Parking Slot Detection Github
Abstract: While real-time parking slot detection plays a critical role in valet parkingsystems, existing methods have limited success in real-world applications. Weargue two reasons accounting for the unsatisfactory performance:romannumeral1, The available datasets have limited diversity, which causes thelow generalization ability. romannumeral2, Expert knowledge for parking slotdetection is under-estimated. Thus, we annotate a large-scale benchmark fortraining the network and release it for the benefit of community. Driven by theobservation of various parking lots in our benchmark, we propose the circulardescriptor to regress the coordinates of parking slot vertexes and accordinglylocalize slots accurately. To further boost the performance, we develop atwo-stage deep architecture to localize vertexes in the coarse-to-fine manner.In our benchmark and other datasets, it achieves the state-of-the-art accuracywhile being real-time in practice. Benchmark is available at:this https URL
Submission history
From: Weiwei Sun [view email]Parking Slot Detection Github Extension
[v1]Tue, 12 May 2020 03:06:25 UTC (1,524 KB)
Assuming a parking lot with 6 slots, the following commands should be run in sequence by typing them in at a prompt and should produce output as described below the command: Input: createparkinglot 6. Output: Created a parking lot with 6 slots. Input: park KA-01-HH-1234 White. Output: Allocated slot number: 1. Input: park KA-01-HH-9999 White. The parking-slot detection module takes the surround-view image as the input, detects the parking-slots, and finally sends their physical positions with respect to the vehicle-centered coordinate system to the decision module for further process. Representative work on vision-based parking-slot detection will be reviewed as follows. Automatic Car Parking Indicator System using micro controller -svsembedded, svskits, 1. Automatic Car Parking System - Assam Don Bos.
Firstly, to facilitate the study of vision-based parking-slot detection, a large-scale parking-slot image database is established. For each image in this database, the marking-points and parking-slots are carefully labeled. Such a database can serve as a benchmark to design and validate parking-slot detection algorithms.
Full-text links:
Download:
Current browse context: References & Citations
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs and how to get involved.
Parking Slot Detection Github Software
Parking Slot Detection Github Machine Learning
