Single-Shot Clothing Category Recognition in Free-Configurations with Application to Autonomous Clothes Sorting

TL;DR

This paper introduces a robust single-shot clothing category recognition method using novel 2.5D features, integrated into an autonomous sorting system with high accuracy on a new dataset, advancing state-of-the-art performance.

Contribution

The paper presents a new single-shot recognition approach with BSP and TSD features, achieving high accuracy and robustness for unknown clothing in unconstrained configurations, integrated into an autonomous sorting system.

Findings

Achieved 83.2% classification accuracy on unseen clothing items.

Outperformed previous state-of-the-art by 36.2%.

Successfully integrated into an autonomous robot sorting system.

Abstract

This paper proposes a single-shot approach for recognising clothing categories from 2.5D features. We propose two visual features, BSP (B-Spline Patch) and TSD (Topology Spatial Distances) for this task. The local BSP features are encoded by LLC (Locality-constrained Linear Coding) and fused with three different global features. Our visual feature is robust to deformable shapes and our approach is able to recognise the category of unknown clothing in unconstrained and random configurations. We integrated the category recognition pipeline with a stereo vision system, clothing instance detection, and dual-arm manipulators to achieve an autonomous sorting system. To verify the performance of our proposed method, we build a high-resolution RGBD clothing dataset of 50 clothing items of 5 categories sampled in random configurations (a total of 2,100 clothing samples). Experimental results show that our approach is able to reach 83.2\% accuracy while classifying clothing items which were previously unseen during training. This advances beyond the previous state-of-the-art by 36.2\%. Finally, we evaluate the proposed approach in an autonomous robot sorting system, in which the robot recognises a clothing item from an unconstrained pile, grasps it, and sorts it into a box according to its category. Our proposed sorting system achieves reasonable sorting success rates with single-shot perception.