ready to beat the machine?

  Play
  • 100 individuals have attempted the challenge
  • 10% have beat the machine
  • Earn glory and fame

About Us

Place recognition is a well defined but extremely challenging problem to solve in the general sense; given sensory information about a place such as a photo, can a human, animal, robot or personal navigation aid decide whether that place is the same as any places it has previously visited or learnt, despite the vast range of ways in which the appearance of that place can change.

Current approaches to the problem using GPS, cameras or lasers have one or more significant theoretical, technological or application-based limitations including high cost, sensitivity to changing environmental conditions, lack of generality, training requirements and long recognition latencies.

Place Recognition

This website is intended to act as a complete resource for all aspects of the Place Recognition problem, including:

What is place recognition?

Developing a clear and concise definition of the place recognition problem.

Why place recognition?

Why focus on place recognition and not just object recognition, face recognition or SLAM?

How is place recognition performed in nature?

State of the art research on how animals and humans perform place recognition.

Algorithmic approaches to place recognition

Including state of the art research from fields like robotics and computer vision.

Benchmarking and Datasets

A categorized set of benchmark datasets that isolate various aspects of the place recognition problem including types of environmental change and pose invariance.

Gamification

Applying game mechanics and game design techniques to motivate people to participate in the Place Recognition simulation.

Some Fun Facts

Completed Games

Average Human Score

Average Machine Score

People who have beaten the Machine

A collaboration between Universities

Queensland University of Technology

University of Queensland

Harvard University