Semantic segmentation is a critical component in autonomous driving and has to be thoroughly evaluated due to safety concerns. Deep neural network (DNN) based semantic segmentation models are widely used in autonomous driving. However, it is challenging to evaluate DNN-based models due to their black-box-like nature, and it is even more difficult to assess model performance for crucial objects, such as lost cargos and pedestrians, in autonomous driving applications. In this work, we propose VASS, a Visual Analytics approach to diagnosing and improving the accuracy and robustness of Semantic Segmentation models, especially for critical objects moving in various driving scenes. The key component of our approach is a context-aware spatial representation learning that extracts important spatial information of objects, such as position, size, and aspect ratio, with respect to given scene contexts. Based on this spatial representation, we first use it to create visual summarization to analyze models' performance. We then use it to guide the generation of adversarial examples to evaluate models' spatial robustness and obtain actionable insights. We demonstrate the effectiveness of VASS via two case studies of lost cargo detection and pedestrian detection in autonomous driving. For both cases, we show quantitative evaluation on the improvement of models' performance with actionable insights obtained from VASS.

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.

Abstract We propose an efficient approach for authoring dynamic and realistic waterfall scenes based on an acquired video sequence. Traditional video based techniques generate new images by synthesizing 2D samples, i.e., texture sprites chosen from a video sequence. However, they are limited to one fixed viewpoint and cannot provide arbitrary walkthrough into 3D scenes. Our approach extends this scheme by synthesizing dynamic 2D texture sprites and projecting them into 3D space. We first generate a set of basis texture sprites, which capture the representative appearance and motions of waterfall scenes contained in the video sequence. To model the shape and motion of a new waterfall scene, we interactively construct a set of flow lines taking account of physical principles. Along each flow line, the basis texture sprites are manipulated and animated dynamically, yielding a sequence of dynamic texture sprites in 3D space. These texture sprites are displayed using the point splatting technique, which can be accelerated efficiently by graphics hardware. By choosing varied basis texture sprites, waterfall scenes with different appearance and shapes can be conveniently simulated. The experimental results demonstrate that our approach achieves realistic effects and real‐time frame rates on consumer PC platforms. Copyright © 2006 John Wiley & Sons, Ltd.