Parquery: Camera-Based Smart Parking With the Power of Artificial Intelligence

Detect any kind of vehicle in any parking situation and weather condition

How does Parquery’s smart parking solution work for any parking situation - whether on- or off-street or even indoors - and any vehicle? Why does it not buckle even in difficult weather and lighting conditions and in the face of heavy clutter, occlusions, or snow cover? Take a glance behind the scenes of Parquery’s powerful Artificial Intelligence (AI) algorithms that analyze still camera images of a parking area to determine if a parking spot is occupied and for how long.

Parquery’s smart parking solution uses cameras and Artificial Intelligence (AI) to monitor parking lots. The intelligent algorithms run either in the cloud or locally on the parking premises and detect vehicles in the camera images and determine whether individual parking spots are occupied.

Learn and adapt

The power of Parquery’s solution lies in its advanced Deep Neural Network algorithms - a far cry from simple background subtraction of classic camera-based solutions. These are machine learning algorithms that allow the system to adapt to any environment by training or experience - that means it learns from its mistakes - just like us.

Starting with a generic model generated from various parking situations, this model is refined as time passes. Hence, it becomes increasingly optimized for the characteristics of a specific parking lot through training on new data. Thus, it gains experience and increases the probability of a correct outcome next time.

Beyond the evident differences between parking lots - such as layout, arrangement of the spots, obstructions, or whether indoors or outdoors - other characteristics include lighting and weather conditions, the types of vehicles encountered, or visual distortions due to camera optics.

Parquery at night, in heavy rain with glare, reflections, and occlusions

From good to great

Typically, the out-of-the-box accuracy of Parquery’s learning solution is about 95% before adapting to the specific parking lot. The 5% error concerns undetected vehicles and empty parking bays erroneously interpreted as occupied.

Parquery then collects the learning material for the AI algorithms, and by the end of the first month, Parquery delivers 99% accuracy thanks to training and adapting the algorithms to the requirements of the parking situation at hand.

Find out more about how Parquery deals with the reality of a physical world that does not conform to rigid norms, occlusions and imperfections, clutter, noise and background patterns.

About Parquery AG Parquery

Parquery AG a leading Swiss technology and camera-based smart parking provider in the field of Computer Vision and Deep Learning.

Contact us at for more information regarding Smart Parking and AI-solutions beyond parking.


There are no comments yet for this item

Join the discussion

You can only add a comment when you are logged in. Click here to login