# Precise Detection in Densely Packed Scenes

## TL;DR

This paper introduces a deep-learning approach for precise object detection in densely packed scenes, featuring a new quality estimation layer, an EM merging unit, and a large annotated dataset, achieving superior results over existing methods.

## Contribution

The paper presents a novel deep-learning method with a Jaccard index estimation layer, an EM merging unit, and a new dataset for densely packed scene detection.

## Key findings

- Outperforms state-of-the-art detectors on SKU-110K, CARPK, and PUCPR+ datasets.
- Provides a new dataset SKU-110K for densely packed retail environments.
- Demonstrates significant improvements in detection accuracy in crowded scenes.

## Abstract

Man-made scenes can be densely packed, containing numerous objects, often identical, positioned in close proximity. We show that precise object detection in such scenes remains a challenging frontier even for state-of-the-art object detectors. We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings. Our contributions include: (1) A layer for estimating the Jaccard index as a detection quality score; (2) a novel EM merging unit, which uses our quality scores to resolve detection overlap ambiguities; finally, (3) an extensive, annotated data set, SKU-110K, representing packed retail environments, released for training and testing under such extreme settings. Detection tests on SKU-110K and counting tests on the CARPK and PUCPR+ show our method to outperform existing state-of-the-art with substantial margins. The code and data will be made available on \url{www.github.com/eg4000/SKU110K_CVPR19}.