SCD: A Stacked Carton Dataset for Detection and Segmentation

TL;DR

This paper introduces a large-scale carton dataset called SCD for detection and segmentation, along with a novel detector that improves accuracy and generalizes well across datasets.

Contribution

The paper provides the first large-scale carton dataset and proposes a new detection method with modules that enhance localization and boundary attention.

Findings

SCD contains 250,000 instance masks from 16,136 images.

The proposed detector improves AP by 3.1%-4.7% on SCD.

OPCL module enhances generalization, improving AP on MS COCO and PASCAL VOC.

Abstract

Carton detection is an important technique in the automatic logistics system and can be applied to many applications such as the stacking and unstacking of cartons, the unloading of cartons in the containers. However, there is no public large-scale carton dataset for the research community to train and evaluate the carton detection models up to now, which hinders the development of carton detection. In this paper, we present a large-scale carton dataset named Stacked Carton Dataset(SCD) with the goal of advancing the state-of-the-art in carton detection. Images are collected from the internet and several warehourses, and objects are labeled using per-instance segmentation for precise localization. There are totally 250,000 instance masks from 16,136 images. In addition, we design a carton detector based on RetinaNet by embedding Offset Prediction between Classification and Localization module(OPCL) and Boundary Guided Supervision module(BGS). OPCL alleviates the imbalance problem between classification and localization quality which boosts AP by 3.1% - 4.7% on SCD while BGS guides the detector to pay more attention to boundary information of cartons and decouple repeated carton textures. To demonstrate the generalization of OPCL to other datasets, we conduct extensive experiments on MS COCO and PASCAL VOC. The improvement of AP on MS COCO and PASCAL VOC is 1.8% - 2.2% and 3.4% - 4.3% respectively.