BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments

TL;DR

This paper introduces an unsupervised domain adaptation method for semantic segmentation in unstructured driving environments, achieving high accuracy and robustness in complex real-world traffic scenarios.

Contribution

It proposes a novel unsupervised domain adaptation technique with a self-training algorithm for multi-source data, improving scene understanding in unstructured traffic environments.

Findings

Achieves 87.18% accuracy on India Driving Dataset.

Improves state-of-the-art performance by 5.17% to 42.9%.

Effectively identifies new objects during testing in unstructured environments.

Abstract

We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians. We describe a new semantic segmentation technique based on unsupervised domain adaptation (DA), that can identify the class or category of each region in RGB images or videos. We also present a novel self-training algorithm (Alt-Inc) for multi-source DA that improves the accuracy. Our overall approach is a deep learning-based technique and consists of an unsupervised neural network that achieves 87.18% accuracy on the challenging India Driving Dataset. Our method works well on roads that may not be well-marked or may include dirt, unidentifiable debris, potholes, etc. A key aspect of our approach is that it can also identify objects that are encountered by the model for the fist time during the testing phase. We compare our method against the state-of-the-art methods and show an improvement of 5.17% - 42.9%. Furthermore, we also conduct user studies that qualitatively validate the improvements in visual scene understanding of unstructured driving environments.