Results 71 to 80 of about 2,071 (151)

An Adaptive Hierarchical Framework With Contrastive Aggregation for Traffic Sign Classification

IEEE Open Journal of Intelligent Transportation Systems
Autonomous vehicles rely on accurate traffic sign classification, which is typically achieved through supervised learning. However, the diversity and complexity of traffic signs make it impractical to rely solely on large labeled datasets. While abundant
Rodolfo Valiente, Jiejun Xu, Alireza Esna Ashari   +2 more
doaj   +1 more source

Stereo matching from monocular images using feature consistency

IET Image Processing, Volume 18, Issue 10, Page 2540-2552, 21 August 2024.
Abstract Synthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between ...
Zhongjian Lu, An Chen, Hongxia Gao, Langwen Zhang, Congyu Zhang, Yang Yang   +5 more
wiley   +1 more source

Towards high‐definition vector map construction based on multi‐sensor integration for intelligent vehicles: Systems and error quantification

IET Intelligent Transport Systems, Volume 18, Issue 8, Page 1477-1493, August 2024.
This paper presents an open‐source and generic high‐definition vector map (HDVM) generation pipeline. Meanwhile, an error propagation scheme is first formed to illustrate how multiple error sources fundamentally influence the accuracy of the HDVM. Abstract A lightweight, high‐definition vector map (HDVM) enables fully autonomous vehicles.
Runzhi Hu, Shiyu Bai, Weisong Wen, Xin Xia, Li‐Ta Hsu   +4 more
wiley   +1 more source

Aplicación para visualizar y contextualizar rutas en la Universidad de Alicante [PDF]

, 2016
Se pretende desarrollar una aplicación que utilice datos de rutas de paseo y ocio establecidas en el campus de la Universidad de Alicante y que ayude a los usuarios a su realización mediante la visualización de información acerca del contexto de la ruta.
Martínez Rueda, Carlos
core  

Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

, 2019
Most progress in semantic segmentation reports on daytime images taken under favorable illumination conditions. We instead address the problem of semantic segmentation of nighttime images and improve the state-of-the-art, by adapting daytime models to ...
Dai, Dengxin, Sakaridis, Christos, Van Gool, Luc   +2 more
core   +1 more source

Humanitarian Mapping within a Student Association: PoliMappers [PDF]

, 2017
The lack of availability and accessibility of open geospatial data, especially in developing countries is addressed by various volunteer mapping associations.
Frassinelli, Francesco, Kilsedar, CANDAN EYLÜL, Minghini, Marco, Montani, Michael, Oxoli, Daniele   +4 more
core  

FieldSAFE: Dataset for Obstacle Detection in Agriculture

, 2017
In this paper, we present a novel multi-modal dataset for obstacle detection in agriculture. The dataset comprises approximately 2 hours of raw sensor data from a tractor-mounted sensor system in a grass mowing scenario in Denmark, October 2016.
Christiansen, Peter, Green, Ole, Jørgensen, Rasmus Nyholm, Karstoft, Henrik, Kragh, Mikkel Fly, Larsen, Morten, Laursen, Morten Stigaard, Steen, Kim Arild   +7 more
core   +2 more sources

PanDA: Panoptic Data Augmentation [PDF]

, 2019
The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel panoptic data
Liu, Yang, Meister, Markus, Perona, Pietro   +2 more
core   +1 more source

DP-Loc: Visual Localization in 2D Maps Using an Embedded Depth Prior

IEEE Access
Recent advancements in cost-effective image-based localization using 2D maps have garnered significant attention, inspired by humans’ ability to navigate with such maps.
Kyoung Eun Kim, Joo Yong Sim
doaj   +1 more source

AutoDIAL: Automatic DomaIn Alignment Layers

, 2017
Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains.
Bulò, Samuel Rota, Caputo, Barbara, Carlucci, Fabio Maria, Porzi, Lorenzo, Ricci, Elisa   +4 more
core   +1 more source