1. Efficient compressed storage and fast reconstruction of large binary images using chain codesDamjan Strnad, Danijel Žlaus, Andrej Nerat, Borut Žalik, 2024, izvirni znanstveni članek Opis: Large binary images are used in many modern applications of image processing. For instance, they serve as inputs or target masks for training machine learning (ML) models in computer vision and image segmentation. Storing large binary images in limited memory and loading them repeatedly on demand, which is common in ML, calls for efficient image encoding and decoding mechanisms. In the paper, we propose an encoding scheme for efficient compressed storage of large binary images based on chain codes, and introduce a new single-pass algorithm for fast parallel reconstruction of raster images from the encoded representation. We use three large real-life binary masks to test the efficiency of the proposed method, which were derived from vector layers of single-class objects – a building cadaster, a woody vegetation landscape feature map, and a road network map. We show that the masks encoded by the proposed method require significantly less storage space than standard lossless compression formats. We further compared the proposed method for mask reconstruction from chain codes with a recent state-of-the-art algorithm, and achieved between and faster reconstruction on test data
Ključne besede: binary mask, machine learning, chain code, binary encoding, bitmap reconstruction
Objavljeno v DKUM: 29.01.2025; Ogledov: 0; Prenosov: 7
 Celotno besedilo (1,45 MB) |
2. Efficient encoding and decoding of voxelized models for machine learning-based applicationsDamjan Strnad, Štefan Kohek, Borut Žalik, Libor Váša, Andrej Nerat, 2025, izvirni znanstveni članek Opis: Point clouds have become a popular training data for many practical applications of machine learning in the fields of environmental modeling and precision agriculture. In order to reduce high space requirements and the effect of noise in the data, point clouds are often transformed to a structured representation such as a voxel grid. Storing, transmitting and consuming voxelized geometry, however, remains a challenging problem for machine learning pipelines running on devices with limited amount of on-chip memory with low access latency. A viable solution is to store the data in a compact encoded format, and perform on-the-fly decoding when it is needed for processing. Such on-demand expansion must be fast in order to avoid introducing substantial additional delay to the pipeline. This can be achieved by parallel decoding, which is particularly suitable for massively parallel architecture of GPUs on which the majority of machine learning is currently executed. In this paper, we present such method for efficient and parallelizable encoding/decoding of voxelized geometry. The method employs multi-level context-aware prediction of voxel occupancy based on the extracted binary feature prediction table, and encodes the residual grid with a pointerless sparse voxel octree (PSVO). We particularly focused on encoding the datasets of voxelized trees, obtained from both synthetic tree models and LiDAR point clouds of real trees. The method achieved 15.6% and 12.8% reduction of storage size with respect to plain PSVO on synthetic and real dataset, respectively. We also tested the method on a general set of diverse voxelized objects, where an average 11% improvement of storage space was achieved.
Ključne besede: voxel grid, feature prediction, tree models, prediction-based encoding, key voxels, residuals, sparse voxel octree
Objavljeno v DKUM: 09.01.2025; Ogledov: 0; Prenosov: 5
Celotno besedilo (20,93 MB) |
3. Region segmentation of images based on a raster-scan paradigmLuka Lukač, Andrej Nerat, Damjan Strnad, Štefan Horvat, Borut Žalik, 2024, izvirni znanstveni članek 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: 3
 Povezava na datoteko |
4. |
5. Geometric Shape Characterisation Based on a Multi-Sweeping ParadigmBorut Žalik, Damjan Strnad, David Podgorelec, Ivana Kolingerová, Andrej Nerat, Niko Lukač, Štefan Kohek, Luka Lukač, 2023, izvirni znanstveni članek Ključne besede: computer science, image analysis, computational geometry, local reflection symmetry
Objavljeno v DKUM: 24.05.2024; Ogledov: 300; Prenosov: 15
Celotno besedilo (1,87 MB)
Gradivo ima več datotek! Več... |
6. FLoCIC: A Few Lines of Code for Raster Image CompressionBorut Žalik, Damjan Strnad, Štefan Kohek, Ivana Kolingerová, Andrej Nerat, Niko Lukač, Bogdan Lipuš, Mitja Žalik, David Podgorelec, 2023, izvirni znanstveni članek Ključne besede: computer science, algorithm, prediction, interpolative coding, PNG, JPEG LS, JPEG 2000 lossless
Objavljeno v DKUM: 22.05.2024; Ogledov: 165; Prenosov: 26
Celotno besedilo (10,78 MB)
Gradivo ima več datotek! Več... |
7. LiDAR-Based Maintenance of a Safe Distance between a Human and a Robot ArmDavid Podgorelec, Suzana Uran, Andrej Nerat, Božidar Bratina, Sašo Pečnik, Marjan Dimec, Franc Žaberl, Borut Žalik, Riko Šafarič, 2023, izvirni znanstveni članek Opis: This paper focuses on a comprehensive study of penal policy in Slovenia in the last 70 years, providing an analysis of statistical data on crime, conviction, and prison populations. After a sharp political and penal repression in the first years after World War II, penal and prison policy began paving the way to a unique "welfare sanction system", grounded in ideas of prisoners' treatment. After democratic reforms in the early 1990s, the criminal legislation became harsher, but Slovenia managed to avoid the general punitive trends characterized by the era of penal state and culture of control. The authoritarian socialist regime at its final stage had supported the humanization of the penal system, and this trend continued in the first years of the democratic reforms in the 1990s, but it lost its momentum after 2000. In the following two decades, Slovenia experienced a continuous harshening of criminal law and sanctions on the one hand and an increasing prison population rate on the other. From 2014 onwards, however, there was a decrease in all segments of penal statistics. The findings of the study emphasize the exceptionalism of Slovenian penal policy, characterized by penal moderation, which is the product of the specific local historical, political, economic, and normative developments.
Ključne besede: LIDAR, robot, human-robot collaboration, speed and separation monitoring, intelligent control system, geometric data registration, motion prediction
Objavljeno v DKUM: 16.02.2024; Ogledov: 417; Prenosov: 34
Celotno besedilo (5,27 MB)
Gradivo ima več datotek! Več... |
8. |
