TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases
This work addresses a domain-specific problem in logistics for high-accuracy detection of regularly shaped objects, but it is incremental as it builds on existing methods like CornerNet.
The paper tackled the problem of detecting objects using four arbitrary vertices instead of bounding boxes, specifically for logistics packaging structure recognition, and achieved a 9% higher accuracy in transport unit side detection compared to a previous Mask R-CNN-based solution.
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.