2020 · 33 citations · 15 references
ComputingAutomotive EngineeringComputer ScienceComputer VisionMachine LearningTransportationDeep LearningInstance SegmentationObject RecognitionPattern RecognitionRepresentation LearningDeep Learning DetectionReal-time ProcessingRobustnessTraffic Congestion
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%.
15
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
Learning to predict by the methods of temporal differences
Richard S. Sutton · Machine Learning · 1988 · 2.8K citations · Full text
Multiscale Combinatorial Grouping
Pablo Arbeláez, Jordi Pont-Tuset, Jon Barron et al. · 2014 · 1.2K citations · Full text