meadow dynamics could be developed as a spatial decision support system for the entire Mediterranean basin. Such a tool could serve as a key element for decision makers in marine protected areas and would potentially support more effective conservation and management actions in these highly productive and important environments.
Ključne besede: Adriatic Sea, seagrass meadow, change analysis, Cimodocea nodosa, image classifiers, Sentinel-2, marine biology, hydrobiology
Objavljeno v DKUM: 17.05.2024; Ogledov: 152; Prenosov: 17
Celotno besedilo (3,45 MB)
Gradivo ima več datotek! Več...