Infrared Tracking Challenge Tracking multiple objects in low-light conditions. The challenge is no longer active and concluded on June 15, 2023.
Congratulations to the winners and participants for their efforts in shaping the future of mobility and infrared tracking technology.
About the

New generation autonomous vehicles are expected to successfully navigate in environments with challenging lighting conditions. This is where common, photometric visual perception-based tracking algorithms are put to their limits. We are now exploring the use of radiometric sensors, providing infrared frames (instead of photometric, RGB ones) for object tracking in low-light conditions. The challenge put forward by the Technology Innovation Institute's Autonomous Robotics Research Center is to develop approaches that can effectively track objects in the dark, in both structured and unstructured environments, including pedestrians, buggies, cars, and motorcyclists, among others.

The Infrared Tracking Challenge is open to innovators, start-ups, research institutes, and university students from anywhere in the world. Challengers are encouraged to leverage public datasets with similar content as TII's sample dataset and utilize color-to-thermal domain adaptation techniques in light of scarce publicly available annotated thermal video sequences. Submissions will be evaluated based on criteria set by TII, based on common tracking metrics in the RGB domain.

Three winners will be awarded prizes totaling US $75,000 by May 17, 2023. 1st place: $40,000 2nd place: $20,000 3rd place: $15,000
Important Dates *Evaluation period includes scoring/ranking, soliciting write-ups and Q&A from top solvers,
and final winner approvals for announcement
DECEMBER 19, 2022 Challenge launch and Pre-registration FEBRUARY 3, 2023 Release of data and full judging criteria APRIL 5, 2023 (8 WEEKS) Submission deadline April 5, 2023 - June 12, 2023 Evaluation period June 15, 2023 Winners announced
DECEMBER 19, 2022 Challenge launch andPre-registration FEBRUARY 3, 2023 Release of data andfull judging criteria APRIL 5, 2023 (8 WEEKS) Submission deadline APRIL 5, 2023 - MAY 17, 2023 (6 WEEKS) Evaluation period* MAY 17, 2023 Winners announced

HeroX exists to enable anyone, anywhere in the world, to create a challenge that addresses any problem or opportunity, build a community around that challenge, and activate the circumstances that can lead to breakthrough innovation.


Anyone is eligible to apply as long as their project submission meets the challenge guidelines.

While the challenge is open, there will not be direct mentorship available, but TII is considering nonmonetary prizes/incentives as part of the challenge, like internships, so stay tuned.

Prize competitions are different than traditional grants and contracts, and while funding is not provided throughout the challenge, prizes will be provided at the end to those who prove they can provide the best algorithm that meets the challenge requirements. The total prize purse available for this challenge is $75,000.

The candidate will be provided with an annotated sample set in order to understand the problem. Candidates are encouraged to use state-of-the-art domain adaptation techniques.

No extra data will be provided by TII. The participants can split a portion of the provided dataset for validation purpose. Competitors may also use open source datasets.

The following is required for the submission format:
  • Dockerized application of the challengers algorithm with clear installation instructions on an Ubuntu platform. 
  • The submission must accept a link to a ROS bagfile as input and output a .json file containing the predictions.
  • Topics in the bagfile are same as the ones shared for training. Predictions are expected to be in same format as ground truth annotations.
  • Each prediction must contain the following information: image frame number, 2D bounding box coordinates and ID of the instance.

The standalone application can be run on an NVIDIA Jetson AGX Xavier board or similar on at least 15 FPS.

Yes, teams containing multiple members can enter the challenge.

No, classical computer vision approaches or a combination of both classical and AI based are welcome.
Contact Us
Conrad Abu Dhabi Etihad Towers
place Conrad Abu Dhabi Etihad Towers

Check all the

Explore next