Rethinking Object Detection in Retail Stores

TL;DR

This paper introduces a new object detection task called Locount for retail stores, focusing on localizing and counting object groups under occlusion, supported by a large dataset and a baseline network.

Contribution

It proposes the Locount task, creates a large annotated dataset, and develops a cascaded network baseline for simultaneous localization and counting.

Findings

The dataset contains over 1.9 million instances across 140 categories.

The baseline network achieves promising results on the new benchmark.

Analysis of failure cases suggests directions for future research.

Abstract

The convention standard for object detection uses a bounding box to represent each individual object instance. However, it is not practical in the industry-relevant applications in the context of warehouses due to severe occlusions among groups of instances of the same categories. In this paper, we propose a new task, ie, simultaneously object localization and counting, abbreviated as Locount, which requires algorithms to localize groups of objects of interest with the number of instances. However, there does not exist a dataset or benchmark designed for such a task. To this end, we collect a large-scale object localization and counting dataset with rich annotations in retail stores, which consists of 50,394 images with more than 1.9 million object instances in 140 categories. Together with this dataset, we provide a new evaluation protocol and divide the training and testing subsets to fairly evaluate the performance of algorithms for Locount, developing a new benchmark for the Locount task. Moreover, we present a cascaded localization and counting network as a strong baseline, which gradually classifies and regresses the bounding boxes of objects with the predicted numbers of instances enclosed in the bounding boxes, trained in an end-to-end manner. Extensive experiments are conducted on the proposed dataset to demonstrate its significance and the analysis discussions on failure cases are provided to indicate future directions. Dataset is available at https://isrc.iscas.ac.cn/gitlab/research/locount-dataset.