Self-supervised classification of dynamic obstacles using the temporal information provided by videos

TL;DR

This paper introduces a self-supervised framework for classifying dynamic obstacles in videos based on their motion patterns, reducing reliance on labeled data and outperforming existing unsupervised methods.

Contribution

A novel self-supervised approach that learns offline clusters from temporal video patches to train real-time obstacle classifiers in autonomous driving.

Findings

Outperforms state-of-the-art unsupervised classification methods on BDD100K dataset.

Effectively classifies dynamic obstacles using motion patterns without labeled data.

Provides a scalable solution for obstacle classification in autonomous driving.

Abstract

Nowadays, autonomous driving systems can detect, segment, and classify the surrounding obstacles using a monocular camera. However, state-of-the-art methods solving these tasks generally perform a fully supervised learning process and require a large amount of training labeled data. On another note, some self-supervised learning approaches can deal with detection and segmentation of dynamic obstacles using the temporal information available in video sequences. In this work, we propose to classify the detected obstacles depending on their motion pattern. We present a novel self-supervised framework consisting of learning offline clusters from temporal patch sequences and considering these clusters as labeled sets to train a real-time image classifier. The presented model outperforms state-of-the-art unsupervised image classification methods on large-scale diverse driving video dataset BDD100K.