Piotr Woźniak

Dr. Piotr Woźniak

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
14 September 2018
Verified
Book Chapter
Closed access
PDF file
PWPiotr Woźniak
Piotr Woźniak
HAHadha Afrisal
Hadha Afrisal
RERigel Galindo Esparza
Rigel Galindo Esparza
BKBogdan Kwolek
Bogdan Kwolek

19 May 2025 in Scientific Data
Verified
Journal Article
Open access
PDF file
PWPiotr Woźniak
Piotr Woźniak
Tomasz KrzeszowskiTomasz Krzeszowski
Tomasz Krzeszowski
BKBogdan Kwolek
Bogdan Kwolek
Visual location recognition encompasses place recognition (PR) and anomaly detection (AD). These are crucial tasks for autonomous robots to accurately determine the location and the occupied place. To accelerate research in this area, we introduce a multi-domain dataset for indoor visual place recognition and anomaly detection by mobile robots. The dataset includes 89,550 RGB images captured in nine rooms. The data collection process involved both manual recordings and recordings captured by mobile robots. The images depict a wide range of scenarios, including variations in lighting, robot vision, and human activity. Additionally, we provide an analysis of other available datasets referenced in the literature. This article presents a freely available dataset for research on place recognition and presents an example application in the field of anomaly detection. The baseline methods were thoroughly tested and achieved an 80.18% accuracy in anomaly detection for single images and 80.63%-84.18% for image sequences. The article includes a comprehensive presentation of the characteristics of individual image sequences and the most significant conclusions drawn from the research.

4 July 2023 in Sensors
Verified
Journal Article
Open access
PDF file
PWPiotr Woźniak
Piotr Woźniak
DODominik Ożóg
Dominik Ożóg
The article presents an algorithm for the multi-domain visual recognition of an indoor place. It is based on a convolutional neural network and style randomization. The authors proposed a scene classification mechanism and improved the performance of the models based on synthetic and real data from various domains. In the proposed dataset, a domain change was defined as a camera model change. A dataset of images collected from several rooms was used to show different scenarios, human actions, equipment changes, and lighting conditions. The proposed method was tested in a scene classification problem where multi-domain data were used. The basis was a transfer learning approach with an extension style applied to various combinations of source and target data. The focus was on improving the unknown domain score and multi-domain support. The results of the experiments were analyzed in the context of data collected on a humanoid robot. The article shows that the average score was the highest for the use of multi-domain data and data style enhancement. The method of obtaining average results for the proposed method reached the level of 92.08%. The result obtained by another research team was corrected.


19 August 2026 in Electronics
Verified
Journal Article
Open access
PDF file
KGKamil Gomułka
Kamil Gomułka
PWPiotr Woźniak
Piotr Woźniak
Tomasz KrzeszowskiTomasz Krzeszowski
Tomasz Krzeszowski
Human action recognition relies heavily on large-scale annotated video datasets, which are costly and time-consuming to curate, while AI-generated videos offer a promising alternative data source, their effectiveness for training action recognition models remains insufficiently explored. This study evaluates AI-generated videos for action recognition across convolutional and transformer-based architectures using real, synthetic, and hybrid datasets. To ensure generative diversity and consistency, a structured prompt engineering pipeline combining action descriptions, environmental contexts, and camera viewpoints was developed. Synthetic datasets were generated using the Grok Imagine and Meta AI Vibes video generation models and paired with a 15-class subset of the Human Motion Database 51 (HMDB51) to construct the Generative Synthetic Human Action Recognition Dataset (GenSynth-HARD). To mitigate domain shift arising from discrepancies between real and AI-generated videos, a Conditional Domain Adversarial Network (CDAN) with a dynamically scaled Gradient Reversal Layer (GRL) was integrated for domain feature alignment. The best-performing hybrid model achieved a Top-1 accuracy of 79.92% on the HMDB51 subset, demonstrating that incorporating synthetic videos effectively supports model performance while significantly reducing annotation overhead.

27 November 2025 in Sensors
Verified
Journal Article
Open access
PDF file
PWPiotr Woźniak
Piotr Woźniak
PPPaweł Penar
Paweł Penar
DBDamian Bielecki
Damian Bielecki
In this paper, we present a stair detection algorithm verified on various platforms, including a real quadruped robot. The proposed approach detects dangerous situations, such as proximity to stairs, in real time, enabling the robot to move safely. In our research, we utilized data collected by a moving four-legged robot, recorded in 18 sequences containing more than 26,000 color images from two cameras positioned at different perspectives. To address the challenge, we utilize a deep neural network with RGB inputs for object detection, complemented by preprocessing, and post-processing. A key feature of this approach is its adaptability to varying camera views, including both front and bottom perspectives on the robot, with training that incorporates multi-camera images from both views. We implemented and tested this algorithm on the Unitree Go1 robot, as well as on other embedded platforms. Using the trained YOLO version 11n network on a single sequence and testing on 17 sequences, we achieved an average mAP@50 of 51.30 for images containing only stairs and 87.56 for all images. This method enables early hazard detection during stair navigation. The proposed evaluation scenario tests the model’s adaptation from a single training sequence to multiple unseen sequences, extending existing stair detection methods for quadrupedal robots. The dataset presents high variability in stair appearance due to the robot’s perspective and limited real-time processing capacity.