Výsledky vyhledávání - "Happold, Michael"

Report

MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion

Autor: Zhang, Ce, Zhang, Chengjie, Guo, Yiluan, Chen, Lingji, Happold, Michael

Multiple Object Tracking (MOT) is crucial to autonomous vehicle perception. End-to-end transformer-based algorithms, which detect and track objects simultaneously, show great potential for the MOT task. However, most existing methods focus on image-b

Externí odkaz: http://arxiv.org/abs/2306.17000

Zobrazit plný text záznamu

Report

ADCNet: Learning from Raw Radar Data via Distillation

Autor: Yang, Bo, Khatri, Ishan, Happold, Michael, Chen, Chulong

As autonomous vehicles and advanced driving assistance systems have entered wider deployment, there is an increased interest in building robust perception systems using radars. Radar-based systems are lower cost and more robust to adverse weather con

Externí odkaz: http://arxiv.org/abs/2303.11420

Zobrazit plný text záznamu

Report

Joint Pose and Shape Estimation of Vehicles from LiDAR Data

Autor: Goforth, Hunter, Hu, Xiaoyan, Happold, Michael, Lucey, Simon

We address the problem of estimating the pose and shape of vehicles from LiDAR scans, a common problem faced by the autonomous vehicle community. Recent work has tended to address pose and shape estimation separately in isolation, despite the inheren

Externí odkaz: http://arxiv.org/abs/2009.03964

Zobrazit plný text záznamu

Report

Geometry-Aware Instance Segmentation with Disparity Maps

Autor: Wu, Cho-Ying, Hu, Xiaoyan, Happold, Michael, Xu, Qiangeng, Neumann, Ulrich

Most previous works of outdoor instance segmentation for images only use color information. We explore a novel direction of sensor fusion to exploit stereo cameras. Geometric information from disparities helps separate overlapping objects of the same

Externí odkaz: http://arxiv.org/abs/2006.07802

Zobrazit plný text záznamu

Report

Hierarchical Deep Stereo Matching on High-resolution Images

Autor: Yang, Gengshan, Manela, Joshua, Happold, Michael, Ramanan, Deva

We explore the problem of real-time stereo matching on high-res imagery. Many state-of-the-art (SOTA) methods struggle to process high-res imagery because of memory constraints or speed limitations. To address this issue, we propose an end-to-end fra

Externí odkaz: http://arxiv.org/abs/1912.06704

Zobrazit plný text záznamu