SmartCity
Introduced by Zhang et al. in Crowd counting via scale-adaptive convolutional neural network
SmartCity consists of 50 images in total collected from ten city scenes including office entrance, sidewalk, atrium, shopping mall etc.. Unlike the existing crowd counting datasets with images of hundreds/thousands of pedestrians and nearly all the images being taken outdoors, SmartCity has few pedestrians in images and consists of both outdoor and indoor scenes: the average number of pedestrians is only 7.4 with minimum being 1 and maximum being 14.
Source: SmartCityPapers
| Paper | Code | Results | Date | Stars |
|---|
