Obtaining an accurate vehicle position is important for intelligent vehicles in supporting driver safety and comfort. This paper proposes an accurate ego-localization method by matching in-vehicle camera images to an aerial image. There are two major problems in performing an accurate matching: (1) image difference between the aerial image and the in-vehicle camera image due to view-point and illumination conditions, and (2) occlusions in the in-vehicle camera image. To solve the first problem, we use the SURF image descriptor, which achieves robust feature-point matching for the various image differences. Additionally, we extract appropriate feature-points from each road-marking region on the road plane in both images. For the second problem, we utilize sequential multiple in-vehicle camera frames in the matching. The experimental results demonstrate that the proposed method improves both ego-localization accuracy and stability.
Accurate vehicle positioning is important not only for in-car navigation systems but is also a requirement for emerging autonomous driving methods. Consumer level GPS are inaccurate in a number of driving environments such as in tunnels or areas where tall buildings cause satellite shadowing. Current vision-based methods typically rely on the integration of multiple sensors or fundamental matrix calculation which can be unstable when the baseline is small. In this paper we present a novel visual localization method which uses a visual street map and extracted SURF image features. By monitoring the difference in scale of features matched between input images and the visual street map within a Dynamic Time Warping framework, stable localization in the direction of motion is achieved without calculation of the fundamental or essential matrices. We present the system performance in real traffic environments. By comparing localization results with a high accuracy GPS ground truth, we demonstrate that accurate vehicle positioning is achieved.
Numerous applications such as autonomous driving, satellite imagery sensing, and biomedical imaging use computer vision as an important tool for perception tasks. For Intelligent Transportation Systems (ITS), it is required to precisely recognize and locate scenes in sensor data. Semantic segmentation is one of computer vision methods intended to perform such tasks. However, the existing semantic segmentation tasks label each pixel with a single object's class. Recognizing object attributes, e.g., pedestrian orientation, will be more informative and help for a better scene understanding. Thus, we propose a method to perform semantic segmentation with pedestrian attribute recognition simultaneously. We introduce an attribute-aware loss function that can be applied to an arbitrary base model. Furthermore, a re-annotation to the existing Cityscapes dataset enriches the ground-truth labels by annotating the attributes of pedestrian orientation. We implement the proposed method and compare the experimental results with others. The attribute-aware semantic segmentation shows the ability to outperform baseline methods both in the traditional object segmentation task and the expanded attribute detection task.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.