VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection
- 20 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 27 (2) , 261-271
Abstract
Traffic light detection is crucial for environment perception and decision-making in autonomous driving. State-of-the-art detectors are built upon deep Convolutional Neural Networks (CNNs) and have exhibited promising performance. However, one looming concern with CNN based detectors is how to thoroughly evaluate the performance of accuracy and robustness before they can be deployed to autonomous vehicles. In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications. The disentangled representation learning extracts data semantics to augment human cognition with human-friendly visual summarization, and the semantic adversarial learning efficiently exposes interpretable robustness risks and enables minimal human interaction for actionable insights. We also demonstrate the effectiveness of various performance improvement strategies derived from actionable insights with our visual analytics system, VATLD, and illustrate some practical implications for safety-critical applications in autonomous driving.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- "Why Should I Trust You?"2016
- Towards Better Analysis of Deep Convolutional Neural NetworksIEEE Transactions on Visualization and Computer Graphics, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Visualizing Object Detection FeaturesInternational Journal of Computer Vision, 2016
- Fast R-CNN2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Mutual Information between Discrete and Continuous Data SetsPLOS ONE, 2014
- The human is the loop: new directions for visual analyticsJournal of Intelligent Information Systems, 2014
- Diagnosing Error in Object Detectors2012
- Hierarchical Grouping to Optimize an Objective FunctionJournal of the American Statistical Association, 1963