Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving

TL;DR

This paper introduces a new automated method for evaluating the robustness of semantic segmentation models in autonomous driving, using additional sensors and metrics to assess performance across diverse environmental conditions.

Contribution

The paper presents a novel sensor-augmented approach for automated robustness analysis of semantic segmentation models, reducing manual labeling and enabling comprehensive performance validation.

Findings

Segmentation performance varies with weather and lighting conditions.

Metrics effectively compare model performance under different environmental scenarios.

Sensor fusion improves failure detection in vision-based perception systems.

Abstract

One of the fundamental challenges in the design of perception systems for autonomous vehicles is validating the performance of each algorithm under a comprehensive variety of operating conditions. In the case of vision-based semantic segmentation, there are known issues when encountering new scenarios that are sufficiently different to the training data. In addition, even small variations in environmental conditions such as illumination and precipitation can affect the classification performance of the segmentation model. Given the reliance on visual information, these effects often translate into poor semantic pixel classification which can potentially lead to catastrophic consequences when driving autonomously. This paper presents a novel method for analysing the robustness of semantic segmentation models and provides a number of metrics to evaluate the classification performance over a variety of environmental conditions. The process incorporates an additional sensor (lidar) to automate the process, eliminating the need for labour-intensive hand labelling of validation data. The system integrity can be monitored as the performance of the vision sensors are validated against a different sensor modality. This is necessary for detecting failures that are inherent to vision technology. Experimental results are presented based on multiple datasets collected at different times of the year with different environmental conditions. These results show that the semantic segmentation performance varies depending on the weather, camera parameters, existence of shadows, etc.. The results also demonstrate how the metrics can be used to compare and validate the performance after making improvements to a model, and compare the performance of different networks.