SeekNet: Improved Human Instance Segmentation and Tracking via Reinforcement Learning Based Optimized Robot Relocation

TL;DR

SeekNet is a reinforcement learning-based optimization method that enhances amodal human recognition and tracking in crowded environments, improving accuracy for social robots and multi-robot systems in real-world scenarios.

Contribution

The paper introduces SeekNet, a novel reinforcement learning approach for optimized robot relocation to improve amodal recognition and tracking of occluded humans in dynamic, crowded settings.

Findings

Significant improvement in occluded human detection accuracy.

Enhanced tracking performance over baseline methods.

Effective multi-robot identification of disease markers.

Abstract

Amodal recognition is the ability of the system to detect occluded objects. Most SOTA Visual Recognition systems lack the ability to perform amodal recognition. Few studies have achieved amodal recognition through passive prediction or embodied recognition approaches. However, these approaches suffer from challenges in real-world applications, such as dynamic obstacles. We propose SeekNet, an improved optimization method for amodal recognition through embodied visual recognition. Additionally, we implement SeekNet for social robots, where there are multiple interactions with crowded pedestrians. We also demonstrate the benefits of our algorithm on occluded human detection and tracking over other baselines. Additionally, we set up a multi-robot environment with SeekNet to identify and track visual disease markers for airborne disease in crowded areas. We conduct our experiments in a simulated indoor environment and show that our method enhances the overall accuracy of the amodal recognition task and achieves the largest improvement in detection accuracy over time in comparison to the baseline approaches.