Human visual perception forms different levels of abstractions expressing the essential semantic components in the scene at different scales. For real-world applications such as driving scene perception, abstractions of both coarse-level, such as the spatial presence of the lead vehicle, and the fine-level, such as the words on a traffic sign, serve as important signals for driver's decision making. However, the granularities of perception required for levels of abstractions are generally different. While current computer vision research makes significant progress in tasks of understanding the global scene (image classification), and dense scene (semantic segmentation), our work takes steps to explore the gap in between. In this paper, we propose Multi-class Probability Pyramid as a representation built on the top of pixel-level semantic scene labels. This representation forms region-level abstractions by controlling the granularity of local semantic information, and thus disentangles the variation of scene semantics at different resolutions. We further show how such representation can be effectively used for evaluation purposes, including interpretable evaluation of scene segmentation and unsupervised diagnosis of segmentation predictions.
Perceptual Evaluation of Driving Scene Segmentation
2021 IEEE Intelligent Vehicles Symposium (IV) ; 1444-1450
11.07.2021
5880106 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
PERCEPTUAL EVALUATION OF DRIVING SCENE SEGMENTATION
British Library Conference Proceedings | 2021
|Video Scene Interpretation Using Perceptual Prominence and Mise-en-scene Features
British Library Conference Proceedings | 2006
|Region-based image segmentation evaluation via perceptual pooling strategies
British Library Online Contents | 2018
|Perceptual Saliency Weighted Segmentation Algorithm
British Library Conference Proceedings | 1999
|