Karol Majek

Karol Majek

Auto-generated profile, based on publicly available information

Karol Majek

Cufix

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2022 in Waste Management
Verified
Journal Article
Open access
SMSylwia Majchrowska
Sylwia Majchrowska
AMAgnieszka Mikołajczyk
Agnieszka Mikołajczyk
MFMaria Ferlin
Maria Ferlin
ZKZuzanna Klawikowska
Zuzanna Klawikowska
MPMarta A. Plantykow
Marta A. Plantykow
KMKarol Majek
Karol Majek
Waste pollution is one of the most significant environmental issues in the modern world. The importance of recycling is well known, both for economic and ecological reasons, and the industry demands high efficiency. Current studies towards automatic waste detection are hardly comparable due to the lack of benchmarks and widely accepted standards regarding the used metrics and data. Those problems are addressed in this article by providing a critical analysis of over ten existing waste datasets and a brief but constructive review of the existing Deep Learning-based waste detection approaches. This article collects and summarizes previous studies and provides the results of authors' experiments on the presented datasets, all intended to create a first replicable baseline for litter detection. Moreover, new benchmark datasets detect-waste and classify-waste are proposed that are merged collections from the above-mentioned open-source datasets with unified annotations covering all possible waste categories: bio, glass, metal and plastic, non-recyclable, other, paper, and unknown. Finally, a two-stage detector for litter localization and classification is presented. EfficientDet-D2 is used to localize litter, and EfficientNet-B2 to classify the detected waste into seven categories. The classifier is trained in a semi-supervised fashion making the use of unlabeled images. The proposed approach achieves up to 70% of average precision in waste detection and around 75% of classification accuracy on the test dataset. The code and annotations used in the studies are publicly available online1.

26 April 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
AKAleksandra Kos
Aleksandra Kos
KMKarol Majek
Karol Majek
DBDominik Belter
Dominik Belter

16 September 2023 in Pomiary Automatyka Robotyka
Verified
Journal Article
Closed access
AKAleksandra Kos
Aleksandra Kos
DBDominik Belter
Dominik Belter
KMKarol Majek
Karol Majek
In recent years, thanks to the development of Deep Learning methods, there has been significant progress in object detection and other computer vision tasks. While generic object detection is becoming less of an issue for modern algorithms, with the Average...


21 February 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
JBJanusz Marian Bȩdkowski
Janusz Marian Bȩdkowski
MPMichał Pełka
Michał Pełka
KMKarol Majek
Karol Majek
MMMarcin Matecki
Marcin Matecki
ARAdrian Radulescu
Adrian Radulescu
JCJakub Chudziński
Jakub Chudziński
This paper describes a software toolbox for LiDAR and LiDAR-Inertial Odometry qualitative and quantitative evaluation. We provide software as https://github.com/MapsHD organization with all necessary information at https://github.com/MapsHD/HDMapping. Our software contributions are a) ground truth data processing tool, b) dockerized state-of-the-art LO and LIO algorithms, c) multi-session data registration to common coordinate system, d) Absolute Pose Error (APE) and Relative Pose Error (RPE) metrics, e) import/export tools for easier 3D data handling and visualizing e.g. in Cloud Compare software. This software is compatible with ROS1 (Robot Operating System) and ROS2 data formats. We shown an example benchmark of LeGO-LOAM, LIO-SAM, FAST-LIO, DLO, VoxelMap, Faster-LIO, KISS-ICP, CT-ICP, SLICT, DLIO, GLIM, iG-LIO, LIO-EKF, I2EKF-LO, GenZ-ICP, RESPLE, odometry_ros_wrapper, Point-LIO, LOAM-Livox algorithms. For all experiments we provide movies.