no code implementations • 25 Apr 2024 • Jer Pelhan, Alan Lukežič, Vitjan Zavrtanik, Matej Kristan
DAVE outperforms the top density-based counters by ~20% in the total count MAE, it outperforms the most recent detection-based counter by ~20% in detection quality and sets a new state-of-the-art in zero-shot as well as text-prompt-based counting.
no code implementations • 8 Jan 2024 • Alan Lukezic, Ziga Trojer, Jiri Matas, Matej Kristan
DiTra sets a new state-of-the-art in transparent object tracking and generalizes well to opaque objects.
no code implementations • 23 Nov 2023 • Benjamin Kiefer, Lojze Žust, Matej Kristan, Janez Perš, Matija Teršek, Arnold Wiliem, Martin Messmer, Cheng-Yen Yang, Hsiang-Wei Huang, Zhongyu Jiang, Heng-Cheng Kuo, Jie Mei, Jenq-Neng Hwang, Daniel Stadler, Lars Sommer, Kaer Huang, Aiguo Zheng, Weitu Chong, Kanokphan Lertniphonphan, Jun Xie, Feng Chen, Jian Li, Zhepeng Wang, Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Tuan-Anh Vu, Hai Nguyen-Truong, Tan-Sang Ha, Quan-Dung Pham, Sai-Kit Yeung, Yuan Feng, Nguyen Thanh Thien, Lixin Tian, Sheng-Yao Kuan, Yuan-Hao Ho, Angel Bueno Rodriguez, Borja Carrillo-Perez, Alexander Klein, Antje Alex, Yannik Steiniger, Felix Sattler, Edgardo Solano-Carrillo, Matej Fabijanić, Magdalena Šumunec, Nadir Kapetanović, Andreas Michel, Wolfgang Gross, Martin Weinmann
The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV).
Ranked #1 on Semantic Segmentation on LaRS
1 code implementation • 2 Nov 2023 • Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj
(ii) We tackle the lack of diverse industrial depth datasets by introducing a simulation process for learning informative depth features in the depth encoder.
Depth Anomaly Detection and Segmentation RGB+3D Anomaly Detection and Segmentation
2 code implementations • ICCV 2023 • Lojze Žust, Janez Perš, Matej Kristan
The progress in maritime obstacle detection is hindered by the lack of a diverse dataset that adequately captures the complexity of general maritime environments.
Ranked #1 on Panoptic Segmentation on LaRS
1 code implementation • 21 Apr 2023 • Matija Teršek, Lojze Žust, Matej Kristan
Tests on a real embedded device OAK-D show that, while WaSR cannot run due to memory restrictions, eWaSR runs comfortably at 5. 5 FPS.
no code implementations • 24 Nov 2022 • Benjamin Kiefer, Matej Kristan, Janez Perš, Lojze Žust, Fabio Poiesi, Fabio Augusto de Alcantara Andrade, Alexandre Bernardino, Matthew Dawkins, Jenni Raitoharju, Yitong Quan, Adem Atmaca, Timon Höfer, Qiming Zhang, Yufei Xu, Jing Zhang, DaCheng Tao, Lars Sommer, Raphael Spraul, Hangyue Zhao, Hongpu Zhang, Yanyun Zhao, Jan Lukas Augustin, Eui-ik Jeon, Impyeong Lee, Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Sagar Verma, Siddharth Gupta, Shishir Muralidhara, Niharika Hegde, Daitao Xing, Nikolaos Evangeliou, Anthony Tzes, Vojtěch Bartl, Jakub Špaňhel, Adam Herout, Neelanjan Bhowmik, Toby P. Breckon, Shivanand Kundargi, Tejas Anvekar, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudengudi, Arpita Vats, Yang song, Delong Liu, Yonglin Li, Shuman Li, Chenhao Tan, Long Lan, Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi, Hsiang-Wei Huang, Cheng-Yen Yang, Jenq-Neng Hwang, Pyong-Kun Kim, Kwangju Kim, Kyoungoh Lee, Shuai Jiang, Haiwen Li, Zheng Ziqiang, Tuan-Anh Vu, Hai Nguyen-Truong, Sai-Kit Yeung, Zhuang Jia, Sophia Yang, Chih-Chung Hsu, Xiu-Yu Hou, Yu-An Jhang, Simon Yang, Mau-Tsuen Yang
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.
1 code implementation • ICCV 2023 • Nikola Djukic, Alan Lukezic, Vitjan Zavrtanik, Matej Kristan
The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts.
Ranked #1 on Object Counting on FSC147
1 code implementation • 7 Oct 2022 • Alan Lukezic, Ziga Trojer, Jiri Matas, Matej Kristan
Visual object tracking has focused predominantly on opaque objects, while transparent object tracking received very little attention.
1 code implementation • 2 Aug 2022 • Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj
The state-of-the-art in discriminative unsupervised surface anomaly detection relies on external datasets for synthesizing anomaly-augmented training images.
Ranked #1 on Supervised Defect Detection on KolektorSDD2
Supervised Defect Detection Unsupervised Anomaly Detection +1
1 code implementation • 27 Jun 2022 • Lojze Žust, Matej Kristan
Robust maritime obstacle detection is critical for safe navigation of autonomous boats and timely collision avoidance.
1 code implementation • 10 Mar 2022 • Lojze Žust, Matej Kristan
Robust maritime obstacle detection is essential for fully autonomous unmanned surface vehicles (USVs).
no code implementations • 22 Dec 2021 • Alan Lukežič, Jiří Matas, Matej Kristan
D3S2 outperforms the leading segmentation tracker SiamMask on video object segmentation benchmarks and performs on par with top video object segmentation algorithms.
3 code implementations • 17 Aug 2021 • Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj
Visual surface anomaly detection aims to detect local image regions that significantly deviate from normal appearance.
Ranked #15 on Anomaly Detection on VisA
2 code implementations • 1 Aug 2021 • Lojze Žust, Matej Kristan
Per-pixel ground truth labeling of such datasets, however, is labor-intensive and expensive.
2 code implementations • 5 May 2021 • Borja Bovcon, Jon Muhovič, Duško Vranac, Dean Mozetič, Janez Perš, Matej Kristan
We propose a new obstacle segmentation performance evaluation protocol that reflects the detection accuracy in a way meaningful for practical USV navigation.
2 code implementations • ICCV 2021 • Vitjan Zavrtanik, Matej Kristan, Danijel Skocaj
Visual surface anomaly detection aims to detect local image regions that significantly deviate from normal appearance.
Ranked #4 on Anomaly Detection on AeBAD-V
2 code implementations • 17 Oct 2020 • Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj
Visual anomaly detection addresses the problem of classification or localization of regions in an image that deviate from their normal appearance.
Ranked #6 on Anomaly Detection on AeBAD-V
3 code implementations • 7 Jan 2020 • Borja Bovcon, Matej Kristan
Obstacle detection by semantic segmentation shows a great promise for autonomous navigation in unmanned surface vehicles (USV).
no code implementations • 2 Dec 2019 • Yanlin Qian, Alan Lukežič, Matej Kristan, Joni-Kristian Kämäräinen, Jiri Matas
In this work, we propose a deep depth-aware long-term tracker that achieves state-of-the-art RGBD tracking performance and is fast to run.
1 code implementation • 20 Nov 2019 • Alan Lukežič, Jiří Matas, Matej Kristan
D3S outperforms the leading segmentation tracker SiamMask on video object segmentation benchmark and performs on par with top video object segmentation algorithms, while running an order of magnitude faster, close to real-time.
no code implementations • 1 Jul 2019 • Alan Lukežič, Ugur Kart, Jani Käpylä, Ahmed Durmush, Joni-Kristian Kämäräinen, Jiří Matas, Matej Kristan
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed.
no code implementations • 19 Jun 2019 • Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed.
3 code implementations • 20 Feb 2019 • Domen Tabernik, Matej Kristan, Aleš Leonardis
Convolutional neural networks excel in a number of computer vision tasks.
no code implementations • CVPR 2019 • Ugur Kart, Alan Lukezic, Matej Kristan, Joni-Kristian Kamarainen, Jiri Matas
Standard RGB-D trackers treat the target as an inherently 2D structure, which makes modelling appearance changes related even to simple out-of-plane rotation highly challenging.
no code implementations • 19 Apr 2018 • Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan
We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances.
no code implementations • 22 Feb 2018 • Borja Bovcon, Rok Mandeljc, Janez Perš, Matej Kristan
The IMU readings are used to estimate the location of horizon line in the image, which automatically adjusts the priors in the probabilistic semantic segmentation model.
2 code implementations • CVPR 2018 • Domen Tabernik, Matej Kristan, Aleš Leonardis
Classical deep convolutional networks increase receptive field size by either gradual resolution reduction or application of hand-crafted dilated convolutions to prevent increase in the number of parameters.
no code implementations • 27 Nov 2017 • Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř, Jiří Matas, Matej Kristan
We propose FuCoLoT -- a Fully Correlational Long-term Tracker.
no code implementations • ICCV 2017 • Luka Čehovin Zajc, Alan Lukežič, Aleš Leonardis, Matej Kristan
Object-to-camera motion produces a variety of apparent motion patterns that significantly affect performance of short-term visual trackers.
4 code implementations • CVPR 2017 • Alan Lukežič, Tomáš Vojíř, Luka Čehovin, Jiří Matas, Matej Kristan
Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance.
Ranked #14 on Visual Object Tracking on VOT2017/18 (using extra training data)
no code implementations • 13 Sep 2016 • Domen Tabernik, Matej Kristan, Jeremy L. Wyatt, Aleš Leonardis
We propose a novel analytic model of a basic unit in a layered hierarchical model with both explicit compositional structure and a well-defined discriminative cost function.
no code implementations • 12 May 2016 • Alan Lukežič, Luka Čehovin, Matej Kristan
Deformable parts models show a great potential in tracking by principally addressing non-rigid object deformations and self occlusions, but according to recent benchmarks, they often lag behind the holistic approaches.
no code implementations • 8 Mar 2016 • Aleksandar Dimitriev, Matej Kristan
We propose a novel unsupervised image segmentation algorithm, which aims to segment an image into several coherent parts.
no code implementations • 6 Mar 2015 • Matej Kristan, Vildana Sulic, Stanislav Kovacic, Janez Pers
The algorithm is tested on a new, challenging, dataset for segmentation and obstacle detection in marine environments, which is the largest annotated dataset of its kind.
no code implementations • 4 Mar 2015 • Matej Kristan, Jiri Matas, Ales Leonardis, Tomas Vojir, Roman Pflugfelder, Gustavo Fernandez, Georg Nebehay, Fatih Porikli, Luka Cehovin
This paper addresses the problem of single-target tracker performance evaluation.
no code implementations • 20 Feb 2015 • Luka Čehovin, Aleš Leonardis, Matej Kristan
The problem of visual tracking evaluation is sporting a large variety of performance measures, and largely suffers from lack of consensus about which measures should be used in experiments.