paper-with-me

Papers

STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction

2020-05-08 · CVPR 2020 6 · Zhishuai Zhang, Jiyang Gao, Junhua Mao, Yukai Liu, Dragomir Anguelov, Cong-Cong Li

Detecting pedestrians and predicting future trajectories for them are critical tasks for numerous applications, such as autonomous driving. Previous methods either treat the detection and prediction as separate tasks or simply add a trajectory regression head on top of a detector. In this work, we present a novel end-to-end two-stage network: Spatio-Temporal-Interactive Network (STINet). In addition to 3D geometry modeling of pedestrians, we model the temporal information for each of the pedestrians. To do so, our method predicts both current and past locations in the first stage, so that each pedestrian can be linked across frames and the comprehensive spatio-temporal information can be captured in the second stage. Also, we model the interaction among objects with an interaction graph, to gather the information among the neighboring objects. Comprehensive experiments on the Lyft Dataset and the recently released large-scale Waymo Open Dataset for both object detection and future trajectory prediction validate the effectiveness of the proposed method. For the Waymo Open Dataset, we achieve a bird-eyes-view (BEV) detection AP of 80.73 and trajectory prediction average displacement error (ADE) of 33.67cm for pedestrians, which establish the state-of-the-art for both tasks.

📄 PDF Abstract BibTeX arXiv:2005.04255

Code (0)

등록된 구현이 없습니다.

Tasks

3D geometryAutonomous Drivingobject-detectionObject DetectionPedestrian DetectionTrajectory Prediction

Similar Papers 제목 키워드 기반

Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework

2021-03-23 · Kaihao Zhang, Dongxu Li, Wenhan Luo, Wenqi Ren 외

Video deraining is an important task in computer vision as the unwanted rain hampers the visibility of videos and deteriorates the robustness of most outdoor vision systems. Despite the significant success which has been…

Rain RemovalVideo deraining

Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting

2021-09-29 · Rui Zhou, HongYu Zhou, Huidong Gao, Masayoshi Tomizuka 외

Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a long-standing challenge. Recent advances in using data-driven approaches have achieved significant improvements in …

Trajectory ForecastingTrajectory Prediction

Spatiotemporal Stacked Sequential Learning for Pedestrian Detection

2014-07-14 · Alejandro González, Sebastian Ramos, David Vázquez, Antonio M. López 외

Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential …

Pedestrian Detection

A Spatio-temporal Graph Network Allowing Incomplete Trajectory Input for Pedestrian Trajectory Prediction

2025-01-22 · Juncen Long, Gianluca Bardaro, Simone Mentasti, Matteo Matteucci

Pedestrian trajectory prediction is important in the research of mobile robot navigation in environments with pedestrians. Most pedestrian trajectory prediction algorithms require the input historical trajectories to be …

Pedestrian Trajectory PredictionPredictionRobot NavigationTrajectory Prediction

Strip-Fusion: Spatiotemporal Fusion for Multispectral Pedestrian Detection

2026-01-25 · Asiegbu Miracle Kanu-Asiegbu, Nitin Jotwani, Xiaoxiao Du arxiv

Pedestrian detection is a critical task in robot perception. Multispectral modalities (visible light and thermal) can boost pedestrian detection performance by providing complementary visual information. Several gaps rem…

Pedestrian Detection