SmartCity

SmartCity 共包含 50 张图像，从办公室入口、人行道、中庭、购物中心等 10 个城市场景收集。与现有的人群计数数据集（包含数百/千行人的图像以及几乎所有在户外拍摄的图像）不同，SmartCity 具有图像中的行人很少，由室外和室内场景组成：平均行人数仅为 7.4，最小为 1，最大为 14。

The SmartCity dataset consists of 50 images collected from 10 urban scene categories including office entrances, sidewalks, atriums, shopping malls and other scenarios. Unlike existing crowd counting datasets, which usually contain images with hundreds or thousands of pedestrians and are almost exclusively captured outdoors, SmartCity features a sparse number of pedestrians in each image and covers both outdoor and indoor scenes. The average number of pedestrians per image is only 7.4, with the minimum being 1 and the maximum being 14.

搜集汇总

背景与挑战

背景概述

SmartCity数据集包含50张图像，采集自办公室入口、人行道等10个城市场景，平均行人数为7.4，范围从1到14，与常规人群计数数据集相比，其行人较少且包含室内外场景。