{"id":20687171,"url":"https://github.com/brandtkilian/mse-skyviewfactor","last_synced_at":"2025-06-30T11:06:08.008Z","repository":{"id":88292185,"uuid":"84206713","full_name":"brandtkilian/MSE-SkyViewFactor","owner":"brandtkilian","description":"Personnal project in image processing/DeepLearning that consists in segmenting sky in images to compute a SkyView Factor","archived":false,"fork":false,"pushed_at":"2018-10-02T19:07:06.000Z","size":99090,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-08T21:13:47.908Z","etag":null,"topics":["deep-learning","factor","image-processing","segmentation","sky"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brandtkilian.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2017-03-07T14:11:34.000Z","updated_at":"2024-08-10T14:59:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"35b7fb4b-d8f5-4de4-a583-8b6ab8a92485","html_url":"https://github.com/brandtkilian/MSE-SkyViewFactor","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/brandtkilian/MSE-SkyViewFactor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandtkilian%2FMSE-SkyViewFactor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandtkilian%2FMSE-SkyViewFactor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandtkilian%2FMSE-SkyViewFactor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandtkilian%2FMSE-SkyViewFactor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brandtkilian","download_url":"https://codeload.github.com/brandtkilian/MSE-SkyViewFactor/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brandtkilian%2FMSE-SkyViewFactor/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262762468,"owners_count":23360330,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","factor","image-processing","segmentation","sky"],"created_at":"2024-11-16T22:56:19.293Z","updated_at":"2025-06-30T11:06:07.965Z","avatar_url":"https://github.com/brandtkilian.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MSE-SkyViewFactor\n\nThis was one of my Master's Degree project, inidividual project of about 100hours of work. The dataset was created by myself and can't be shared due to images rights. The details and results can't be shared as well.\n\nThe project consists of computing the Skyviewfactor (SVF) from hemispheric images (taken by an embeded camera in a backpack while walking) using image processing technics and a CNN SegNet as segmentation tools.\n\nThis project is part of a big project called CityFeels developed by the Hepia in Geneva and directed by the team of Peter\nGallinelli and Reto Componovo that target the goal of increase the understanding of the factors\nthat influence the well-being of people in urban environments\n\n## Image Processing\n\nI've used multiple technics\n\n1. Segment using color: with thresholds, in HSV and RGB\n2. Watershed: with initial markers chosed using color, Otsu tresholding or texture analysis (variance)\n\n## SegNet\n\nThe Segnet architecture used in this project is inspired by the work of [pradyu1993](https://github.com/pradyu1993/segnet) that made a Keras implementation of the SegNet proposed in a paper from the Cambridge University that you can find [there](http://arxiv.org/pdf/1511.00561v2.pdf).\n\nMy final trained model recognize 3 classes (4 if we take into account the \"void\" class that are black pixels due to the fisheye) with an accuracy of about 95%:\n* Buildings\n* Sky\n* Vegetation\n\nSince the dataset has been handmade for this project, I used some Data Augmentation technics.\n\n## Pipeline\n\n![Pipeline](https://raw.githubusercontent.com/brandtkilian/MSE-SkyViewFactor/master/figures/pipeline.png)\n\n1. Correct projection and keep only the 180° (half sphere) above horizontal from images. The projection is corrected with a calibration image on which a graduated perfect arc circle is taken on photograph, the radius function is then interpolated.\n2. Segment image using Image Processing algorithms or trained SegNet (SegNet is much more better)\n3. Compute Sky View Factor\n\n![Sky view factor computing](https://raw.githubusercontent.com/brandtkilian/MSE-SkyViewFactor/master/figures/svf_algo.png)\n\nThe sky view factor is computed with an iterative algorithm (a kind of integral computation) knowing the angle of each circles. The algorithm is presented in the paper [Holmer Björn, A simple operative method for determination of sky\nview factors in complex urban canyons from fisheye photographs, January 1992. Web. 04\nJune 2017](http://bit.ly/2rzb2zT)\n\n## A SegNet segmented image with the three classes segmented (overlay)\n\nJust an image to show the segmentation results by SegNet\n![Segmentation results](https://raw.githubusercontent.com/brandtkilian/MSE-SkyViewFactor/master/figures/segmentationoverlay.jpg)\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrandtkilian%2Fmse-skyviewfactor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrandtkilian%2Fmse-skyviewfactor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrandtkilian%2Fmse-skyviewfactor/lists"}