Paper Reading AI Learner

Public Parking Spot Detection And Geo-localization Using Transfer Learning

2022-09-01 04:09:51
Moseli Mots'oehli, Yao Chao Yang

Abstract

In cities around the world, locating public parking lots with vacant parking spots is a major problem, costing commuters time and adding to traffic congestion. This work illustrates how a dataset of Geo-tagged images from a mobile phone camera, can be used in navigating to the most convenient public parking lot in Johannesburg with an available parking space, detected by a neural network powered-public camera. The images are used to fine-tune a Detectron2 model pre-trained on the ImageNet dataset to demonstrate detection and segmentation of vacant parking spots, we then add the parking lot's corresponding longitude and latitude coordinates to recommend the most convenient parking lot to the driver based on the Haversine distance and number of available parking spots. Using the VGG Image Annotation (VIA) we use 76 images from an expanding dataset of images, and annotate these with polygon outlines of the four different types of objects of interest: cars, open parking spots, people, and car number plates. We use the segmentation model to ensure number plates can be occluded in production for car registration anonymity purposes. We get an 89% and 82% intersection over union cover score on cars and parking spaces respectively. This work has the potential to help reduce the amount of time commuters spend searching for free public parking, hence easing traffic congestion in and around shopping complexes and other public places, and maximize people's utility with respect to driving on public roads.

Abstract (translated)

URL

https://arxiv.org/abs/2209.00213

PDF

https://arxiv.org/pdf/2209.00213.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot