This video tutorial shows you how you can use Deep Netts to create visual parking lot occupancy detection using deep learning.
The data set contains labeled images of vacant and occupied parking spaces, extracted from the camera under different light conditions.
Occupancy detection is performed with a convolutional neural network in pure Java created with Deep Netts, with accuracy around 99%. This example implements the work from the research paper https://www.sciencedirect.com/science/article/pii/S095741741630598X but with a much smaller and computationally less demanding network with the same accuracy. This kind of network can be used with cameras to create distributed systems smart cameras for parking monitoring.
The clear advantages of decentralization are the reduction of the communication overhead and the elimination of computing bottleneck. As a consequence, the system scales better when the number of monitored parking spaces increases .
- Data set: http://cnrpark.it
- How to do it in Java code using Deep Netts Community Edition
 Original paper: Deep learning for decentralized parking lot occupancy detection