[ 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, remote biometric analysis, and non-cooperative face recognition. 1
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.
This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries.
To help understand how TownCentre has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Oxford Town Centre was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location.
The dataset citations used in the visualizations were collected from Semantic Scholar, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to trainĀ or test machine learning algorithms.
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. 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.
Several researchers have posted their demo videos using the Oxford Town Centre dataset on YouTube:
[ add visualization ]
TODO
Benfold, Ben and Reid, Ian. "Stable Multi-Target Tracking in Real-Time Surveillance Video". CVPR 2011. Pages 3457-3464.
"Guiding Visual Surveillance by Tracking Human Attention". 2009.