Update README.md

In order to solve the practical industrial application problems and promote the academic research of the problem, we put forward the necessary elements of the task: 

In order to solve the practical industrial application problems and promote the academic research of the problem, we put forward the necessary elements of the task: 

*problem definition*, *Locount dataset*, *evaluation protocol* and *baseline method*. This work was accepted by the International Artificial Intelligence Conference AAAI 2021.

*problem definition*, *Locount dataset*, *evaluation protocol* and *baseline method*. This work was accepted by the International Artificial Intelligence Conference AAAI 2021.

![Figure 1: The previous object recognition datasets in grocery stores have focused on image classification, i.e., (a) Supermarket

!["Figure 1: The previous object recognition datasets in grocery stores have focused on image classification, i.e., (a) Supermarket

Produce (Rocha et al. 2010) and (b) Grozi-3.2k (George and Floerkemeier 2014), and object detection, i.e., (c) D2S (Follmann

Produce (Rocha et al. 2010) and (b) Grozi-3.2k (George and Floerkemeier 2014), and object detection, i.e., (c) D2S (Follmann

et al. 2018), (d) Freiburg Groceries (Jund et al. 2016), and (e) Sku110k (Goldman et al. 2019). We introduce the Loccount task,

et al. 2018), (d) Freiburg Groceries (Jund et al. 2016), and (e) Sku110k (Goldman et al. 2019). We introduce the Loccount task,

aiming to localize groups of objects of interest with the numbers of instances, which is natural in grocery store scenarios, shown

aiming to localize groups of objects of interest with the numbers of instances, which is natural in grocery store scenarios, shown

in the last row, i.e., (f), (g), (h), (i), and (j). The numbers on the right hand indicate the numbers of object instances enclosed in

in the last row, i.e., (f), (g), (h), (i), and (j). The numbers on the right hand indicate the numbers of object instances enclosed in

the bounding boxes. Different colors denotes different object categories. Best viewed in color and zoom in.](Images/dataset-comparison.jpg)

the bounding boxes. Different colors denotes different object categories. Best viewed in color and zoom in."](Images/dataset-comparison.jpg)

<div align=center><img src="Images/dataset-comparison.jpg" width="900" height="400" /></div>

<div align=center><img src="Images/dataset-comparison.jpg" width="1100" height="400" /></div>

## Locount dataset

## Locount dataset

To solve the above issues, we collect a large-scale object localization and counting dataset at 28 different stores and apartments, which consists of 50,394 images with the JPEG image resolution of 1920x1080 pixels. 

To solve the above issues, we collect a large-scale object localization and counting dataset at 28 different stores and apartments, which consists of 50,394 images with the JPEG image resolution of 1920x1080 pixels.