Automated Vehicle Parking Slot Detection System Using Deep Learning

Traffic congestion at the parking slots is a major problem that the modern society is facing nowadays, as the vehicle numbers are increasing at a rapid pace without the increment of the parking slots. The research done here helps solve the traffic congestion problem at the bottleneck of the networks mainly at the parking slots, by Instance Segmentation algorithms and Deep Learning. The model gets all the initial available parking slots that are available in the given area and real time processing is done on the obtained data to find whether the slots are empty or occupied with any vehicle and gives the information of empty slots. Apart from locating a free parking space for a car, the model also finds out appropriate parking space for two wheelers (less space occupant vehicles). The proposed system shows improved robustness achieving a mask rate of recognition greater than 92.33% and a boundary recognition rate of 98.4%.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jonathan T. Barron,et al.  Multiscale Combinatorial Grouping , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Qi Wu,et al.  Robust Parking Space Detection Considering Inter-Space Correlation , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[4]  Luiz Eduardo Soares de Oliveira,et al.  PKLot - A robust dataset for parking lot classification , 2015, Expert Syst. Appl..

[5]  Peter Stone,et al.  Value Functions for RL-Based Behavior Transfer: A Comparative Study , 2005, AAAI.

[6]  Vijayakumar T Dr,et al.  COMPARATIVE STUDY OF CAPSULE NEURAL NETWORK IN VARIOUS APPLICATIONS , 2019, Journal of Artificial Intelligence and Capsule Networks.

[7]  Qi Wu.  Parking Lots Space Detection , 2006 .

[8]  Meng-Hsun Tsai,et al.  Utilization-based parking space suggestion in smart city , 2018, 2018 15th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[9]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[11]  Carlo Meghini,et al.  Deep learning for decentralized parking lot occupancy detection , 2017, Expert Syst. Appl..

[12]  Claudio Gennaro,et al.  Car parking occupancy detection using smart camera networks and Deep Learning , 2016, 2016 IEEE Symposium on Computers and Communication (ISCC).

[13]  Abul Bashar,et al.  SURVEY ON EVOLVING DEEP LEARNING NEURAL NETWORK ARCHITECTURES , 2019, December 2019.

[14]  Volker Gruhn,et al.  Recommended architecture for car parking management system based on cyber-physical system , 2017, 2017 International Conference on Engineering & MIS (ICEMIS).

[15]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Liu Sen,et al.  Research on Vehicle Appearance Component Recognition Based on Mask R-CNN , 2019 .

[17]  Manfred Huber,et al.  Effective Control Knowledge Transfer through Learning Skill and Representation Hierarchies , 2007, IJCAI.

[18]  Jitendra Malik,et al.  Poselets: Body part detectors trained using 3D human pose annotations , 2009, 2009 IEEE 12th International Conference on Computer Vision.