diff options
| author | adamhrv <adam@ahprojects.com> | 2019-04-05 14:09:19 +0200 |
|---|---|---|
| committer | adamhrv <adam@ahprojects.com> | 2019-04-05 14:09:19 +0200 |
| commit | 7cc03d5914ce3fb634516d27973ccb69ee63fe8d (patch) | |
| tree | f7c9ba3e165208bc98abf4c0ffce8cf28e312f96 /site/content/pages/datasets/oxford_town_centre/index.md | |
| parent | b73e233acec5ad6c3aca7475288482f366f7a31f (diff) | |
updating
Diffstat (limited to 'site/content/pages/datasets/oxford_town_centre/index.md')
| -rw-r--r-- | site/content/pages/datasets/oxford_town_centre/index.md | 19 |
1 files changed, 13 insertions, 6 deletions
diff --git a/site/content/pages/datasets/oxford_town_centre/index.md b/site/content/pages/datasets/oxford_town_centre/index.md index b3bce9af..d2d37230 100644 --- a/site/content/pages/datasets/oxford_town_centre/index.md +++ b/site/content/pages/datasets/oxford_town_centre/index.md @@ -21,21 +21,28 @@ authors: Adam Harvey [ page under development ] -The Oxford Town Centre dataset is a video of pedestrians in a busy downtown area in Oxford used for creating surveillance algorithms with "potential applications in activity recognition and remote biometric analysis" or non-cooperative face recognition. [^ben_benfold_orig] +The Oxford Town Centre dataset is a video of pedestrians in a busy downtown area in Oxford used for creating surveillance algorithms with potential applications in activity recognition, remote biometric analysis, and non-cooperative face recognition. [^ben_benfold_orig] -Based on observations of the dataset video and Google Street images, the source of the footage has been geolocated to a public CCTV camera at the intersection of Cornmarket and Market St. Oxford, England ([map](https://www.google.com/maps/@51.7528347,-1.2581078,3a,90y,324.38h,101.91t/data=!3m6!1e1!3m4!1s3uTXi12qVnI35DnDJbDofg!2e0!7i13312!8i6656)). Based on an analysis of the papers that use or cite this dataset [^guiding_surveillance] the inferred year of capture was definitely 2009 and the season was perhaps February or March based on the the window advertisements and cool-weather clothing. - -Halfway through the video a peculiar and somewhat rude man enters the video and stands directly over top a water drain for over a minute. His unusual demeanor and apparently scripted behavior suggests a possible relationship to the CCTV operators. +REVISE Although Oxford Town Centre dataset first appears as a pedestrian dataset, it was created to improve the stabilization of pedstrian detections in order to extract a more accurate head region that would lead to improvements in face recognition. - - {% include 'dashboard.html' %} {% include 'supplementary_header.html' %} +### Location + +The street location of the camera used for the Oxford Town Centre dataset can be easily confirmed using only two visual clues in video: the GAP store and the main road [source](https://www.google.com/maps/@51.7528162,-1.2581152,3a,50.3y,310.59h,87.23t/data=!3m7!1e1!3m5!1s3FsGN-PqYC-VhQGjWgmBdQ!2e0!5s20120601T000000!7i13312!8i6656). The camera angle and field of view indicate that the camera was elevated and placed at the corner. The edge of the building is visible and there is a small white nylon strap and pigeon deterrent spikes visible on the upper perimeter of the building. Combined with stability of camera and pigeon appearances in front of the camera at 1:24 and 3:29, these visual cues indicate that the camera was mounted outside on the corner of the building just above the deterrence spikes. + + + +Halfway through the video a peculiar and somewhat rude man enters the video and stands directly over top a water drain for over a minute. His unusual demeanor and apparently scripted behavior suggests a possible relationship to the CCTV operators. + +### Demo Videos Using Oxford Town Centre Dataset + Several researchers have posted their demo videos using the Oxford Town Centre dataset on YouTube: + - [Multi target tracking on Oxford Dataset](https://www.youtube.com/watch?v=nO-3EM9dEd4) - [Multi-pedestrian tracking (TownCentre dataset)]https://www.youtube.com/watch?v=nO-3EM9dEd4 - [Multiple object tracking with kalman tracker and sort](https://www.youtube.com/watch?v=SKXk6uB8348) |
