Precise Detection in Densely Packed Scenes
TL
TL;DR
This work proposes a novel, deep-learning based method for precise object detection, designed for such challenging settings as packed retail environments, and shows the method to outperform existing state-of-the-art with substantial margins.
Abstract
Man-made scenes are often 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.
References53 items
1
Divide and Count: Generic Object Counting by Image Divisions
2
Deep Learning for Generic Object Detection: A Survey
3
Acquisition of Localization Confidence for Accurate Object Detection
4
Improving Object Localization with Fitness NMS and Bounded IoU Loss
5