Marin Kačan

Mr. Marin Kačan

Faculty of Electrical Engineering and Computing, Zagreb, Zagreb, Grad, Croatia
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
10 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MKMarin Kačan
Marin Kačan
FTFilip Turčinović
Filip Turčinović
DBDario Bojanjac
Dario Bojanjac
MBMarko Bosiljevac
Marko Bosiljevac
The availability of low-cost microwave components today enables the development of various high-frequency sensors and radars, including Ground-based Synthetic Aperture Radar (GBSAR) systems. Similar to optical images, radar images generated by applying a reconstruction algorithm on raw GBSAR data can also be used in object classification. The reconstruction algorithm provides an interpretable representation of the observed scene, but may also negatively influence the integrity of obtained raw data due to applied approximations. In order to quantify this effect, we compare the results of a conventional computer vision architecture, ResNet18, trained on reconstructed images versus one trained on raw data. In this process, we focus on the task of multi-label classification and describe the crucial architectural modifications that are necessary to process raw data successfully. The experiments are performed on a novel multi-object dataset RealSAR obtained using a newly developed 24 GHz (GBSAR) system where the radar images in the dataset are reconstructed using the Omega-k algorithm applied to raw data. Experimental results show that the model trained on raw data consistently outperforms the image-based model. We provide a thorough analysis of both approaches across hyperparameters related to model pretraining and the size of the training dataset. This, in conclusion, shows how processing raw data provides overall better classification accuracy, it is inherently faster since there is no need for image reconstruction and it is therefore useful tool in industrial GBSAR applications where processing speed is critical.

20 September 2020
Verified
Conference Paper
Closed access
MKMarin Kačan
Marin Kačan
MOMarin Orsic
Marin Orsic
SSSinisa Segvic
Sinisa Segvic
MŠMarko Ševrović
Marko Ševrović
We address the automatic recognition of road safety attributes according to the iRAP methodology. We formulate the problem as a separate multi-class classification of each iRAP attribute in georeferenced video clips that correspond to particular road segments. We propose a solution based on an efficient multi-task model with shared features, which can recognize all attributes with a single forward pass and learn in an end-to-end fashion. We perform experiments on a novel real dataset acquired along 1850 km of public roads in Bosnia and Herzegovina, in which all iRAP attributes have been annotated by human experts. We express recognition accuracy as per-attribute macro-F1 scores due to a significant class imbalance present within most attributes. We thoroughly validate different variants of our model, analyze the contributions of several hyper-parameters, and report recognition accuracy on the independent test set.

17 September 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
MKMarin Kačan
Marin Kačan
MŠMarko Ševrović
Marko Ševrović
SŠSiniša Šegvić
Siniša Šegvić
Road-safety inspection is an indispensable instrument for reducing road-accident fatalities related to road infrastructure. Recent work formalizes the assessment procedure in terms of carefully selected risk factors that are also known as road-safety attributes. In current practice, these attributes are manually annotated in geo-referenced monocular video for each road segment. We propose to reduce dependency on tedious human labor by automating attribute collection through a two-stage deep learning approach. The first stage recognizes more than forty road-safety attributes by observing a local spatio-temporal context. Our design leverages an efficient convolutional pipeline, which benefits from pre-training on semantic segmentation of street scenes. The second stage enhances predictions through sequential integration across a larger temporal window. Our design leverages per-attribute instances of a lightweight recurrent architecture. Both stages alleviate extreme class imbalance by incorporating a multi-task variant of recall-based dynamic loss weighting. We perform experiments on the novel iRAP-BH dataset, which involves fully labeled geo-referenced video along 2,300 km of public roads in Bosnia and Herzegovina. Moreover, we evaluate our approach against the related work on three road-scene classification datasets from the literature: Honda Scenes, FM3m, and BDD100k. Experimental evaluation confirms the value of our contributions on all three datasets.

5 April 2024 in Sensors
Verified
Journal Article
Open access
PDF file
FTFilip Turčinović
Filip Turčinović
MKMarin Kačan
Marin Kačan
DBDario Bojanjac
Dario Bojanjac
MBMarko Bosiljevac
Marko Bosiljevac
Zvonimir SipusZvonimir Sipus
Zvonimir Sipus
In recent years, the development of intelligent sensor systems has experienced remarkable growth, particularly in the domain of microwave and millimeter wave sensing, thanks to the increased availability of affordable hardware components. With the development of smart Ground-Based Synthetic Aperture Radar (GBSAR) system called GBSAR-Pi, we previously explored object classification applications based on raw radar data. Building upon this foundation, in this study, we analyze the potential of utilizing polarization information to improve the performance of deep learning models based on raw GBSAR data. The data are obtained with a GBSAR operating at 24 GHz with both vertical (VV) and horizontal (HH) polarization, resulting in two matrices (VV and HH) per observed scene. We present several approaches demonstrating the integration of such data into classification models based on a modified ResNet18 architecture. We also introduce a novel Siamese architecture tailored to accommodate the dual input radar data. The results indicate that a simple concatenation method is the most promising approach and underscore the importance of considering antenna polarization and merging strategies in deep learning applications based on radar data.