TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases

TL;DR

TetraPackNet is a novel four-corner-based object detection model designed for logistics applications, achieving higher accuracy than previous methods by focusing on precise corner detection of regularly shaped objects.

Contribution

The paper introduces TetraPackNet, a new model based on CornerNet, tailored for four-corner object detection in logistics, demonstrating improved accuracy over existing solutions.

Findings

TetraPackNet outperforms Mask R-CNN by 9% in accuracy.

The model effectively detects four corners of transport units.

Superior performance on real-world logistics dataset.

Abstract

While common image object detection tasks focus on bounding boxes or segmentation masks as object representations, we consider the problem of finding objects based on four arbitrary vertices. We propose a novel model, named TetraPackNet, to tackle this problem. TetraPackNet is based on CornerNet and uses similar algorithms and ideas. It is designated for applications requiring high-accuracy detection of regularly shaped objects, which is the case in the logistics use-case of packaging structure recognition. We evaluate our model on our specific real-world dataset for this use-case. Baselined against a previous solution, consisting of a Mask R-CNN model and suitable post-processing steps, TetraPackNet achieves superior results (9% higher in accuracy) in the sub-task of four-corner based transport unit side detection.