Competition Paper "ICPR 2024 Competition on VISual Tracking in Adverse Conditions (VISTAC)" has been published. Please cite our article when you are using the NV-SID dataset. 

@inproceedings{ali2024icpr, title={ICPR 2024 Competition on VISual Tracking in Adverse Conditions (VISTAC)},author={Ali, Asfak and Pandit, Arya and Mandal, Shirshendu and Bhattacharjee, Srinjan and Maiti, Sauptik and Acharjee, Suvojit and Sarkar, Ram and Chaudhuri, Sheli Sinha and Agaian, Sos S and Djemal, Khalifa},booktitle={International Conference on Pattern Recognition}, pages={91--102},year={2024}, organization={Springer}}

ANNOUNCEMENT TO ALL PARTICIPANTS

Dataset Access Link: Click here 

Results Declared! - Congratulations to all Winners!

Competition Outline

Over the years, object tracking has predominantly been conducted on videos captured in natural or well-lit environments. This focus has led to significant advancements in tracking algorithms, enhancing their robustness across various challenging scenarios. However, the low-light and nighttime object tracking still needs to be explored. Furthermore, while infrared (IR) imaging offers promising advantages for object tracking—due to its lower sensitivity to lighting conditions and appearance variability—its potential is not yet fully harnessed. Research on object tracking using IR videos is significantly less developed than visible spectrum imaging. 

Historically, only a handful of studies have effectively combined spatiotemporal information extracted from IR videos for object tracking. Recognizing the need to fill this gap, our project aims to leverage IR video for object tracking, making this dataset a foundational step towards developing specialized algorithms for single-object tracking in nighttime environments aided by infrared video data.

The NV-SID contains 100 videos, from which we will publish 80 videos with ground truth for training and validation on May 5th, 2024. The rest of the 20 videos will be published without any ground truth on May 25th, 2024. 

The ground truths are in (X1, Y1, W, H, IQA) format, where (X1, Y1) are the top-left coordinates of the bounding box of the object, (W,H) are the width and height of the bounding box respectively. IQA represents the visual quality of the frame given by a pure fraction, where a numerically higher value denotes higher image distortion. The IQA value is provided as an extra tool, which the participants may utilize to design their tracking models and/or enhance the tracking performance, to their own liberty.

Participants in the competition are required to submit the tracking results in form of a .json file named "team_name.json". The file should contain tracking results in form of a nested list = [[X1,Y1, W1, H1],[X2, Y2, W2, H2],....], where 1,2,3,...represent the frame number for a video sequence. Hence, the "team_name.json" file content shall be as follows:

{ “<sequence-1>”: [[X1,Y1,W1,H1],[X2,Y2,W2,H2],....] , “<sequence-2>”: [[X1,Y1,W1,H1],[X2,Y2,W2,H2],....], ...... ,“<sequence-n>”: [[X1,Y1,W1,H1],[X2,Y2,W2,H2],....] }

For examples, refer to the dataset link and view the "train.json" and "validation.json" files.

More than one submission from a team will result in the organizers taking the last submission as the final one.

The winner will be determined based on the team achieving the highest Qualitative Precision (QP) performance on the test sequences.  

• Each team is required to provide two deliverables: 

a) Tracking results for the test videos. 

b) A concise one-page report outlining the methodology employed in the tracking algorithm.

**Please note that the proposed machine learning model needs to be trained solely on the training dataset of the NV-SID, fine-tuning of the pre-trained machine learning models are not permitted. 

 Competition Objectives

This competition is designed to achieve several key goals: 

1. Introduce the Night Vision Spatiotemporal Infrared-Video Dataset (NV-SID): This newly developed dataset consists of 100 nighttime infrared videos, each accompanied by detailed ground truth data. The NV-SID dataset is designed to highlight spatiotemporal characteristics, capturing intricate motion patterns and providing valuable temporal information across frames. The introduction of this dataset aims to advance the field of object tracking under challenging nighttime conditions. 

2. Foster Collaboration and Knowledge Exchange: This competition provides a dedicated platform for researchers and practitioners to engage in a lively discussion about the challenges, innovative methodologies, and best practices in adverse condition object tracking. This collaborative environment is intended to spur the development of new ideas and approaches in the community. 

3. Establish a Benchmark for Object Tracking Algorithms: A critical objective of this competition is to set a benchmark for evaluating and comparing the effectiveness of machine learning-based object-tracking algorithms. To facilitate this, we introduce the Qualitative Precision (QP) metric, specifically tailored to assess the accuracy of tracking algorithms in diverse and challenging nighttime scenarios. Through these objectives, the competition seeks to catalyze significant advancements in the technology and methodology of object tracking, particularly in low-light and IR imaging contexts, thereby contributing to the broader field of computer vision. 

Please consider citing our article if you use NV-SID for your research!

@inproceedings{ali2024icpr, title={ICPR 2024 Competition on VISual Tracking in Adverse Conditions (VISTAC)},author={Ali, Asfak and Pandit, Arya and Mandal, Shirshendu and Bhattacharjee, Srinjan and Maiti, Sauptik and Acharjee, Suvojit and Sarkar, Ram and Chaudhuri, Sheli Sinha and Agaian, Sos S and Djemal, Khalifa},booktitle={International Conference on Pattern Recognition}, pages={91--102},year={2024}, organization={Springer}}

For queries and suggestions, contact us at: nvisot.ju.etce@gmail.com